MACHINE LEARNING FOR PREDICTING ION TRAP FILL FUNCTIONS

Abstract

Systems / techniques are provided to support the prediction of ion trap filling functions using machine learning. In various embodiments, a system can access a requested ion population size. In different aspects, the system can instruct a mass analyzer to perform a scan using an injection time that correlates with the requested ion population size through an ion trap filling function, whereby a set of coefficients of the ion trap filling function can be predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer.

Description

BACKGROUND Supporting the automatic gain control of a mass analyzer can be considered a significant task. SUMMARY The following is a summary to provide a basic understanding of one or more embodiments. This summary is not intended to identify key or critical elements or to define the scope of the respective embodiments or the scope of the claims. Its sole purpose is to present concepts in a simplified form as an introduction to the more detailed description to follow. One or more embodiments described herein comprise devices, systems, computerized methods, apparatus, or computer program products that enable machine learning-based prediction of ion trap filling functions. A system according to one or more embodiments is provided. The system may include non-transitory computer-readable memory capable of storing computer-executable components. The system may further include a processor that can be operationally coupled to the non-transitory computer-readable memory and that can execute the computer-executable components stored in the non-transitory computer-readable memory. In various embodiments, the computer-executable components may include an access component capable of accessing a requested ion population size.In various embodiments, the computer-executable components can include a scan component that causes a mass analyzer to perform a scan using an injection time that correlates with the requested ion population size by an ion trap filling function, wherein a coefficient set of the ion trap filling function can be predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. According to one or more embodiments, a computer-aided method is provided. In various embodiments, the computer-aided method may involve accessing a requested ion population size by a device operationally coupled to a processor. In various aspects, the computer-aided method may consist of the device instructing a mass analyzer to perform a scan using an injection time correlated with the requested ion population size via an ion trap filling function, wherein a set of coefficients for the ion trap filling function can be predicted using a machine learning model based on a current operating parameter configuration of the mass analyzer. According to one or more embodiments, a computer program product is provided to support the prediction of ion trap filling functions by machine learning. In various embodiments, the computer program product may include a non-transitory, computer-readable memory containing program instructions. In various aspects, the program instructions may be executable by a processor, allowing the processor to access a requested ion population size.In various cases, the program instructions may be further executable, so that the processor instructs a mass analyzer to perform a scan using an injection time correlated with the requested ion population size by an ion trap filling function, where a coefficient set of the ion trap filling function is predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. DESCRIPTION OF THE DRAWINGS Various embodiments are easily understood through the following detailed description in conjunction with the accompanying figures. To aid this description, identical reference numbers denote identical structural elements. In the figures, embodiments are presented by way of example and not as limitations. The figures are not necessarily to scale. Fig. 1 shows an exemplary, non-limiting block diagram of a scientific instrument module according to various embodiments described herein. Fig. 2 shows an exemplary, non-limiting flow diagram of a computer-aided method according to various embodiments described herein. Fig. 3 shows a block diagram of an exemplary, non-limiting system that enables the prediction of ion trap filling functions by machine learning according to one or more embodiments described herein.Figure 4 shows a block diagram of an exemplary, non-restrictive system comprising an ion trap filling function consisting of a set of coefficients, a set of fitted coefficient values, a machine learning model, and a training dataset, which supports the prediction of ion trap filling functions by machine learning according to one or more embodiments described herein. Figures 5-8 show exemplary, non-restrictive block diagrams illustrating how a set of fitted coefficient values ​​for an ion trap filling function can be obtained according to one or more embodiments described herein. Figure 9 shows a block diagram of an exemplary, non-restrictive system with a specified ion injection time, which supports the prediction of ion trap filling functions by machine learning according to one or more embodiments described herein.Figures 10-12 are exemplary, non-restrictive block diagrams showing how a specific ion injection time can be achieved using an ion trap filling function with adjusted coefficient values ​​according to one or more embodiments described herein. Figure 13 is a block diagram of an exemplary, non-restrictive system with a resulting ion population that supports the prediction of ion trap filling functions using machine learning according to one or more embodiments described herein. Figure 14 is an exemplary, non-restrictive block diagram showing how a resulting ion population size can be used to update a machine learning model according to one or more embodiments described herein.Figure 15 presents an exemplary, non-limiting graphic illustrating a difference between linear and non-linear ion trap filling models according to one or more embodiments described herein. Figure 16 illustrates exemplary, non-limiting experimental data according to one or more embodiments described herein. Figure 17 presents a block diagram of an exemplary, non-limiting operating environment in which one or more embodiments described herein can be implemented. Figure 18 presents an exemplary network environment in which various implementations described herein can be executed. DETAILED DESCRIPTION The following detailed description serves only for illustration and is not intended to limit the embodiments or the applications / uses of the embodiments. Furthermore, there is no intention to be bound by the express or implied information set forth in the preceding "Background" or "Summary" sections or in the "Detailed Description" section. One or more embodiments will now be described with reference to the drawings, using the same reference numerals throughout for identical elements. For explanatory purposes, numerous specific details are set forth in the following description to facilitate a more thorough understanding of the one or more embodiments. However, it is evident in several cases that the one or more embodiments can be implemented without these specific details. It is also evident that new embodiments may arise from combining the embodiments described herein and / or from omitting certain features from the embodiments described therein, where appropriate. Various processes may be described as several discrete actions or operations performed sequentially in a manner most helpful for understanding the subject matter disclosed herein. However, the order of description should not be interpreted as implying that these processes are necessarily dependent on the order in which they are presented. In particular, these processes may be performed in a different order than the order in which they are presented. The described operations may be performed in a different order than in the described embodiments. Various additional operations may be performed, or the described operations may be omitted in additional embodiments. Although some elements may be referred to in the singular (e.g., "a process device"), all corresponding elements may be represented by multiple instances of that element, and vice versa. For example, a set of operations described as being performed by a process device may be implemented with different operations being performed by different process devices. As used herein, the phrase "based on" should be understood to mean "at least partially based on" unless otherwise specified. A mass spectrometer coupled to a chromatograph can be considered a type of scientific instrument that can be used in a scientific, laboratory, research, or clinical operational context or environment to determine the chemical composition of unknown samples. To support such a determination of chemical composition, the mass spectrometer or chromatograph may include a complex array of actuated parts (e.g., ion sources, ion lenses, heaters, condensers, columns, ovens, injectors, mass analyzers, liquid valves, liquid pumps, circuit isolators), sensors (e.g., ion detectors, voltmeters, thermistors, potentiometers, pressure gauges), or consumables (e.g., carrier fluids, calibrators, filters). A mass analyzer can be considered a particularly complex component of a mass spectrometer. A mass analyzer separates (or in some cases, measures without physically separating) ions based on their mass-to-charge ratio (based on their -m / z values), allowing all chemical species that comprise a sample or sample to be identified or quantified. Different mass analyzers have different physical designs, constructions, or operating principles (e.g., quadrupole mass analyzers versus time-of-flight mass analyzers or orbital falling mass analyzers). For a mass analyzer to function properly (e.g.,In order to correctly, accurately, or reliably distinguish ions based on their mass-to-charge ratio, the mass analyzer (or the mass spectrometer of which it is a component) must be able to automatically determine the injection time required to achieve a given or desired ion population size. Such a determination is called automatic gain control. More specifically, a mass analyzer can use, consist of, or otherwise be associated with (e.g., be located downstream of) ion trap hardware. This ion trap hardware can accumulate ions emitted from or originating from a particular ion source. Automatic gain control can be considered the task or process of controlling how many ions are physically trapped or accumulated in such ion trap hardware at any given time. The proper, accurate, or otherwise reliable performance of automatic gain control can improve the quality of the spectral data produced by the mass analyzer. In fact, this process can help to mitigate space charge effects within the mass analyzer.Furthermore, this can help ensure that the accumulated ion population within the ion trap hardware remains within a measurable dynamic range of the mass analyzer. It can also ensure that the accumulated ion population within the ion trap hardware is sufficient for the specific acquisition or scanning technique used. The proper, accurate, or otherwise reliable execution of automatic gain control can degrade or compromise the quality of the spectral data generated by the mass analyzer. In particular, overcrowding the ion trap hardware can lead to mass discrimination (where, for example, low or high mass-to-charge ratios are lost), detector saturation, or spectral artifacts (e.g., global m / z ratio shift, Gibbs free oscillations). Existing techniques perform automatic gain control by estimating and linearly scaling an ion flux. More precisely, existing techniques first obtain or estimate a flux ion injection time and a flux ion population size. The flux ion injection time can be very short (e.g., only milliseconds) and is sometimes referred to as the "pre-scan" or "flux scan." The flux ion population size can be viewed as the number of ions that accumulate in the ion trap hardware of a mass analyzer in response to that hardware implementing the flux ion injection time.In other words, the pre-scan or flow scan can be a scan that corresponds to, relates to, or contains (in terms of the types of trapped ions) the scan for which the injection time is to be estimated, and the ion population size can be the measured ion population of the flow scan or a portion of the measured ion population relevant to the scan for which the injection time is to be estimated. When a target population size is given, existing techniques always scale the flow ion injection time by assuming that the ion trap hardware accumulates ions linearly with respect to time. Specifically, existing techniques scale the flow ion injection time by the ratio formed between the target ion population size and the flow ion population size.In other words, existing techniques either conclude or determine that the target ion population size can be achieved by an ion injection time that corresponds to this linearly scaled version of the flux ion injection time. The reliability of existing techniques is adequate when the target ion population size is close to the flux ion population size. However, the reliability of such techniques decreases significantly as the target ion population size deviates further and further from the flux ion population size. Unfortunately, the flux ion population size can sometimes be extremely small (e.g., due to a very short flux ion injection time), and since the target ion population size can sometimes be very large (e.g., many times larger than the flux ion population size), automatic gain control using such existing techniques may not be performed properly or reliably. Accordingly, systems or techniques that can improve the reliability or accuracy of automatic gain control may be desirable. Several embodiments described herein can solve this technical problem. The one or more embodiments described herein comprise systems, computer-aided methods, devices, or computer program products that enable machine learning-based prediction of ion trap filling functions. In particular, the inventors of several embodiments described herein have recognized that, contrary to the numerical assumptions of existing techniques, the ion trap hardware of a mass analyzer actually behaves nonlinearly in a manner that depends uniquely on the specific properties or attributes of that ion trap hardware.In fact, the inventors mentioned here recognized that the way in which the ion trap hardware accumulates ions as a function of time can be considered to depend, in an exponential growth pattern, on the pseudopotential trap depth of the ion trap hardware, the trap radius of the ion trap hardware, and the Coulomb repulsion of the accumulated ions in the ion trap hardware. The inventors mentioned here recognized that, although the pseudopotential trap depth, the trap radius, and the Coulomb repulsion are often not directly measurable or controllable in real time, such properties or attributes can be considered to be indirectly controlled, influenced, or otherwise correlated with various operating parameters of the ion trap hardware (e.g., scan range; isolation width).In other words, such operating parameters can be viewed as directly measurable or directly configurable proxies that accurately represent or depict the pseudopotential trap depth, trap radius, and Coulomb repulsion. Given a current or present operating parameter configuration of the ion trap hardware, various embodiments described herein may involve the use of machine learning to predict or derive a specific nonlinear function (e.g., an exponential growth function) that describes, expresses, represents, or otherwise models the actual accumulation behavior of this ion trap hardware.By using this predicted or derived nonlinear function, any estimated ion flux can be scaled to accurately or reliably scale any target ion population size as desired, regardless of how far the target ion population size is from the estimated ion flux. This contrasts with existing techniques whose reliability deteriorates as the target ion population size deviates from the estimated ion flux. Several embodiments described herein can be considered a computer-based tool (e.g., any suitable combination of computer-based hardware or computer-executable software) that can support machine learning-based prediction of ion trap filling functions. In various aspects, such a computer-based tool may include an access component, a model component, a scan component, or a feedback component. In various embodiments, a mass spectrometer can be operationally coupled or uncoupled with a chromatograph in a suitable manner. In various aspects, the mass spectrometer can comprise any suitable constituent hardware (e.g., any suitable ion beam emitter; any suitable ion detector; any suitable optical ion equipment). In various cases, this constituent hardware can include a mass analyzer having a suitable design, construction, or architecture (e.g., quadrupole mass filter analyzer, time-of-flight (TOF) analyzer, electrostatic falling or orbital falling mass analyzer (e.g., ORBITRAP™), or Fourier transform ion cyclotron resonance (FT-ICR) mass analyzer). In various cases, the mass analyzer may incorporate or be associated with any suitable type of ion trap hardware, and such ion trap hardware may incorporate any suitable type of configurable operating parameter. In various aspects, a configurable operating parameter may be any suitable selectively controllable property or setting that governs the behavior of the ion trap hardware and that can be directly adjusted or changed in response to electronic instructions or commands received from a user. Such configurable operating parameters may include, for example, a scan range implemented by the mass analyzer; first, last, or central masses of an upstream quadrupole mass analyzer; or an isolation width implemented by the mass analyzer.In various cases, the configurable operating parameters of the ion trap hardware of the mass analyzer may have a current or present configuration (e.g., they may currently be set to specific or certain values). In any case, it may be desirable for the mass analyzer to perform a scan on any suitable sample or species using an ion population size requested by a user or technician (e.g., specified by the user or technician via a graphical user interface of the mass analyzer). In various aspects, the computer-aided tool can support such a scan as described herein. In various embodiments, the access component of the computerized tool can access the mass spectrometer electronically. That is, the access component can establish an electronic connection with the mass spectrometer, allowing all other components of the computerized tool to interact electronically with the mass spectrometer and thus with the mass analyzer (e.g., send electronic instructions to the mass spectrometer or read electronic signals from the mass spectrometer). Accordingly, the access component can electronically receive, retrieve, or otherwise obtain the following: the current configuration of the operating parameters of the ion trap hardware; or the requested ion population size. Therefore, each other component of the computerized tool can interact with the following (e.g.,(read, write, edit, copy, manage, use): the current or present configuration of the operating parameters of the ion trap hardware; or the requested ion population size. In various embodiments, the model component of the computer-based tool can electronically store, manage, control, or otherwise access an ion trap filling function. In various aspects, the ion trap filling function can be any suitable nonlinear mathematical function (e.g., an exponential growth function) that takes an ion population size (or a normalized version thereof) as an input parameter and produces an ion injection time (or a normalized version thereof) as an output, which is required to achieve the input ion population size. It should be understood or otherwise acknowledged that in some cases, the ion trap filling function can accept any other suitable input parameters as desired or required (e.g.,In some situations, it can receive a flux ion injection time and a flux ion population size as input, in addition to a given or desired ion population size. In various cases, the ion trap filling function can be defined by a set of coefficients, the numerical application of which to the population size of the input ions yields the injection time of the output ions. Accordingly, the specific ion injection time that the ion trap filling function produces as output for any given input ion population size can depend on which values ​​are chosen, selected, or used for the set of coefficients.In various cases, the model component can electronically determine or calculate which specific values ​​of the coefficient set would cause the ion trap filling function to accurately or reliably represent or model the temporary ion accumulation within the mass analyzer's ion trap hardware, based on the current configuration of the ion trap hardware's configurable operating parameters. In various aspects, the model component can support such a determination or calculation by utilizing a machine learning model. In particular, the model component can electronically store, manage, control, or otherwise access the ML model. In various aspects, the ML model can have any suitable internal architecture for artificial intelligence. For example, the ML model can have any suitable type of internal architecture of a neural network for deep learning. For instance, the ML model can contain any suitable number of suitable types of layers (e.g., input layer, one or more hidden layers, output layer, each of which can be a convolution layer, a dense layer, an LSTM (Long Short-Term Memory) layer, a transformer layer, a nonlinearity layer, a pooling layer, a batch normalization layer, or a padding layer). As another example, the ML model can include any suitable number of neurons in different layers (e.g.,Different layers can have the same or a different number of neurons. As another example, the machine learning model can include all suitable activation functions (e.g., softmax, sigmoid, hyperbolic tangent, rectified linear unit) in different neurons. Similarly, the machine learning model can include all suitable interneuron connections or interlayer connections (e.g., forward connections, jumping connections, recurring connections). In other cases, however, the ML model can also have any other suitable type of internal architecture (e.g., a support vector machine architecture, a random forest regressor architecture, a naive Bayesian architecture). Regardless of its specific internal architecture, the machine learning model can be viewed as a type of regressor capable of mapping, linking, or otherwise correlating the following: values ​​of the configurable operating parameters of the ion trap hardware; to values ​​for the coefficient set of the ion trap filling function. That is, the machine learning model can be configured to receive any given parameter configuration of the ion trap hardware as input and calculate as output coefficient values ​​that would cause the ion trap filling function to accurately and reliably reproduce the actual transient accumulation behavior of any hardware using that particular parameter configuration of the ion trap hardware. Accordingly, in various embodiments, the model component can execute the machine learning model on the current configuration of the ion trap hardware's operating parameters, and such execution can yield customized or user-defined values ​​for the coefficient set of the ion trap filling function. As a non-restrictive example, let's assume that the machine learning model is a deep learning neural network. In such a case, the model component can pass the current configuration of the ion trap hardware's operating parameters to an input layer of the machine learning model.In various aspects, the current configuration can perform a forward pass through one or more hidden layers of the machine learning model, and an output layer of the machine learning model can compute or calculate the fitted or user-defined coefficient values ​​based on any hidden activations generated by the hidden layers. In various cases, the fitted or user-defined coefficient values ​​can be considered any specific values ​​of the coefficient set that would cause the ion trap filling function to accurately or reliably replicate the real accumulation behavior of the mass analyzer's ion trap hardware. For the various embodiments described herein to function properly, the machine learning model can first be trained. The model component can support such training in various ways (e.g., in a supervised manner), as described later herein. In various embodiments, the scan component of the computer-aided tool can electronically determine an ion injection time that, when implemented by the ion trap hardware of the mass analyzer, would achieve the requested ion population size, by using the fitted or user-defined coefficient values ​​predicted by the machine learning model. As a non-restrictive example, the scan component can assign the fitted or user-defined coefficient values ​​to the coefficient set of the ion trap filling function, thereby causing the ion trap filling function to take a specific or particular shape, and the scan component can then pass the requested ion population size as an input parameter to the ion trap filling function. In some cases, any scalar output generated by the ion trap filling function can be considered a specific ion injection time.In other cases, this scalar output may be multiplied by a flux ion injection time and divided by the result obtained from applying the ion trap filling functions to a flux ion population size achieved when the mass analyzer implements this flux ion injection time. The numerical result of such operations can be considered the specified ion injection time. In various cases, the scan component can electronically instruct the mass analyzer to perform a scan using the specified ion injection time (e.g., on each suitable sample) as soon as the specified ion injection time is obtained. In various embodiments, the feedback component of the computer-based tool can electronically update the machine learning model in real time or in online learning mode. As a non-restrictive example, the feedback component can measure the actual ion population size achieved within the mass analyzer as a result of implementing a specific ion injection time. In various aspects, the feedback component can calculate any suitable error (e.g., mean absolute error) between the requested and measured ion population sizes. In some cases, the feedback component can incrementally update internal parameters (e.g., weighting matrices, bias values) of the machine learning model (e.g., via backpropagation) based on these errors. In any case, various embodiments described herein can be considered to support automatic gain control via artificial intelligence prediction of the nonlinear ion accumulation behavior of a mass analyzer. Compared to existing techniques that erroneously assume linear ion accumulation behavior, such embodiments can more accurately calculate the ion injection times required to achieve the desired ion population sizes. The various embodiments described here can be used to solve highly technical problems (e.g., supporting the prediction of ion trap filling functions through machine learning) using hardware or software. These problems are not abstract and cannot be performed by a human as a series of mental actions. Furthermore, some of the processes can be carried out by a specialized computer (e.g., mass spectrometers coupled with liquid, gas, or ion chromatograms; deep learning neural networks consisting of weight matrices or convolutional kernels) to perform defined actions related to the field of automatic gain control. Such defined actions may include, for example: accessing a requested ion population size from a device operationally coupled to a processor; and instigating, using the device, a scan by a mass analyzer using an injection time correlated with the requested ion population size via an ion trap filling function, wherein a set of coefficients for the ion trap filling function is predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. In some aspects, such defined actions may also include: passing the current operating parameter configuration from the device as input to the machine learning model, the machine learning model generating the set of coefficients as output. Such defined actions are inherently computerized. A mass spectrometer is indeed a highly technical, computerized device consisting of specific computerized hardware (e.g., temperature sensors, pressure sensors, voltage sensors, ion beam emitters, electron beam emitters, focusing lenses, ion detectors, electron detectors, beam apertures, fluid valves). A mass spectrometer, the processes it performs, and the mass spectra it acquires cannot be implemented in a reasonable or practical way by the human mind, or by a person using only pen and paper, without a computer. Furthermore, a mass analyzer is a specific, concrete piece of hardware in various scientific instruments that separates, arranges, orders, measures, or otherwise distinguishes ions according to their mass-to-charge ratio.A mass analyzer and its ion discrimination functionality cannot be implemented in any way by the human mind or by a person using only pen and paper. Furthermore, machine learning models, such as artificial neural networks, are inherently computerized constructs that incorporate specific software-oriented architectures (e.g., input layers, hidden layers, or output layers, each of which may consist of trainable or untrainable internal parameters, such as convolutional layers or LSTM layers). Machine learning models cannot be adequately or practically trained, executed, or updated by the human mind or by a person using only pen and paper without a computer. Furthermore, various embodiments described herein can practically apply different principles from the field of automatic gain control. As explained above, automatic gain control is the task or process of determining which injection time yields the desired ion population size when implemented by a mass analyzer or any ion trap hardware associated with the mass analyzer. Existing techniques enable automatic gain control by estimating an ion flux and subsequently scaling this estimated ion flux according to a linear ion trap filling function. Such existing techniques produce increasingly inaccurate or incorrect results as the desired ion population size deviates from the estimated ion flux, which can be considered undesirable. Several embodiments described herein can help to resolve this technical problem. In particular, several embodiments described herein can utilize machine learning to predict a nonlinear ion trap filling function (e.g., an exponential growth function) that represents the actual ion accumulation behavior associated with the mass analyzer. Specifically, several embodiments described herein can involve training a machine learning model to predict exponential growth coefficients based on input ion trap parameter configurations. Thus, for each given ion trap parameter configuration, the machine learning model can be executed to derive which specific exponential growth coefficients describe the ion accumulation behavior exhibited or caused by that given ion trap parameter configuration.These predicted or derived exponential growth coefficients can therefore be used to nonlinearly scale any estimated ion flux to any desired ion population size, regardless of how far the desired ion population size is from the estimated ion flux. In this way, various embodiments described herein can perform automatic gain control more accurately or reliably compared to existing techniques that assume a linear ion trap filling function regardless of the ion trap's operating parameter configuration. Furthermore, it must be emphasized how counterintuitive several of the embodiments described herein are. Indeed, several of the embodiments described herein can be considered highly unusual, strange, creative, or unexpected applications or uses of machine learning. After all, as explained above, automatic gain control is usually performed by linearly scaling an estimated ion flux to a desired ion population size. Conventional efforts aimed at increasing the accuracy or reliability of automatic gain control focus in the short term on improving or correcting the ion flux estimate (e.g., so that linear scaling is applied to a corrected or improved ion flux estimate rather than a crude or uncorrected one).In other words, such conventional efforts treat linear scaling as an established, immutable, or unquestionable step within automatic gain control. In stark contrast to such conventional doctrines, several embodiments described herein replace linear scaling with nonlinear scaling, such nonlinear scaling being performed using a nonlinear function whose defining coefficients are derived or predicted via machine learning. Therefore, several embodiments described herein can be viewed as a clever use of machine learning that completely contradicts the conventional doctrines of the field of automatic gain control. For at least the reasons stated above, the various embodiments described herein can be considered as means that address or improve upon various technical problems or disadvantages of existing techniques. Therefore, the various embodiments described herein can be regarded as a concrete and tangible technical improvement or effect in the field of automatic gain control. Accordingly, the various embodiments described herein are certainly considered useful and practical applications of computers. Furthermore, various embodiments described herein can control real physical devices based on the disclosed teachings. For example, various embodiments described herein can electronically activate, deactivate, or otherwise operate real hardware (e.g., ion traps) of real mass analyzers. Fig. 1 shows an exemplary, non-restrictive block diagram of a scientific instrument module 102 according to various embodiments described herein. In various embodiments, the scientific instrument module 102 can be implemented by circuits (e.g., including electrical or optical components), such as a programmed computer. The logic of the scientific instrument module 102 can be contained in a single computer or distributed across several computer devices that communicate with each other, as required. Examples of computer devices that can implement the scientific instrument module 102, individually or in combination, are discussed herein with reference to Fig. 17, and examples of systems or networks of interconnected computer devices in which the scientific instrument module 102 can be implemented on one or more of the computer devices are discussed herein with reference to Fig. 18. The scientific instrument module 102 can comprise a first logic 104, a second logic 106, and a third logic 108. As used herein, the term "logic" can include a device designed to perform a series of operations associated with the logic. For example, each of the logic elements included in the scientific instrument module 102 can be implemented by one or more computer devices programmed with instructions to cause one or more process devices of the computer devices to perform the associated series of operations. In a particular embodiment, a logic element can comprise one or more non-transitory computer-readable media containing instructions which, when executed by one or more process devices of one or more computer devices, cause the one or more computer devices to perform the associated series of operations.As used herein, the term "module" can refer to a collection of one or more logical elements that together perform a function associated with the module. Different logic elements within a module may take the same form or different forms. For example, part of the logic in a module may be implemented by a programmed general-purpose processing device, while another part of the logic in a module may be implemented by an application-specific integrated circuit (ASIC). In another example, the different logic elements in a module may be associated with different sets of instructions that are executed by one or more processing devices.In a module, one or more of the logic elements shown in the associated figures may be omitted; for example, a module may contain a subset of the logic elements shown in the associated figures if this module is to perform a subset of the operations discussed here with reference to this module. In various embodiments, there can be a scientific instrument corresponding to scientific instrument module 102. In various aspects, the scientific instrument can be any suitable computerized device capable of electronically measuring scientifically, clinically, or research-relevant properties, characteristics, or attributes of an analytical sample (e.g., a known or unknown mixture, compound, or accumulation of material). As a non-restrictive example, a scientific instrument can be a scanning electron microscope. In such a case, the scientific instrument can measure or determine a surface topography of the sample under investigation. As another non-restrictive example, a scientific instrument can be a transmission electron microscope.In such a case, the scientific instrument can measure or determine internal structural details of the sample being analyzed. As yet another, non-restrictive example, a scientific instrument could be an electron energy loss microscope. In such a case, the scientific instrument could measure or determine location-specific counts or intensities over a range of defined energy loss cavities or bands for the analytical sample. As a more general, non-restrictive example, a scientific instrument could be any suitable type of charged particle microscope (e.g., some types of microscopes can use beams of non-electron ions to acquire images or energy spectra, or to interact with samples in some other way). As yet another, non-restrictive example, a scientific instrument could be a mass spectrometer operationally coupled with a chromatogram.In such a case, the scientific instrument can measure or determine chromatograms (e.g., the relative abundance of compounds as a function of retention time) or mass spectra (e.g., the relative abundance of ions as a function of the mass-to-charge ratio) of the analytical sample. In each of these situations, the scientific instrument may include a mass analyzer or incorporate one in some other way. In various embodiments, the first logic 104 can involve accessing the mass analyzer or otherwise establishing electronic communication with it. In various embodiments, the second logic 106 can include the prediction, via a machine learning model, of an ion trap filling function based on a current operating parameter configuration of the mass analyzer. Specifically, the ion trap filling function can be a numerical function that takes as its input a real scalar representing the ion population size and produces as its output a real scalar representing the ion injection time. In various aspects, the ion trap filling function can be defined by different scalar coefficients that can be added, subtracted, multiplied, divided, used as exponents, raised to a power, or otherwise mathematically applied to the input ion population size to generate, calculate, or determine the output ion injection time.In any case, the machine learning model can be viewed as predicting or deriving specific values ​​of these scalar coefficients, where these specific values ​​cause the ion trap filling function to accurately or reliably reproduce the true or real (e.g., nonlinear) temporal ion accumulation behavior of the mass analyzer. In other words, the machine learning model can be viewed as identifying which specific values ​​of these scalar coefficients cause the ion trap filling function to correctly map the ion population sizes to the ion injection times required by the mass analyzer to achieve these ion population sizes. In various embodiments, the third logic 108 can involve causing the mass analyzer to perform a scan using an ion injection time that correlates with a requested ion population size via the ion trap filling function. In some cases, the ion injection time used during the scan can correspond to the result obtained when the requested ion population size is passed as input to the ion trap filling function. In other cases, the ion injection time used during the scan can correspond to a flux ion injection time that is scaled using the ion trap filling function. Accordingly, the scientific instrument module 102 can support the prediction of the ion trap filling function through machine learning. Fig. 2 shows an exemplary, non-limiting flowchart of a computer-aided method 200 according to various embodiments described herein. The operations of the computer-aided method 200 can be used in any suitable context to perform appropriate tasks (e.g., they can be performed by, or in conjunction with, the various modules, computer devices, or graphical user interfaces described with reference to Figs. 1, 17, and 18). The operations are shown once in Fig. 2 and in a specific sequence; however, they can be rearranged or repeated as desired and appropriate (e.g., different operations can be performed in parallel, depending on suitability). In various aspects, action 202 can involve carrying out initial operations that access a mass analyzer. In various cases, the initial logic 104 can carry out or otherwise enable action 202. In various embodiments, action 204 can include a second process consisting of predicting, via a machine learning model, an ion trap filling function based on a current operating parameter configuration of the mass analyzer. In various cases, the second logic 106 can perform or otherwise support action 204. In various embodiments, action 206 may include a third operation in which the mass analyzer is caused to perform a scan using an injection time that correlates with a requested ion population size by the ion trap filling function. Accordingly, the computer-aided method 200 can support the prediction of ion trap filling functions through machine learning. Fig. 3 shows a block diagram of an exemplary, non-restrictive system that enables the prediction of ion trap filling functions by machine learning according to one or more embodiments described herein. A mass spectrometer 302 can be present in various embodiments. In various aspects, the mass spectrometer 302 can be any suitable type of mass spectrometer, having any suitable design or setup for measuring the mass spectra of analytical samples. In various cases, the mass spectrometer 302 can consist of any suitable stock hardware. As a non-limiting example, the mass spectrometer 302 can include any suitable ion source or ion beam emitter, such as a matrix-assisted laser desorption / ionization (MALDI) source, an electrospray ionization (ESI) source, an atmospheric pressure chemical ionization (APCI) source, an atmospheric pressure photoionization (APPI) source, or an inductively coupled plasma (ICP) source.As another non-restrictive example, the mass spectrometer 302 can include any suitable ion detectors, such as electron multiplication detectors, microchannel plate detectors, image charge detectors, or Faraday cup detectors. As yet another non-restrictive example, the mass spectrometer 302 can include any suitable ion-optical equipment, such as ion focusing lenses, guides, or deflectors. In some cases, the mass spectrometer 302 can be any suitable type of Fourier-transform mass spectrometer. In various cases, one of the hardware components comprising the mass spectrometer 302 may be a mass analyzer 304. In various aspects, the mass analyzer 304 may have any suitable design or construction capable of physically separating ions according to their mass-to-charge ratio (or, in some cases, distinguishing them otherwise without physically separating them). As a non-restrictive example, the mass analyzer 304 may be any suitable type of quadrupole filter mass analyzer. As a non-restrictive example, the mass analyzer 304 may be any suitable type of time-of-flight mass analyzer. As a non-restrictive example, the mass analyzer 304 may be any suitable type of orbital falling mass analyzer. As yet another non-restrictive example, the mass analyzer 304 may be any suitable type of Fourier transform ion cyclotron resonance mass analyzer.As a non-restrictive example, the mass analyzer 304 can be any suitable type of magnetic sector field mass spectrometer. Depending on its specific design or construction, the mass analyzer 304 can be assumed to have, be equipped with, or otherwise be associated with any suitable type of ion trap from which the mass analyzer 304 can physically receive captured ions. As a non-limiting example, the mass analyzer 304 may have, be physically equipped with, be physically integrated into, or be physically downstream of a quadrupole ion trap. As another non-limiting example, the mass analyzer 304 may have, be physically equipped with, or be physically integrated into, or be physically located downstream of a linear ion trap. As yet another non-limiting example, the mass analyzer 304 may have a curved ion trap (e.g.,C-) may have, be physically equipped with, or be physically integrated with, or be physically located downstream of, a SLIM device (Lossless Ion Manipulation Structure) or any suitable ion trap array. As yet another non-restrictive example, the mass analyzer 304 may have, be physically equipped with, be physically integrated into, or be physically located downstream of a SLIM device (Lossless Ion Manipulation Structure) or any suitable ion trap array. Regardless of the specific type of ion trap, it can have any suitable number of any suitable types of configurable ion accumulation parameters. In various aspects, a configurable ion accumulation parameter can be any suitable hardware-related or software-related property of the ion trap of the mass analyzer 304 that can direct, influence, or otherwise prescribe how the ion trap physically captures, accumulates, collects, hosts, or stores ions, and which can be selectively controlled, modified, adjusted, or otherwise set (e.g., by a user of the mass spectrometer 302 or automatically). In some cases, such configurable ion accumulation parameters may include one or more parameters that represent or are otherwise related to a scan range of the mass analyzer 304. In fact, the scan range of the mass analyzer 304 can be considered the range or interval of mass-to-charge ratios over which the mass analyzer 304 is configured for ion detection during a scan. Any ion whose mass-to-charge ratio falls within the scan range can be considered detectable, isolable, separable, or otherwise measurable by the mass analyzer 304 (e.g., such ions may be visualized or detected in the resulting images by the mass spectrometer 302). Any ion whose mass-to-charge ratio lies outside the scan range can be considered undetectable, isolable, separable, or otherwise measurable by the mass analyzer 304 (e.g.,Such ions can be represented or detected in the resulting spectral data generated by the mass spectrometer 302. As a non-restrictive example, the configurable ion accumulation parameters can include a lower limit parameter of the scan range and an upper limit parameter of the scan range. In various aspects, the lower limit parameter of the scan range can be viewed as a real scalar variable whose magnitude indicates the lowest, minimum, smallest, or initial mass-to-charge ratio within the scan range. In various cases, the upper limit parameter of the scan range can be viewed as a real scalar variable whose magnitude indicates the highest, maximum, largest, or final mass-to-charge ratio in the scan range.As another, non-restrictive example, the configurable ion accumulation parameters can include a scan range mean parameter and a scan range width parameter. In various aspects, the scan range mean parameter can be viewed as a real scalar variable whose magnitude indicates the median, mean, or central mass-to-charge ratio within the scan range. In various cases, the scan range width parameter can be viewed as a real scalar variable whose magnitude indicates the difference between the highest and lowest mass-to-charge ratios within the scan range. In each of these cases, selectively changing (e.g., increasing or decreasing) the scan range lower limit parameter, the scan range upper limit parameter, the scan range midpoint parameter, or the scan range width parameter can produce a corresponding change (e.g.,Expanding, narrowing, or shifting) the scan range implemented by the Mass Analyzer 304. In some cases, such configurable ion accumulation parameters may include one or more parameters that represent a passage range of the mass analyzer 304 or are otherwise associated with it. In fact, the passage range of the ion trap can be considered the range or interval of mass-to-charge ratios for which the ion trap is configured to accumulate, capture, collect, detect, or store. Any ion whose mass-to-charge ratio falls within the permissible passage range can be considered as accumulable or captureable by the ion trap (e.g., such ions can subsequently be separated by the mass analyzer and thus represented or detected in the resulting spectral data generated by the mass spectrometer 302).Any ion whose mass-to-charge ratio lies outside the permissible scan range can be considered non-accumulable or non-capturable by the ion trap (e.g., such ions cannot subsequently be separated by the mass analyzer and thus cannot be represented or detected in the resulting spectral data generated by the Mass Spectrometer 302). As a non-restrictive example, the configurable ion accumulation parameters can include a lower scan range limit parameter and an upper scan range limit parameter. In various aspects, the lower scan range limit parameter can be viewed as a real scalar variable whose magnitude specifies the lowest, minimum, smallest, or initial mass-to-charge ratio within the scan range.In various cases, the upper limit parameter of the scan range can be considered a real scalar variable whose magnitude indicates the highest, greatest, largest, or ultimate mass-to-charge ratio within the scan range. As another, non-restrictive example, the configurable ion accumulation parameters may include a mean scan range parameter and a width scan range parameter. In various aspects, the mean scan range parameter can be considered a real scalar variable whose magnitude indicates the median, mean, or central mass-to-charge ratio within the scan range. In various cases, the width scan range parameter (sometimes called the isolation width parameter) can be considered a real scalar variable whose magnitude indicates the difference between the highest and lowest mass-to-charge ratios within the scan range.In each of these cases, the passage area implemented by the ion trap can be modified accordingly (e.g., widened, narrowed, or shifted) by selectively changing (e.g., increasing or decreasing) the lower limit parameter of the passage area, the upper limit parameter of the passage area, the midpoint parameter of the passage area, or the width parameter of the passage area. In some aspects, the configurable ion accumulation parameters may include one or more parameters that represent or are otherwise associated with injections from a stacked ring ion guide (SRIG) connected to the mass spectrometer 302. In fact, an SRIG can be considered an S-lens or funnel radio frequency (RF) ion guide that is physically located or attached to an input of the mass spectrometer 302. The SRIG can serve to refocus ions as they migrate from atmospheric pressure outside the mass spectrometer 302 to lower pressures or vacuum pressures inside the mass spectrometer 302.In various aspects, SRIG injections can be viewed as multiple, serial injections of ions with different or corresponding RF levels through the SRIG (and therefore with different or corresponding m / z intervals), with these ions then being stored together in the ion trap associated with the mass analyzer.304. In other words, the SRIG can be physically located upstream of the ion trap, and the SRIG injections can be viewed as filling or populating the ion trap. In several cases, the greater the number of implemented SRIG injections, the greater the diversity of the m / z distribution of those ions stored or trapped in the ion trap (e.g., full scans or any other scans that extend over or cover a large m / z range can be performed using a larger number of SRIG injections).Conversely, the lower the number of implemented SRIG injections, the lower the diversity of the m / z distribution for those ions stored or trapped in the ion trap (e.g., selective scans or any other scans that extend over or cover a narrow m / z range can be performed using a lower number of SRIG injections). As a non-restrictive example, the configurable ion accumulation parameters can include a parameter for the number of SRIG injections. In various aspects, the SRIG injection number parameter can be viewed as an integer scalar variable whose magnitude indicates how many SRIG injections (e.g., at each HF level) are implemented or used by the 302 mass spectrometer during any given scan. It should be understood or otherwise acknowledged that the mass analyzer 304 may have or otherwise be associated with any other suitable types of configurable ion accumulation parameters. In any case, all specific values ​​or states currently assigned to the configurable ion accumulation parameters of the mass analyzer 304 may be collectively referred to as the ion accumulation parameter configuration 306. As a non-restrictive example, the ion accumulation parameter configuration 306 may be one or more scalars, one or more vectors, one or more matrices, one or more tensors, one or more strings, or any suitable combination thereof, that can specify, represent, or otherwise communicate: which specific value is currently assigned to the lower limit parameter of the scan range of the mass analyzer 304; which specific value is currently assigned to the upper limit parameter of the scan range of the mass analyzer 304;which specific value is currently assigned to the mean parameter of the scan range of mass analyzer 304; which specific value is currently assigned to the width parameter of the scan range of mass analyzer 304; which specific value is currently assigned to the lower limit parameter of the passage range of the ion trap; which specific value is currently assigned to the upper limit parameter of the passage range of the ion trap; which specific value is currently assigned to the mean parameter of the passage range of the ion trap; which specific value is currently assigned to the width parameter of the passage range of the ion trap; or which specific value is currently assigned to the parameter for the number of SRIG injections of mass spectrometer 302. In various aspects, a required ion population size 308 may exist. In some cases, the required ion population size 308 may be an integer scalar whose size indicates how many ions should be accumulated in the ion trap of the mass analyzer 304 during a subsequent or upcoming scan. In other cases, the required ion population size 308 may be provided, selected, or otherwise identified electronically by a user or technician of the mass spectrometer 302, for example, through physical interaction with a graphical user interface (e.g., touchscreen, keyboard, mousepad) of the mass spectrometer 302. In order for such a subsequent or upcoming scan to be performed, it must be determined what ion injection time the ion trap of the mass analyzer 304 would require to accumulate the required ion population size 308.As described herein, a System 310 can support such a determination and such a scan. It should be noted that in some cases, System 310 can be implemented or hosted on the Mass Spectrometer 302 itself or on a suitable computer workstation connected or coupled to the Mass Spectrometer 302. In such situations, System 310 can be considered client-side (e.g., System 310 can be considered local to the Mass Spectrometer 302). In other cases, however, System 310 can be implemented or hosted remotely from the Mass Spectrometer 302, for example, in a cloud computing environment. In such situations, System 310 can be considered server-side. In various aspects, the system 310 can comprise a processor 312 (e.g., computer processing unit, microprocessor) and a non-transitory, computer-readable memory 314, which is functionally, operationally, or communicatively connected or coupled to the processor 312. The non-transitory, computer-readable memory 314 can store computer-executable instructions which, when executed by the processor 312, can cause the processor 312 or other components of the system 310 (e.g., access component 316, model component 318, scan component 320, feedback component 322) to perform one or more actions. In various embodiments, the non-transitory, computer-readable memory 314 can store computer-executable components (e.g., access component 316, model component 318, scan component 320, feedback component 322), and the processor 312 can execute the computer-executable components. In various embodiments, the system 310 can include an access component 316. In various ways, the access component 316 can electronically access the mass spectrometer 302 and thus the mass analyzer 304. That is, the access component 316 can communicate electronically with the mass spectrometer 302 in any suitable manner or otherwise interact electronically (e.g., send electronic instructions or commands to the mass spectrometer; receive electronic data from it). Accordingly, the access component 316 can act as a proxy or conduit through which other components of the system 310 can interact with, communicate with, activate, deactivate, or otherwise manipulate the mass spectrometer 302 or the mass analyzer 304.Due to such electronic communication, the access component 316 can electronically receive, query, or otherwise obtain the ion accumulation parameter configuration 306 or the requested ion population size 308. Thus, any other component of the system 310 can interact with or otherwise utilize the ion accumulation parameter configuration 306 or the requested ion population size 308. In various embodiments, the system 310 can include a model component 318. In various aspects, the model component 318, as described herein, can predict or derive coefficients for an ion trap filling function based on the ion accumulation parameter configuration 306 by executing a machine learning model. In various embodiments, the system 310 can include a scan component 320. In various cases, the scan component 320, as described herein, can identify an ion injection time that correlates with the requested ion population size 308 by the predicted coefficients of the ion trap filling function, and the scan component 320 can further cause the spectrometer 302 to perform a scan using this identified ion injection time. In various embodiments, the system 310 can include a feedback component 322. In various cases, the feedback component 322, as described herein, can perform a real-time update of the machine learning model based on a measured ion population size achieved by the identified ion injection time. It should be noted that in various cases, the access component 316, the model component 318, the scan component 320, and the feedback component 322 can be considered together as one or more software components 315 of the system 310. It should be noted that, for the sake of simplicity and illustration, the one or more software components 315 are primarily described here as four components (e.g., the access component 316, the model component 318, the scan component 320, and the feedback component 322). However, the one or more software components 315 are not limited to being implemented as precisely these four components in every embodiment.In some embodiments, the functions of these four components described herein can be combined in any suitable manner so that they can be implemented in or by fewer than four components (e.g., in some cases, a single component can perform all the functions described herein with respect to the access component 316, the model component 318, the scan component 320, and the feedback component 322). In other embodiments, the functions of these four components described herein can instead be distributed, separated, divided, or fragmented in any suitable manner so that they can be implemented in or by more than four components (e.g.,Two or more components can support the functions that can be performed by the access component 316; two or more components can support the functions that can be performed by the model component 318; two or more components can support the functions that can be performed by the scan component 320; two or more components can support the functions that can be performed by the feedback component 322). Fig. 4 shows a block diagram of an exemplary, non-restrictive system comprising an ion trap filling function consisting of a set of coefficients, a set of fitted coefficient values, a machine learning model and a training data set, which support the prediction of ion trap filling functions by machine learning according to one or more embodiments described herein. In various embodiments, the model component 318 can electronically store, manage, control, or otherwise electronically access an ion trap filling function 402. In various aspects, the ion trap filling function 402 can be any suitable numerical function or combination of numerical functions designed to model, predict, or otherwise represent the transient ion accumulation behavior of the ion trap of the mass analyzer 304. In other words, the ion trap filling function 402 can be any suitable combination of numerical operators (e.g., addition operators, subtraction operators, multiplication operators, division operators, radical operators, power operators, exponential operators, logarithmic operators, trigonometric operators, rounding operators, derivative operators, integral operators) that can convert an input parameter into an output parameter.In various cases, the input parameter of the ion trap filling function 402 can be a scalar with real values ​​representing the ion population size. Similarly, in various cases, the output argument of the ion trap filling function 402 can be a real scalar representing the injection time. That is, the ion trap filling function 402 can mathematically transform or convert an input ion population size into an output ion injection time. Such a transformation or conversion can be interpreted as meaning that the implementation of the output ion injection time by a mass analyzer ion trap will achieve the input ion population size. The ion trap filling function 402 can also be nonlinear in various aspects. Regardless of the specific structure or format of the ion trap filling function 402, it may consist of a set of coefficients 404 or be otherwise defined by them. In various cases, the set of coefficients 404 may comprise any suitable number of coefficients, each of which may be considered a real scalar variable. In various cases, the ion trap filling function 402 may be viewed as a calculation of the output ion injection time by mathematically combining the input ion population size with the set of coefficients 404 in any suitable manner. As a non-restrictive example, each coefficient of the set of coefficients 404 may be viewed as a constant that is added to, subtracted from, multiplied by, or divided by the input ion population size.As another non-restrictive example, each coefficient of coefficient set 404 can be viewed as a power or root to which the input ion population size is increased. As yet another non-restrictive example, each coefficient of coefficient set 404 can be viewed as a base whose exponent is a function of the input ion population size. For the non-restrictive illustration, it is assumed that the ion trap filling function 402 is given by the following exponential growth function: In such a case, S can represent an input ion population size, f(S) can represent a discharged ion injection time at which an ion population size of S is reached, and a, b, and c can be regarded as the set of coefficients 404 (e.g., they can be considered as three real scalars that the ion trap filling function 402 uses to mathematically converge or transform S into f(S)). In various aspects, the model component 318 can electronically identify or otherwise electronically determine a set of fitted coefficient values ​​405, each corresponding (e.g., in a one-to-one manner) to the coefficient set 404. In various cases, each of the fitted coefficient values ​​405 can be a specific scalar value that can be assigned to or otherwise inherited from a respective coefficient in the coefficient set 404. In various cases, the set of fitted coefficient values ​​405 can consist of any specific values ​​which, when assigned to or otherwise inherited from the coefficient set 404, cause the ion trap filling function 402 to accurately, precisely, correctly, or otherwise reliably represent the actual ion accumulation behavior actually or truly exhibited by the mass analyzer 304.To continue the above non-restrictive illustration, the ion trap filling function 402 is given by; the set of fitted coefficient values ​​405 can consist of three definite fixed scalar values ​​which, when assigned to or assumed by the coefficients a, b and c respectively, cause the ion trap filling function 402 to output exactly or correctly those injection times f(p) implemented by the mass analyzer 304 which would actually or truly achieve the input ion population sizes p. In various embodiments, the model component 318 can electronically identify or determine the set of fitted coefficient values ​​405 by using a machine learning model 406 that is or has been trained on a training data set 408. Figures 5-8 describe various non-restrictive aspects. Figures 5-8 are exemplary, non-restrictive block diagrams showing how a set of fitted coefficient values ​​405 for an ion trap filling function can be obtained according to one or more embodiments described herein. First, consider Fig. 5, which represents a non-restrictive exemplary embodiment of the training data set 408. In various embodiments, the training data set 408 can comprise or consist of multiple ion accumulation training parameter configurations 502. In various aspects, the multiple ion accumulation training parameter configurations 502 can comprise a total of n configurations for each suitable positive integer n > 1: a ion accumulation training parameter configuration 502(1) to a ion accumulation training parameter configuration 502(n). In various cases, each of the multiple ion accumulation training parameter configurations 502 can be a unique or distinct collection of values ​​or states that may or potentially be assigned to or assumed by the configurable ion accumulation parameters of the mass analyzer 304.Therefore, each of the multiple training parameter configurations 502 for ion accumulation can have the same format, size, or dimensionality as the ion accumulation parameter configuration 306. As a non-restrictive example, suppose that the configurable ion accumulation parameters of the mass analyzer 304 include a lower bound parameter of the scan range, an upper bound parameter of the scan range, and a mean parameter of the passage range. In such a situation, the ion accumulation training parameter configuration 502(1) can be considered the first unique or distinct tuple with lower bound, upper bound, and mean parameters that can potentially be assigned to the lower bound parameter of the scan range, the upper bound parameter of the scan range, and the mean parameter of the passage range.Similarly, the training parameter configuration 502(n) of ion accumulation in such a situation can be viewed as a unique or distinct n-tuple with lower bound, upper bound and mean, which may or potentially be assigned to the lower bound parameter of the scan range, the upper bound parameter of the scan range and the mean parameter of the passage range. In various aspects, the training dataset 408 can include or consist of multiple sets of ground truth coefficient values ​​504. In several cases, the multiple sets of ground truth coefficient values ​​504 can each correspond (e.g., in a one-to-one manner) to the multiple training parameter configurations 502 of the ion accumulation. Since the multiple training parameter configurations 502 of the ion accumulation can accordingly comprise a total of n configurations, multiple ground truth coefficient values ​​504 can comprise a total of n sets: one set of ground truth coefficient values ​​504(1) to one set of ground truth coefficient values ​​504(n).In various cases, each of the several ground truth coefficient values ​​504 can be a collection of specific scalar values ​​which, when each is assigned to the coefficient set 404, are known or are assumed to cause the ion trap filling function to correctly or exactly represent the ion accumulation behavior of the mass analyzer 304 when the mass analyzer 304 operates according to one of the several training parameter configurations 502 of the ion accumulation. As a non-restrictive example, the set of ground-truth coefficient values ​​504(1) can correspond to the training parameter configuration 502(1) of the ion accumulation. Therefore, the set of baseline coefficient values ​​504(1) can be considered as the specific or particular values ​​of the set of coefficients 404 that would cause the ion trap filling function 402 to accurately represent or model the ion accumulation behavior of the mass analyzer 304, given that the configurable ion accumulation parameters of the mass analyzer 304 have specific values ​​or states determined by training the parameter configuration 502(1) for ionization. As a non-restrictive example, the set of ground truth coefficient values ​​504(n) can correspond to the training parameter configuration 502(n) of the ion accumulation. Therefore, the set of ground truth coefficient values ​​504(n) can be considered to be the specific or particular values ​​of the coefficient set 404 that would cause the ion trap filling function 402 to correctly or accurately represent or model the ion accumulation behavior of the mass analyzer 304, provided that the configurable ion accumulation parameters of the mass analyzer 304 have any specific values ​​or states determined by the training parameter configuration 502(n) of the ion accumulation. In various cases, the multiple ground truth coefficient values ​​504 can be empirically identified. In particular, the ion population size can be plotted as opposed to the ion injection time for each of the multiple training parameter configurations 502 of the ion accumulation, and such plots can each yield or otherwise lead to the multiple sets of ground truth coefficient values ​​504. This is shown in more detail with reference to Fig. 6. As shown in Fig. 6, the model component 318 can select any one of the several training parameter configurations 502 of the ion accumulation. Such a selected configuration can be called the training parameter configuration 502(j) of the ion accumulation for any suitable positive integer j ≤ n. In various aspects, the model component 318 can cause the mass analyzer 304 to perform multiple scans (e.g., on each suitable sample or on no sample at all) using the training parameter configuration 502(j).In other words, the model component 318 can electronically instruct, command, or otherwise cause the mass analyzer 304 to perform multiple scans in sequential order, while the configurable ion accumulation parameters of the mass analyzer 304 are set or configured in any specific way—values ​​or states are specified in the ionization accumulation parameter configuration 502(j). For easier illustration and explanation, assume that the model component 318 causes the mass analyzer 304 to perform a total of p sequential scans using the training parameter configuration 502(j) for each suitable positive integer p > 1. In various aspects, the mass analyzer 304 can electronically generate or otherwise electronically record empirical data 601 as a result of these p-scans. In particular, each of these p-scans can be performed according to a unique, distinct, or respective ion injection time, and the mass spectrometer 302 can measure, as a result of this unique, distinct, or respective ion injection time, how many ions have accumulated or have accumulated in the ion trap connected to the mass analyzer 304. It should be acknowledged that such a measurement can be supported in any suitable way (e.g., by detection of an ion signal, resonance excitation and ejection, monitoring of ion decay, detection of ion fragmentation and charging, statistical estimation). In any case, the empirical data 601 can thus include several ion injection times 602 and several measured ion population sizes 604, each of which (e.g.,(in a one-to-one manner) these p scans can correspond. More precisely, the multiple ion injection times 602 can comprise a total of p times: from an ion injection time 602(1) to an ion injection time 602(p). Likewise, the multiple measured ion population sizes 604 can comprise a total of p sizes: from a measured population size 604(1) to a measured population size 604(p). In various cases, each of the multiple ion injection times 602 can be the specific ion injection time used in the respective p scan, and each of the multiple measured ion population sizes 604 can be an ion population size achieved in the ion trap during one of these respective p scans.As a non-restrictive example, the ion injection time 602(1) can be a scalar indicating the injection time used during the first scan, and the measured ion population size 604(1) can be the number of ions accumulated in the ion trap due to the ion injection time 602(1) during that first scan. As a non-restrictive example, the ion injection time 602(p) can be a scalar indicating the injection time used during the p scan, and the measured ion population size 604(p) can be the number of ions accumulated in the ion trap due to the ion injection time 602(p) during that p scan. In other words, the empirical data 601 can be viewed as a collection of p tuples, each tuple representing a corresponding ion injection time and the resulting ion population size. It should be noted that the empirical data 601 can be represented as a graph whose abscissa represents the ion population size and whose ordinate represents the ion injection time. In various aspects, the model component 318 can electronically fit the ion trap filling functions 402 to such a graph by using any suitable curve-fitting technique (e.g., the method of least squares). In various cases, such a fitting can yield or generate a set of ground-truth coefficient values ​​504(j), which can be considered as any one of the several sets of ground-truth coefficient values ​​504 corresponding to the training parameter configuration 502(j) of the ion accumulation.In other words, the act of fitting the ion trap filling function 402 to the empirical data 601 can be viewed as a repeated calculation or identification of the specific values ​​of the coefficient set 404 which minimize an error (e.g. mean squared error) between the ion trap filling function 402 and the empirical data 601, and such calculated or identified values ​​of the coefficient set 404 can be called the set of ground-truth coefficient values ​​504(j). In various aspects, the model component 318 can repeat different actions described above for each of the multiple training parameter configurations 502 of the ion accumulation, and such repetition can ultimately yield the multiple sets of ground-truth coefficient values ​​504. Now to Fig. 7. In various embodiments, the model component 318 can electronically store, manage, control, or otherwise electronically access the machine learning model 406. In various aspects, the machine learning model 406 can have any suitable internal architecture for artificial intelligence. As a non-restrictive example, the machine learning model 406 can have any suitable internal architecture of a neural network for deep learning. In fact, in various cases, the machine learning model 406 can have an input layer, one or more hidden layers, and an output layer. In various cases, any of these layers can be coupled to each other by suitable interneuron connections or interlayer connections, such as forward connections, jumping connections, or recurring connections.Furthermore, all such layers can, in various cases, be suitable types of neural network layers with appropriate internal learnable or trainable parameters. For example, any input layer, one or more hidden layers, or an output layer can be a convolutional layer whose learnable or trainable parameters can be convolutional kernels. As another example, such input layers, one or more hidden layers, or output layers can be dense layers whose learnable or trainable parameters can be weight matrices or bias values. Yet another example is that any of these input layers, one or more hidden layers, or output layers can be batch normalization layers whose learnable or trainable parameters can be shift factors or scaling factors.As another example, such input layers, one or more hidden layers, or output layers can be LSTM layers whose trainable parameters can be input state weight matrices or hidden state weight matrices. As yet another example, each of these input layers, one or more hidden layers, or output layers can be transformation layers whose trainable parameters can be single-head or multi-head attention blocks, or other weight matrices. Furthermore, in various cases, all such layers can be suitable types of neural network layers with appropriate internal fixed or non-trainable parameters. For example, each of these input layers, one or more hidden layers, or output layers can be nonlinearity layers, padding layers, pooling layers, or chaining layers.In other non-restrictive examples, however, the machine learning model 406 can have any suitable internal architecture of a non-neural network, such as an internal decision tree architecture, an internal random forest regressor architecture, an internal naive Bayes architecture, or an internal logistic regression architecture. Regardless of the specific internal architecture (e.g., the specific number, type, or organization of layers) implemented in the machine learning model 406, the model component 318 can electronically and supervisely train the machine learning model 406 using the training data set 408 to act as a regressor, or to operate as a predictor of the values ​​of the coefficient set 404 in response to the input ion accumulation parameter configurations. In particular, before the start of such training, the model component 318 can initialize the trainable internal parameters (e.g., convolutional kernels, weight matrices, bias values) of the machine learning model 406 in any suitable way (e.g., random initialization). In various cases, the model component 318 can select any suitable ion accumulation training parameter configuration and the corresponding set of ground truth coefficient values ​​from the training dataset 408. These can be referred to as the ion accumulation training parameter configuration 702 and the ground truth coefficient set 704, respectively. In various cases, the model component 318 can execute the machine learning model 406 with the ion accumulation training parameter configuration 702, causing the machine learning model 406 to produce an output 706. More precisely, we assume that the machine learning model 406 has the internal architecture of a deep learning neural network. In such a situation, the model component 318 can electronically pass the ion accumulation training parameter configuration 702 to an input layer of the machine learning model 406.In various aspects, the training parameter configuration 702 of the ion accumulation can perform a forward pass through one or more hidden layers of the machine learning model 406. In various cases, an output layer of the machine learning model 406 can compute or calculate the output 706 based on the hidden activation maps or hidden feature maps generated by the one or more hidden layers during the forward pass. Note that the format, size, or dimensionality of output 706 can be determined by the number, arrangement, size, or other properties of the neurons, convolutional kernels, attention blocks, or other internal parameters of the output layer (or any other layers) of machine learning model 406. Accordingly, output 706 can be forced into any desired format, size, or dimensionality by adding, removing, or otherwise modifying properties of the output layer (or any other layers) of machine learning model 406. In particular, output 706 can be forced to have the same format, size, or dimensionality as the set of ground-truth coefficient values ​​704.Accordingly, output 706 can be considered as the predicted or derived scalar values ​​which the machine learning model 406 assumes that, if assigned to the respective coefficient set 404, would cause the ion trap filling function 402 to accurately or reliably represent the ion accumulation behavior of the mass analyzer 304 when the mass analyzer 304 operates or functions according to the ion accumulation training parameter configuration 702.In various cases, the set of ground-truth coefficient values ​​704 can be viewed as a collection of specific scalar values ​​which, when assigned to the respective values ​​of the coefficient set 404, are known or expected to cause the ion trap filling function 402 to accurately or precisely represent the ion accumulation behavior of the mass analyzer 304 when the mass analyzer 304 operates according to the ion accumulation training parameter configurations 702. Note that the output 706 may be highly inaccurate if the machine learning model 406 has undergone little or no training. In other words, the output 706 may deviate significantly from the set of ground-truth coefficient values ​​704. In various aspects, the model component 318 can compute an error 708 (e.g., mean absolute error (MAE), mean squared error (MSE), cross-entropy error) between the output 706 and the set of ground truth coefficient values ​​704. In various cases, the model component 318 can incrementally update the trainable internal parameters of the machine learning model 406 via backpropagation (e.g., stochastic gradient descent) driven by the error 708. In various cases, the model component 318 can repeat such an execution and update procedure for any suitable number of ion accumulation training parameter configurations (e.g., for each of the multiple ion accumulation training parameter configurations 502). This can ultimately lead to the iterative optimization of the trainable internal parameters of the machine learning model 406 to accurately derive scalar values ​​of the coefficient set 404 based on input configurations of the configurable ion accumulation parameters of the mass analyzer 304. In various aspects, any suitable training batch sizes, any suitable error / loss functions, or any suitable criteria for training termination during such training can be used. Although the disclosure contained herein mainly describes the machine learning model 406, which is trained in a supervised manner, this is merely a non-limiting example for the sake of simplicity and illustration. In various embodiments, any other suitable training paradigms can be used to train the machine learning model 406, such as unsupervised training, partially supervised training, or reinforcement learning, each of which may be federated or unfederated. Now to Fig. 8. After the machine learning model 406 has been trained, the model component 318 can electronically execute the machine learning model 406 based on the ion accumulation parameter configuration 306, and such execution can cause the machine learning model 406 to generate the set of fitted coefficient values ​​405. More precisely, we assume that the machine learning model 406 has the internal architecture of a neural network for deep learning.In such a situation, the model component 318 can electronically forward the ion accumulation parameter configuration 306 to the input layer of the machine learning model 406, the ion accumulation parameter configuration 306 can complete a forward pass through the one or more hidden layers of the machine learning model 406, and the output layer of the machine learning model 406 can compute or calculate the set of fitted coefficient values ​​405 based on the hidden activation maps or hidden feature maps generated by the one or more hidden layers during the forward pass. In any case, the set of fitted coefficient values ​​405 can be considered to specify all scalar values ​​which, when assigned to the coefficient set 404, would, according to the assumption of the machine learning model 406, result in the ion trap filling function 402 correctly and accurately or reliably representing the ion accumulation behavior of the mass analyzer 304 when the mass analyzer 304 operates or functions according to the ion accumulation parameter configuration 306. Fig. 9 shows a block diagram of an exemplary, non-restrictive system with a specific ion injection time, which can support the prediction of ion trap filling functions using machine learning according to one or more embodiments described herein. In various embodiments, the scan component 320 can electronically calculate or identify a specific ion injection time 902 based on the set of adapted coefficient values ​​405. In various aspects, the specific ion injection time 902 can be a real scalar representing an ion injection time or duration expected to be needed, necessary, or required for the mass analyzer 304 to achieve the requested ion population size 308 when the mass analyzer 304 operates or functions according to the ion accumulation parameter configuration 306. Figures 10-12 describe various non-limiting aspects. Figures 10-12 are exemplary, non-restrictive block diagrams showing how the determined ion injection time 902 can be obtained using the ion trap filling function 402 with the set of adapted coefficient values ​​405 according to one or more embodiments described herein. Consider first Fig. 10. In various embodiments, the scan component 320 can electronically calculate the specified ion injection time 902 based on the set of fitted coefficient values ​​405 and the requested ion population size 308. In particular, the scan component 320 can: assign the set of fitted coefficient values ​​405 to the respective values ​​of the coefficient set 404; and introduce the requested ion population size 308 as an input parameter into the ion trap filling function 402. As a non-restrictive example, suppose that the ion trap filling function 402 is given by [equation missing in original text]. In such a case, the set of fitted coefficient values ​​405 can be assigned to a, b, and c respectively, and the specified ion injection time 902 can be equal to f(pr), where pr is the requested ion population size 308. Now to Fig. 11. In various embodiments, the scan component 320 can electronically calculate the specified ion injection time 902, based not only on the set of adapted coefficient values ​​405 and the requested ion population size 308, but also on a flux ion injection time 1102 and a flux ion population size 1104. In particular, the flux ion injection time 1102 can be any suitable ion injection time that is of short duration (e.g., only milliseconds or shorter than a suitable threshold time). In various aspects, the scan component 320 can electronically command, instruct, or otherwise cause the mass analyzer 304 (which is currently or is presently set to the ion accumulation parameter configuration 306) to perform a scan (e.g., on any suitable sample or no sample at all) according to the flux ion injection time 1102.In various cases, the scan component 320 can electronically measure the resulting ion population size accumulated in the ion trap during such a scan, and this can be referred to as the flux ion population size 1104. It should be understood or otherwise acknowledged that the flux ion injection time 1102 and the flux population size 1104 together can be referred to as an estimated ion flux associated with the mass analyzer 304. It should also be understood or otherwise acknowledged that such an estimated ion flux can be used in any suitable coarse form or in any suitable corrected form (e.g., after one or more flux correction techniques have been applied).In various cases, the scan component 320 can perform the following tasks: assigning the set of fitted coefficient values ​​405 to the respective values ​​of the coefficient set 404; passing the requested ion population size 308 as an input parameter to the ion trap filling function 402, resulting in a first value; passing the flux ion population size 1104 as an input parameter to the ion trap filling function 402, resulting in a second value; dividing the first value by the second value, resulting in a ratio; and scaling the flux ion injection time 1102 by this ratio.As a non-restrictive example, let us assume that the ion trap filling function 402 is given by In such a case, the set of fitted coefficient values ​​405 can be assigned a, b, and c respectively, and the determined ion injection time 902 can be equal to , where pr is the requested ion population size 308, where pf is the flux ion population size 1104, and where tf is the flux ion injection time 1102. Now to Fig. 12. In various embodiments, the scan component 320 can electronically calculate the specified ion injection time 902, based not only on the set of adapted coefficient values ​​405, the requested ion population size 308, the flux ion injection time 1102, and the flux ion population size 1104, but also on an ion distribution 1202. It is assumed that the mass spectrometer 302 is known or expected to perform scans with a total of q different ion species, for each suitable positive integer q. In such a case, the ion distribution 1202 can be any suitable electronic data indicating the extent to which each of these ion species q is known or expected to contribute to a particular scan.As a non-restrictive example, the ion distribution 1202 can include a contribution percentage 1202(1) of the ion species, which can be a positive real scalar expressing, in percentage form, the extent to which a first ion species used or employed by the mass spectrometer 302 is known, presumed, or expected to contribute to a particular scan. As a non-restrictive example, the ion distribution 1202 can include a contribution percentage 1202(q) of the ion species, which can be a positive real scalar expressing, in percentage form, the extent to which a q-th ion species used or employed by the mass spectrometer 302 is known, presumed, or expected to contribute to a particular scan. In various situations, the sum of all contribution percentages of the ion species to the ion distribution 1202 can be uniform (e.g., it can be 1).In various cases, the scan component 320 can perform the following tasks: assigning the set of adapted coefficient values ​​405 to the respective values ​​of the coefficient set 404; scaling, for each of the ion species q, the requested ion population size 308 by the respective contribution percentage specified in the ion distribution 1202, resulting in a total of q scaled ion population sizes; passing these q scaled ion population sizes as input parameters to the ion trap filling function 402, resulting in a total of q first values; adding all q first values, resulting in a second value; passing the flux ion population size 1104 as an input parameter to the ion trap filling function 402, resulting in a third value; dividing the second value by the third value, resulting in a ratio; and scaling the flux ion injection time 1102 by this ratio.As a non-restrictive example, let us assume that the ion trap filling function 402 is given by In such a case, the set of fitted coefficient values ​​405 can each be assigned a, b and c, and the determined ion injection time 902 can be equal to where pr is the requested ion population size 308, where pf is the flux ion population size 1104, wotf is the flux ion injection time 1102, where i is a summation index, where q is the total number of ion species implemented by the mass spectrometer 302, and where kid is the contribution percentage of the i-th ion species (as specified in the ion distribution 1202). In any case, the specific ion injection time 902 can be considered as the time interval correlated by the ion trap filling function 402 with the requested ion population size 308 when the set of fitted coefficient values ​​405 is assigned to the coefficient set 404. In other words, the specific ion injection time 902 can be considered as the ion injection time that is derived or inferred as required, necessary, or essential for the mass analyzer 304 to achieve the requested ion population size 308 when the mass analyzer 304 operates or functions according to the ion accumulation parameter configuration 306. In various aspects, the scan component 320 can electronically instruct, electronically direct, or otherwise electronically cause the mass spectrometer 302 to perform a scan (e.g., on any suitable sample or on no sample at all), using or otherwise implementing the specified ion injection time 902. Thus, it may be desired that the mass spectrometer 302 perform a scan in which the ion trap of the mass analyzer 304 reaches the requested ion population size 308, and it can be assumed that the scan component 320 fulfills this request. Fig. 13 shows a block diagram of an exemplary, non-restrictive system with a resulting ion population that can support the prediction of ion trap filling functions using machine learning according to one or more embodiments described herein. In various embodiments, the feedback component 322 can electronically measure (e.g., using any suitable ion population measurement technique) the actual ion population size achieved by the ion trap of the mass analyzer 304 when the mass spectrometer 302 performs a scan using or implementing the specified ion injection time 902. This measured ion population size can be referred to as the resulting ion population size 1302. In various aspects, the feedback component 322 can electronically update the machine learning model 406 in real time, online, or on-the-fly, based on the resulting ion population size 1302. Figure 14 describes various non-restrictive aspects. Fig. 14 presents an exemplary, non-restrictive block diagram showing how the resulting ion population size 1302 can be used to update the machine learning model 406 according to one or more embodiments described herein. In various aspects, the requested ion population size 308 can be considered the ion population size that is desired or expected to be achieved when the mass spectrometer 302 implements the specified ion injection time 902. In contrast, the resulting ion population size 1302 can be considered the ion population size actually achieved when the mass spectrometer 302 implements the specified ion injection time 902. In various cases, the feedback component 322 can electronically calculate an error 1402 (e.g., mean absolute error, mean squared error, cross-entropy error, percentage difference) between the requested ion population size 308 and the resulting ion population size 1302. In various cases, the feedback component 322 can use backpropagation (e.g., stochastic gradient descent) to train the internal parameters (e.g.,The convoluted cores and weight matrices of machine learning model 406 are incrementally updated based on error 1402. In this way, machine learning model 406 can be expected to update in real time, or on-the-fly, based on any differences between the desired ion population sizes and the ion population sizes actually generated by or over the predictions of machine learning model 406. Figure 15 presents an exemplary, non-limiting graph 1500 illustrating a difference between linear and non-linear ion trap filling models according to one or more embodiments described herein. The abscissa (e.g., horizontal) in graph 1500 represents the ion population size, while the ordinate (e.g., vertical) in graph 1500 represents the ion injection time required to achieve a given ion population size. Figure 1502 shows a linear ion trap filling model, while figure 1504 shows an ion trap filling model with exponential growth. In the notation of Figure 15, pf represents the flux ion population size 1104, tf the flux ion injection time 1102, and pr the requested ion population size 308.In various aspects, td represents the ion injection time that would be determined as needed, necessary, or required to reach przu, assuming that the ion trap accumulates ions linearly, which is unrealistic. In various cases, it represents the ion population size that td would actually reach, since the ion trap accumulates ions exponentially and not linearly. In other words, a linear ion trap filling model shows that td would reach przu, but td actually falls significantly short of przu. In various cases, it represents the ion injection time that would actually be needed, necessary, or required to reach przu, since the ion trap accumulates ions exponentially and not linearly. In other words, a linear ion trap filling model shows that td would reach przu, but a significantly longer ion injection time than td is required to reach przu. Figure 1500 helps to illustrate how existing techniques lead to degraded performance in automatic gain control and how various embodiments described herein can achieve improved or better performance in automatic gain control. In particular, when pf, t, and pr are given, existing techniques determine which ion injection time to implement, assuming a linear ion trap filling model that does not account for the actual parameters of the ion accumulation of the mass analyzer 304 (e.g., selecting existing techniques (note that this does not depend on or vary with the ion accumulation parameter configuration)). In stark contrast, various embodiments described herein can predict a nonlinear exponential growth function that better models the ion accumulation behavior of the mass analyzer 304 (e.g.,Various embodiments described herein can be selected, where g represents the predicted nonlinear exponential growth function that varies with the ion accumulation parameter configuration. Accordingly, various embodiments described herein can avoid or reduce the problem of insufficient ion injection time, a disadvantage of existing techniques. Fig. 16 illustrates exemplary, non-limiting experimental data according to one or more embodiments described herein. In particular, the present inventors have implemented one embodiment of the machine learning model 406. In one implementation, the machine learning model 406 had an internal architecture of a random forest regressor, and the ion trap filling function 402 had the following form: As described above, the training dataset 408 was obtained empirically such that each training parameter configuration of the ion accumulation corresponded to a respective representation of the ion injection time versus the measured ion population size.To evaluate the effectiveness of the machine learning model 406 after training, each plot of ion injection time against the measured ion population size was analyzed as follows: (1) the mean squared error was calculated from this plot and from each version of the ion trap filling function 402 fitted via the least squares method in this plot; and (2) the mean squared error was calculated from this plot and from each version of the ion trap filling function 402 applied by the machine learning model 406 in response to the ion accumulation training parameter configuration corresponding to this plot. As a non-restrictive example, a specific plot of ion injection time versus measured ion population size was created for the following ion accumulation parameter configuration: scan range from 50 m / z to 120 m / z; and pass range from 69 m / z to 70 m / z. The minimum sum of squares resulted in a, b, and c having the following respective values: -0.1216, 0.1197, and 0.4476. This yields a mean square error of 1.415e-4 between this first plot and the ion trap filling function 402. In contrast, the machine learning model 406 predicts that a, b, and c will have the following values: -0.1514, 0.1487, and 0.4825. This yields a mean square error of 4.151e-4 between this first plot and the ion trap filling function 402. As a non-restrictive example, a specific plot of ion injection time versus measured ion population size was created for the following ion accumulation parameter configuration: scan range from 200 m / z to 2000 m / z; and pass range from 1297 m / z to 1347 m / z. The minimum sum of squares resulted in a, b, and c having the following respective values: -0.7808, 0.7744, and 1.1903. This yields a mean square error of 4.196e-4 between this first plot and the ion trap fill function 402. In contrast, the machine learning model 406 predicts that a, b, and c will have the following values: -0.7693, 0.7635, and 1.1718. This results in a mean squared error of 4.149e-4 between this first representation and the ion trap filling function 402. The calculated mean squared errors from such an experiment are shown in graph 1600. The abscissa of graph 1600 represents the mean squared error between a given plot and the ion trap filling function 402 calculated using the least squares method. In contrast, the ordinate of graph 1600 represents the mean squared error between a given plot and the version of the ion trap filling function 402 predicted by the machine learning model 406. As shown, the mean squared errors lie exactly on the diagonal y = x, indicating that the machine learning model 406 exhibited performance closely matching that of the least sum of squares.In other words, the machine learning model 406 has successfully learned how to accurately predict the coefficients of the ion trap filling function 402 in response to input ion accumulation parameter configurations. It should be understood or otherwise acknowledged that all suitable data processing techniques (e.g., normalization) can be implemented in conjunction with all embodiments described herein. Indeed, implementing data normalization, particularly in embodiments where the specific ion injection time 902 is calculated based on the flux ion injection time 1102 and the flux ion population size 1104 (e.g., as described with reference to Fig. 11 or 12), can help promote or increase the transferability or generalizability of the machine learning model 406 across different instruments, instrument conditions, or sample conditions. Consider again, in particular, Fig. 6. As mentioned above, the empirical data 601 can be viewed as forming a representation whose abscissa represents the ion population size (e.g.,604) and whose ordinate axis represents the measured ion injection time (e.g., 602). In various aspects, the abscissa axis of such a representation can be normalized in any suitable way to range from a minimum value of 0 to a maximum value of 1. As a non-restrictive example, a maximum ion population size that may be implemented or achieved by the mass spectrometer 302 can be represented by a normalized value of 1, a zero or empty ion population size can be represented by a normalized value of 0, and each of the several ion population sizes 604 can correspond to a normalized value that proportionally indicates where that ion population size lies between that maximum ion population size and that zero or empty ion population size.As another non-restrictive example, the largest of the multiple ion population sizes 604 can be represented by a normalized value of 1, the smallest by a normalized value of 0, and each remaining multiple ion population size 604 can correspond to a normalized value that proportionally indicates where that ion population size lies between the largest and smallest ion population sizes. Similarly, the ordinate axis of such a representation can be normalized in any suitable way to range from a minimum value of 0 to a maximum value of 1.As a non-restrictive example, a maximum ion injection time that may be implemented by the mass spectrometer 302 can be represented by a normalized value of 1, an empty or non-existent ion injection time can be represented by a normalized value of 0, and each of the multiple ion injection times 602 can correspond to a normalized value that proportionally indicates where that ion injection time lies between that maximum ion injection time and that zero or non-existent internal injection time.As another non-restrictive example, the largest of the several ion injection times 602 can be represented by a normalized value of 1, the smallest of the several ion injection times 602 can be represented by a normalized value of 0, and each remaining of the several ion injection times 602 can correspond to a normalized value that proportionally indicates where that ion injection time lies between the largest and the smallest ion injection time.As another non-restrictive example, any injection time associated with the ion population size whose normalized value is 1 can be represented by a normalized value of 1, any injection time associated with the ion population size whose normalized value is 0 can be represented by a normalized value of 0, and any remaining of the multiple ion injection times 602 can correspond to a normalized value that proportionally indicates where that ion injection time lies between these normalized extreme values. In each case, if such normalization is implemented, the ion trap filling function 402 (after least sum of squares fitting) can be assumed to map the normalized ion population size to the normalized ion injection time (as opposed to mapping the coarse ion population size to the coarse ion injection time).In such situations, the training of the machine learning model 406 as described herein can result in the machine learning model 406 being configured to receive an ion accumulation parameter configuration as input and to produce as output which values ​​of the coefficient set 404 would cause the ion trap filling function 402 to properly, accurately, or reliably map the normalized ion population size to the normalized ion injection time when the mass analyzer 304 operates according to the input ion accumulation parameter configuration. Although the disclosure contained herein mainly describes various embodiments in which machine learning is applied to ion trap filling function prediction to ion traps connected to mass analyzers, these are merely non-limiting examples for ease of explanation and illustration. In various other embodiments, machine learning can be applied to any suitable ion trap, even those not connected to mass analyzers. As a non-limiting example, in some cases a linear ion trap can pass or emit captured ions into a downstream mass analyzer, or in other cases pass or emit captured ions into any other suitable type of downstream device that is not a mass analyzer.In both cases, machine learning as described herein can be used to predict the true or exact ion trap filling functions of the linear ion trap. In various cases, machine learning algorithms or models can be implemented in any suitable way to support all the appropriate aspects described herein. To support some of the machine learning aspects of various embodiments described above, the following discussion of artificial intelligence (AI) is considered. Various embodiments described herein can employ artificial intelligence to support the automated use of one or more features or functions. The components can apply various AI-based schemes to perform the various embodiments / examples disclosed herein. To provide or support the numerous provisions described herein (e.g.,Determinations (which can be described as determining, ascertaining, inferring, calculating, predicting, forecasting, estimating, inferring, anticipating, detecting, or computing) can examine all or part of the data to which they have access and, based on a series of observations recorded about events or data, infer or determine the state of the system or its environment. Determinations can be used to identify a particular context or action, or they can, for example, generate a probability distribution over states. Determinations can be probabilistic; that is, the calculation of a probability distribution over states of interest based on data and events. Determinations can also refer to techniques used to assemble events at a higher level from a series of events or data. Such provisions can lead to the creation of new events or actions from a series of observed events or stored event data, regardless of whether the events are correlated in close temporal proximity or not, and regardless of whether the events and data originate from one or more event and data sources. The components disclosed herein can employ various classification schemes (explicitly trained, e.g., via training data) as well as implicitly trained (e.g., through observation of behavior, preferences, historical information, the reception of extrinsic information, etc.) schemes or systems (e.g., supporting vector machines, neural networks, expert systems, Bayesian belief networks, fuzzy logic, data fusion machines, etc.) to perform automatic or specific actions related to the subject matter of the claim.Thus, classification schemes or systems can be used to automatically learn and perform a range of functions, actions, or provisions. A classifier can map an input attribute vector, z = (z1, z2, z3, z4, zn), to a confidence level that the input belongs to a class, as expressed by f(z) = confidence(class). Such a classification can use probabilistic or statistically based analysis (e.g., considering benefits and costs in the analysis) to determine an action to be performed automatically. A support vector machine (SVM) can be an example of a classifier that can be used. The SVM works by finding a hyperplane in the space of possible inputs, where the hyperplane attempts to separate the triggering criteria from the non-triggering events. Intuitively, this ensures that the classification is correct for those test data that are close to, but not identical to, the training data.Other directed and undirected model classification approaches include, for example, naive Bayesian models, Bayesian networks, decision trees, neural networks, fuzzy logic models, or probabilistic classification models, which offer different independence patterns and from which any one can be used. The classification used here also includes statistical regression, which is used to develop priority models. To provide additional context for the various embodiments described herein, Fig. 17 and the following discussion provide a brief, general description of a suitable computer environment 1700 in which the various embodiments of the embodiment described herein can be implemented. While the embodiments above have been described in the general context of computer-executable instructions that can be executed on one or more computers, the person skilled in the art will recognize that the embodiments can also be implemented in combination with other program modules or as a combination of hardware and software. In general, program modules comprise routines, programs, components, data structures, etc., that perform specific tasks or implement specific abstract data types. Furthermore, the person skilled in the art will recognize that the inventive methods can be practiced with other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframes, Internet of Things (IoT) devices, distributed computer systems, as well as personal computers, portable computers, microprocessor-based or programmable consumer electronics devices, and the like, each of which can be functionally coupled with one or more associated devices. The illustrated embodiments of the embodiments described herein can also be implemented in distributed computing environments where certain tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside on both local and remote memory storage devices. Computer devices typically comprise a variety of media, which may include computer-readable storage media, machine-readable storage media, or communication media. These two terms are used interchangeably herein. Computer-readable storage media or machine-readable storage media can be any available storage media that the computer can access and includes both volatile and non-volatile media, removable and non-removable media. For example, but not limited to, computer-readable storage media or machine-readable storage media can be implemented in conjunction with any method or technology for storing information, such as computer-readable or machine-readable instructions, program modules, and structured or unstructured data. Computer-readable storage media may include, but are not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other storage technologies, Compact Disk Read Only Memory (CD-ROM), Digital Versatile Disk (DVD), Blu-ray Disc (BD) or other optical storage media, magnetic cartridges, magnetic tapes, magnetic disk storage or other magnetic storage devices, solid-state drives or other solid-state storage devices, or other physical or non-transient media that can be used to store desired information.In this context, the terms “material” or “non-transient” herein, as they refer to storage, data or computer-readable media, are to be understood as excluding only propagating transitory signals per se as modifiers and do not transfer the rights to all standard storage, storage media or computer-readable media which do not transmit only propagating transitory signals per se. Computer-readable storage media can be accessed by one or more local or remote computer devices, e.g., via access requests, queries, or other data retrieval protocols, for a variety of operations relating to the information stored on the medium. Communication media typically embody computer-readable instructions, data structures, program modules, or other structured or unstructured data in a data signal, such as a modulated data signal, e.g., a carrier wave or other transport mechanisms, and encompass all information transmission or transport media. The term "modulated data signal" or "modulated data signals" refers to a signal in which one or more of its properties are set or modified to encode information in one or more signals. For example, and without limitation, communication media include wired media such as a wired network or a directly wired connection, as well as wireless media such as acoustic, RF, infrared, and other wireless media. With reference to Fig. 17, the exemplary environment 1700 for implementing various implementation forms of the aspects described herein comprises a computer 1702, wherein the computer 1702 includes a processing unit 1704, a system memory 1706, and a system bus 1708. The system bus 1708 connects system components, including but not limited to the system memory 1706, to the processing unit 1704. The processing unit 1704 can be any of the various commercially available processors. Dual microprocessor and other multiprocessor architectures can also be used as the processing unit 1704. The system bus 1708 can be one of several types of bus architecture, which can also be connected to a memory bus (with or without a memory controller), a peripheral bus, and a local bus using a variety of commercially available bus architectures. The system memory 1706 comprises a ROM 1710 and a RAM 1712. A basic input / output system (BIOS) can be stored in non-volatile memory such as a ROM, a erasable programmable read-only memory (EPROM), or an EEPROM, with the BIOS containing the basic routines that facilitate the transfer of information between components within the computer 1702, for example, during startup. The RAM 1712 can also include high-speed RAM, such as static RAM for temporary data storage. The Computer 1702 also includes an internal hard disk drive (HDD) 1714 (e.g., EIDE, SATA), one or more external storage devices 1716 (e.g., a magnetic floppy disk drive (FDD) 1716, a memory stick or flash drive reader, a memory card reader, etc.), and a drive 1720, e.g., a solid-state drive, an optical drive capable of reading from or writing to a data carrier 1722, such as a CD-ROM, DVD, BD, etc. Otherwise, if a solid-state drive were used, the hard disk drive 1722 would not be included unless it is separate. While the internal HDD 1714 is shown as it is located in the Computer 1702, the internal HDD 1714 can also be configured for external use in a suitable enclosure (not shown). Although not shown in environment 1700, a solid-state drive (SSD) could be used in addition to or instead of a hard disk 1714.The hard disk drives 1714, the external storage device(s) 1716, and the drive 1720 can be connected to the system bus 1708 via an HDD interface 1724, an external storage location 1726, or a drive interface 1728, respectively. The interface 1724 for external drive implementations can include at least one or both of the following interface technologies: Universal Serial Bus (USB) and Institute of Electrical and Electronics Engineers (IEEE) 1394. Other external drive connection technologies are possible within the scope of the embodiments described herein. The drives and associated computer-readable storage media enable the non-volatile storage of data, data structures, computer-executable instructions, etc. In Computer 1702, the drives and storage media allow the storage of any data in a suitable digital format. Although the above description of computer-readable storage media refers to the specific types of storage devices, those skilled in the art should be aware that other types of computer-readable storage media, whether currently available or developed in the future, could also be used in the example operating environment, and that such storage media could furthermore contain computer-executable instructions for carrying out the procedures described herein. The drives and RAM 1712 can store a number of program modules, including an operating system 1730, one or more application programs 1732, further program modules 1734, and program data 1736. All or parts of the operating system, applications, modules, or data can also be cached in RAM 1712. The systems and procedures described here can be implemented using various commercially available operating systems or combinations of operating systems. The computer 1702 may optionally include emulation technologies. For example, a hypervisor (not shown) or other intermediary may emulate a hardware environment for the operating system 1730, the emulated hardware optionally differing from the hardware shown in Fig. 17. In such an embodiment, the operating system 1730 may include a virtual machine (VM) with multiple VMs hosted on the computer 1702. Furthermore, the operating system 1730 may provide runtime environments, such as the Java Runtime Environment or the .NET Framework, for applications 1732. Runtime environments are consistent execution environments in which applications 1732 can run on any operating system that includes the runtime environment.Similarly, the operating system 1730 can be container-based, and the applications 1732 can be in the form of containers, which are lightweight, standalone, executable software packages, such as code, runtime, system tools, system collections, and settings for an application. Furthermore, the Computer 1702 can be activated with a security module, such as a Trusted Processing Module (TPM). With a TPM, for example, the boot components create a hash of the next boot components and wait for a match between the results and the secured values ​​before loading the next boot component. This process can occur at any level of the Computer 1702's code execution stack, such as the application execution level or the operating system kernel (OS) level, thus enabling security at every level of code execution. A user can input instructions and information into the computer 1702 via one or more wired / wireless input devices, such as a combination of a keyboard 1738, touchscreen 1740, and a pointing device, for example, a mouse 1742. Other input devices (not shown) may include: a microphone, an IR remote control, a radio frequency (RF) remote control or other remote control, a joystick, a virtual reality controller or virtual reality headset, a gamepad, a stylus, an image input device, such as one or more cameras, a gesture sensor input device, an image motion sensor input device, an emotion or face recognition device, a biometric input device, such as a fingerprint or iris scanner, or similar devices.These and other input devices are often connected to the processing unit 1704 via an input device interface 1744, which can be coupled to the system bus 1708, but can also be connected via other interfaces, such as a parallel port, a serial IEEE 1394 port, a game port, a USB port, an IR interface, a BLUETOOTH® interface, etc. A 1746 monitor or other display device can also be connected to the 1708 system bus via an interface, for example a 1748 video adapter. In addition to the 1746 monitor, a computer typically has other peripheral output devices (not shown), such as speakers, printers, etc. The Computer 1702 can operate in a network environment, establishing logical connections to one or more remote computers, such as one or more remote computers 1750, using wired or wireless communications. The remote computer(s) 1750 can be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other common network node, and typically include many or all of the elements described with respect to the Computer 1702, although for brevity only one storage device 1752 is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) 1754 or to larger networks, such as a wide area network (WAN) 1756.Such LAN and WAN network environments are common in offices and businesses and support enterprise-wide computer networks such as intranets, all of which can be connected to a global communication network, e.g., the Internet. When used in a LAN network environment, the computer 1702 can be connected to the local network 1754 via a wired or wireless communication network interface or an adapter 1758. The adapter 1758 can enable wired or wireless communication with the LAN 1754, which may also include a WLAN access point (AP) for wireless communication with the adapter 1758. When used in a WAN network environment, computer 1702 can include a modem 1760 or be connected to a communication server in the WAN 1756 by other means to establish communications over the WAN 1756, for example, via the Internet. The modem 1760, which can be an internal or external modem and a wired or wireless device, can be connected to the system bus 1708 via the input device interface 1744. In a network environment, program modules represented relative to computer 1702 or parts thereof can be stored in the remote memory / storage device 1752. It should be noted that the network connections shown are examples and other means can be used to establish a communication link between the computers. When used in either a LAN or WAN network environment, the computer 1702 can access cloud storage systems or other network-based storage systems, such as, but not limited to, a virtual network machine that provides one or more aspects of information storage or processing, in addition to or instead of external storage devices 1716 as described above. Generally, a connection between the computer 1702 and a cloud storage system can be established via a LAN 1754 or WAN 1756, for example, using the adapter 1758 or the modem 1760, respectively. When the computer 1702 is connected to an associated cloud storage system, the external storage interface 1726, using the adapter 1758 or the modem 1760, can manage the storage provided by the cloud storage system in the same way as other types of external storage.For example, the external storage interface 1726 can be configured to access cloud storage sources as if those sources were physically connected to the computer 1702. The Computer 1702 can be authorized to communicate with any wireless device or instance operationally used for wireless communication, such as a printer, scanner, desktop or laptop computer, portable data assistant, communications satellite, any equipment or location connected to a wirelessly detectable tag (e.g., a kiosk, newsstand, store shelf, etc.), and a telephone. This can include Wireless Fidelity (Wi-Fi) and Bluetooth® wireless technologies. Communication can thus follow a predefined structure, like a traditional network, or simply be ad-hoc communication between at least two devices. Figure 18 is a schematic block diagram of an example computer environment 1800 with which the subject of the disclosure can interact. The example computer environment 1800 comprises one or more client(s) 1810. The client(s) 1810 can be hardware or software (e.g., threads, processes, computer devices). The example computer environment 1800 comprises one or more servers 1830. The server(s) 1830 can be hardware or software (e.g., threads, processes, computer devices). The server(s) 1830 can host threads to perform transformations using one or more of the embodiments described herein, for example. Possible communication between a client 1810 and a server 1830 can take the form of a data packet adapted for transmission between two or more computer processes.The example computer environment 1800 includes a communication framework 1850 that can be used to support communication between the client(s) 1810 and the server(s) 1830. The client(s) 1810 is / are functionally connected to one or more client data stores 1820, which can be used to store information that is local to the client(s) 1810. Similarly, the server(s) 1830 are functionally connected to one or more server data stores 1840, which can be used to store information that is local to the server(s) 1830. Various embodiments can be a system, a method, a device, or a computer program product at any possible level of technical detail of integration. The computer program product can include a computer-readable storage medium (or media) containing computer-readable program instructions that cause a processor to execute aspects of various embodiments. The computer-readable storage medium can be a physical device capable of storing and retaining instructions for an instruction-executing device. The computer-readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof.The following non-exhaustive list may include further specific examples of computer-readable storage media: a portable computer floppy disk, a hard disk, random-access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random-access memory (SRAM), portable compact read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically coded device such as punched cards or relief structures in a groove on which instructions are recorded, and any suitable combination thereof. A computer-readable storage medium, as used herein, is not to be understood as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g.,Light pulses transmitted through an optical fiber cable), or electrical signals transmitted via a cable. The computer-readable program instructions described herein can be downloaded to the respective computer / process devices from a computer-readable storage medium or to an external computer or storage device via a network, such as the Internet, a local area network, a remote network, or a wireless network. The network may include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, or edge servers. A network adapter card or network interface in each computer / process device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage on a computer-readable storage medium in the respective computer / process device.Computer-readable program instructions for performing operations of various types can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or both source code and object code, written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, or similar languages, and procedural programming languages ​​such as C or similar languages. The computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server.In the latter case, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (e.g., via the internet using an internet service provider). In some embodiments, electronic circuits, including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can execute the computer-readable program instructions by using state information from the computer-readable program instructions to personalize the electronic circuits to perform various functions. Various aspects are described herein with reference to flowcharts or block diagrams of processes, devices (systems), and computer program products according to various embodiments. It is understood that each block of the flowchart figures or block diagrams, and combinations of blocks in the flowchart figures or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or any other programmable data processing device to create a machine such that the instructions executed by the processor of the computer or other programmable data processing device provide the means to implement the functions / actions specified in the flowchart or block diagram block(s).These computer-readable program instructions can also be stored on a computer-readable storage medium that can instruct a computer, programmable data processing device, or other equipment to operate in a particular manner, such that the computer-readable storage medium with the instructions stored therein comprises a manufactured product including instructions that implement aspects of the function / actions specified in the flowchart or block diagram or block diagrams.The computer-readable program instructions can also be loaded onto a computer, other programmable data processing device, or other equipment to cause a series of operator actions to be performed on the computer, other programmable device, or other equipment to create a computerized process, such that the instructions executed on the computer, other programmable device, or other equipment implement functions / actions in the flowchart or block diagram or block diagrams. The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, procedures, and computer program products according to various embodiments. In this respect, each block in the flowchart or block diagrams can represent a module, segment, or part of the instructions that includes one or more executable instructions for implementing the specific logical function(s). In some alternative implementations, the functions specified in the blocks may be executed in a different order than shown in the figures. For example, two blocks shown consecutively may actually be executed essentially simultaneously, or the blocks may sometimes be executed in sequence depending on the functionality they provide.It is also noted that each block of the block diagram or flowchart representation and each combination of blocks in the block diagram or flowchart representation can be implemented by hardware-based systems for specific purposes, which perform the specified functions or actions, or execute combinations of special hardware and computer instructions. Although the subject matter above has been described in the general context of computer-executable instructions for a computer program product running on one or more computers, it will be clear to the person skilled in the art that this disclosure can also be implemented in combination with other program modules. In general, program modules comprise routines, programs, components, data structures, etc., that perform specific tasks or implement certain abstract data types. Furthermore, the person skilled in the art will recognize that various aspects can also be practiced with other computer system configurations, including single-processor or multi-processor computer systems, mini-computers, mainframe computers, as well as computers and handheld computing devices (e.g., PDAs, telephones), microprocessor-based or programmable consumer or industrial electronics, and the like.The aspects described can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. However, some, if not all, aspects of this revelation can be implemented on standalone computers. In a distributed computing environment, program modules can reside on both local and remote memory storage devices. The terms “component,” “system,” “platform,” “interface,” and similar terms used in this application may refer to or encompass a computer-related instance or an instance pertaining to an operational machine with one or more specific functionalities. The instances disclosed herein may be hardware, a combination of hardware and software, software, or running software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. By way of illustration, both an application running on a server and the server itself may be a component. One or more components may reside within a process or thread, and a component may be localized on one computer or distributed across two or more computers.In another example, the respective components can run from different computer-readable media on which different data structures are stored. The components can communicate via local or remote processes, for example, in accordance with a signal that contains one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, or over a network such as the internet). As yet another example, a component can be a device with a specific functionality provided by mechanical parts operated by electrical or electronic circuits, where the circuits are operated by a software or firmware application running on a processor.In such a case, the processor can be located inside or outside the device and execute at least part of the software or firmware application. As another example, a component can be a device that provides certain functionalities through electronic components without mechanical parts, where the electronic components may include a processor or other means for executing software or firmware that at least partially provides the functionalities of the electronic components. In one aspect, a component can emulate an electronic component via a virtual machine, for example, within a cloud computing system. Furthermore, the term "or" means an inclusive "or" and not an exclusive "or". Unless otherwise stated or clear from the context, "X employs A or B" means any of the natural inclusive permutations. That is, if XA employs; X employs B; or X employs both A and B, then "X employs A or B" is satisfied in each of the aforementioned cases. The term "and / or" here has the same meaning as "or". In addition, the articles "a" and "an", as used in the present description and in the accompanying illustrations, should generally be interpreted as meaning "one or more", unless otherwise stated or it is clear from the context that they are singular forms. The terms "example" or "for example" are used here to serve as an example, specimen, or illustration.For the avoidance of doubt, it is pointed out that the subject matter disclosed herein is not limited by such examples. Furthermore, aspects or designs described herein as "example" or "by way of example" are not necessarily to be construed as being preferable or advantageous over other aspects or designs, nor are they to be understood as excluding equivalent exemplary structures and techniques known to those of average skill. The disclosure described herein provides non-limiting examples. For the sake of simplicity, various parts of the disclosure contained herein use the terms "each" or "all" when discussing different examples. The use of the terms "each" or "all" is non-limiting. In other words, when the disclosure presented herein provides a description that applies to "each" or "all" of a particular object or component, this should be understood as a non-limiting example, and it should also be further understood that in various other examples, such a description may apply to fewer than "each" or "all" of that particular object or component. As used in this description, the term "processor" can essentially refer to any computing unit or device, including but not limited to: single-core processors; single-core processors with software multithreading capability; multi-core processors; multi-core processors with software multithreading capability; multi-core processors with hardware multithreading technology; parallel platforms; and parallel platforms with distributed shared memory.Furthermore, a processor can refer to an integrated circuit, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. In addition, processors can utilize nanoscale architectures, such as molecular- and quantum-dot-based transistors, switches, and gates, to optimize space utilization or improve the performance of user equipment. A processor can also be implemented as a combination of computer processing units.In this disclosure, terms such as "memory," "storage," "data storage," "database," and essentially all other information storage components relevant to the operation and functionality of a component are used to denote "memory components," units embodied in a "memory," or components that constitute a memory. It should be noted that the memory or memory components described herein may be either volatile memory or non-volatile memory, or may include both. For illustration and without limitation, non-volatile memory may be read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, or non-volatile random-access memory (RAM) (e.g.,This includes ferroelectric RAM (FeRAM). Volatile memory can also include RAM that can function, for example, as an external buffer. For illustrative purposes, and not as a limitation, RAM is available in many forms, such as Synchronous RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double-Data-Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Direct Rambus RAM (DRRAM), Direct Rambus Dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM). Furthermore, the memory components of systems or computer-based methods disclosed herein are intended to include, but are not limited to, these and all other suitable types of memory. The preceding descriptions are merely examples of systems and computer-aided methods. It is obviously not possible to describe every conceivable combination of components or computer-aided methods for the purpose of describing this disclosure, but many further combinations and permutations of this disclosure are possible. Furthermore, the terms "comprises," "includes," "possesses," and similar terms, as used in the detailed description, claims, appendices, and drawings, are to be understood in a similar way to the term "comprehensive," just as "comprehensive" is interpreted as a transitional term in a claim. The descriptions of the various embodiments serve for illustration purposes but are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be obvious without deviating from the scope and nature of the described embodiments. The terminology used here has been chosen to best explain the principles of the embodiments, their practical application, or the technical improvement over technologies available on the market, or to enable other persons with normal knowledge in the field to understand the embodiments disclosed herein. The following examples describe various, non-restrictive examples. EXAMPLE 1: A system may include: a processor that executes computer-executable components stored in non-transitory computer-readable memory, wherein the computer-executable components may include: an access component that can access a requested ion population size; and a scan component that can cause a mass analyzer to perform a scan using an injection time correlated with the requested ion population size by an ion trap filling function, wherein a coefficient set of the ion trap filling function can be predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. EXAMPLE 2: The system of any of the preceding examples can be implemented, wherein the computer-executable components may include: a model component that can pass the current operating parameter configuration as input to the machine learning model, wherein the machine learning model can generate the set of coefficients as output. EXAMPLE 3: The system of any of the preceding examples can be implemented, wherein the model component can train the machine learning model in a supervised manner on a training dataset, the training dataset being able to include: multiple operational parameter configurations that can be implemented by the mass analyzer; and multiple ground truth coefficient sets, each corresponding to the multiple operational parameter configurations. EXAMPLE 4: The system of any of the preceding examples can be implemented, wherein the access component can access an ion flux estimate that includes a flux injection time and a flux ion population size achieved by the flux injection time, and wherein the model component can: apply the ion trap filling function to the requested ion population size, yielding a first value; apply the ion trap filling function to the flux ion population size, yielding a second value; divide the first value by the second value, yielding a ratio; and calculate the injection time based on scaling the flux injection time by the ratio. EXAMPLE 5: The system of any preceding example can be implemented, wherein the access component can access an ion flux estimate comprising a flux injection time and a flux ion population size achieved by the flux injection time; wherein the access component can access an ion distribution, showing a respective contribution percentage for each of several ion species used by the mass analyzer; wherein the model component can: scale, for each of the several ion species, the requested ion population size by a respective contribution percentage, resulting in several scaled ion population sizes; apply the ion trap filling function to each of the several scaled ion population sizes, resulting in several first values; summate the several first values, resulting in a second value;Applying the ion trap filling function to the flux ion population size yields a third value; dividing the second value by the third value yields a ratio; and calculating the injection time based on scaling the flux injection time with the ratio. EXAMPLE 6: The system of any of the preceding examples can be implemented, where the current operating parameter configuration may include: an initial mass, final mass, center mass, or width of a scan range currently implemented by the mass analyzer; an initial mass, final mass, center mass, or width of a passage range currently implemented by an ion trap of the mass analyzer; or a number of stacked ring ion conductor injections currently implemented by the mass analyzer. EXAMPLE 7: The system of each preceding example can be implemented, where the machine learning model can be a random forest regressor or a neural network for deep learning. EXAMPLE 8: The system of any previous example can be implemented, where the ion trap filling function can be nonlinear. EXAMPLE 9: The system of any of the preceding examples can be implemented, where the computer-executable components may include: a feedback component capable of: measuring an actual ion population size achieved by the injection time; calculating an error between the actual ion population size and the requested ion population size; and updating the machine learning model by backpropagation based on the error. In various embodiments, any combination or combinations of Examples 1 - 9 can be implemented. EXAMPLE 10: A computer-aided procedure that may include: accessing, from a device operationally coupled to a processor, a requested ion population size; and causing, by means of the device, a scan to be performed by a mass analyzer using an injection time correlated with the requested ion population size by an ion trap filling function, wherein a coefficient set of the ion trap filling function is predicted by means of a machine learning model based on a current operating parameter configuration of the mass analyzer. EXAMPLE 11: A computer-based method of any of the foregoing examples that can be implemented and further comprises: forwarding, from the device, the current operating parameter configuration as input to the machine learning model, wherein the machine learning model can generate the set of coefficients as output. EXAMPLE 12: A computer-based method of any of the foregoing examples that can be implemented and further comprises: supervised training of the machine learning model, by the device, using a training dataset, wherein the training dataset comprises: several operating parameter configurations that can be implemented by the mass analyzer; and several ground-truth coefficient sets, each corresponding to the several operating parameter configurations. EXAMPLE 13: A computer-based procedure of any of the foregoing examples that can be implemented, further comprising: Accessing, by the device, an ion flux estimate that includes a flux injection time and a flux ion population size achieved by the flux injection time; Applying, by the device, the ion trap filling function to the requested ion population size, yielding a first value; Applying, by the device, the ion trap filling function to the flux ion population size, yielding a second value; Dividing, by the device, the first value by the second value, yielding a ratio; and calculating, by the device, the injection time based on scaling the flux injection time by the ratio. EXAMPLE 14: A computer-based procedure of any of the foregoing examples that can be implemented, further comprising: Accessing, by the device, an ion flux estimate comprising a flux injection time and a flux ion population size achieved within the flux injection time; Accessing, by the device, an ion distribution specifying a respective contribution percentage for each of the several ion species used by the mass analyzer; Scaling, by the device and for each of the several ion species, the requested ion population size by a respective contribution percentage, resulting in several scaled ion population sizes; Applying, by the device, the ion trap filling function to each of the several scaled ion population sizes, resulting in several first values; Summing, by the device, the several first values, resulting in a second value;Apply, by the device, the ion trap filling function to the flux ion population size, resulting in a third value; divide, by the device, the second value by the third value, resulting in a ratio; and calculate, by the device, the injection time based on scaling the flux injection time with the ratio. EXAMPLE 15: A computer-aided method of any of the foregoing examples that can be implemented, wherein the current operating parameter configuration may include: an initial mass, final mass, center mass, or width of a scan range currently implemented by the mass analyzer; an initial mass, final mass, center mass, or width of a passage range currently implemented by an ion trap of the mass analyzer; or a number of stacked ring ion conductor injections currently implemented by the mass analyzer. EXAMPLE 16: A computer-based method of each of the preceding examples to be implemented, where the machine learning model can be a random forest regressor or a neural network for deep learning. EXAMPLE 17: Computer-aided method of any previous example that can be implemented, where the ion trap filling function can be nonlinear. EXAMPLE 18: A computer-based procedure of any of the foregoing example that can be implemented, further comprising: measuring, by a device, an actual ion population size achieved by the injection time; calculating, by the device, an error between the actual ion population size and the requested ion population size; and updating, by the device, the machine learning model by backward propagation based on the error. In various embodiments, any combination or combinations of Examples 10-18 can be implemented. EXAMPLE 19: A computer program product to support the prediction of ion trap filling functions by machine learning may include a non-transitory, computer-readable memory containing program instructions. In various aspects, the program instructions may be executable by a processor to cause the processor to: access a requested ion population size; and cause a mass analyzer to perform a scan using an injection time correlated with the requested ion population size by an ion trap filling function, where a set of coefficients of the ion trap filling function is predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. EXAMPLE 20: The computer program product of any of the preceding examples can be implemented, wherein the program instructions are executable to cause the processor to do the following: Pass the current operating parameter configuration as input to the machine learning model, wherein the machine learning model produces the set of coefficients as output. In various embodiments, any combination or combinations of Examples 19-20 can be implemented. In various embodiments, any combination or combinations of Examples 1 - 20 can be implemented.

Claims

A system comprising: a processor that executes computer-executable components stored in non-transitory computer-readable memory, wherein the computer-executable components include: an access component that accesses a requested ion population size; and a scan component that causes a mass analyzer to perform a scan using an injection time correlated with the requested ion population size by an ion trap filling function, wherein a coefficient set of the ion trap filling function is predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. System according to claim 1, wherein the computer-executable components comprise: a model component that forwards the current operating parameter configuration as input to the machine learning model, wherein the machine learning model generates the set of coefficients as output. System according to claim 2, wherein the model component trains the machine learning model in a supervised manner using a training dataset, the training dataset comprising: several operating parameter configurations that can be implemented by the mass analyzer; and several ground truth coefficient sets, each corresponding to the several operating parameter configurations. System according to claim 2, wherein the access component can access an ion flux estimate comprising a flux injection time and a flux ion population size achieved by the flux injection time, and wherein the model component: applies the ion trap filling function to the requested ion population size, resulting in a first value; applies the ion trap filling function to the flux ion population size, resulting in a second value; divides the first value by the second value, resulting in a ratio; and calculates the injection time based on scaling the flux injection time by the ratio. System according to claim 2, wherein the access component accesses an ion flux estimate comprising a flux injection time and a flux ion population size achieved by the flux injection time, wherein the access component accesses an ion distribution specifying a respective contribution percentage for each of the multiple ion species used by the mass analyzer, and wherein the model component performs the following: scaling, for each of the multiple ion species, the requested ion population size by a respective contribution percentage, resulting in multiple scaled ion population sizes; applying the ion trap filling function to each of the multiple scaled ion population sizes, resulting in multiple first values; summing the multiple first values, resulting in a second value; applying the ion trap filling function to the flux ion population size, resulting in a third value;Dividing the second value by the third value yields a ratio; and calculating the injection time based on scaling the flow injection time with the ratio. System according to claim 2, wherein the current operating parameter configuration comprises: an initial mass, final mass, center mass or width of a scan area currently implemented by the mass analyzer; an initial mass, final mass, center mass or width of a passage area currently implemented by an ion trap of the mass analyzer; or a number of stacked ring ion conductor injections currently implemented by the mass analyzer. System according to claim 1, wherein the machine learning model is a random forest regressor or a neural network for deep learning. System according to claim 1, wherein the ion trap filling function is nonlinear. System according to claim 1, wherein the computer-executable components comprise: a feedback component which: measures an actual ion population size achieved within the injection time; calculates an error between the actual ion population size and the requested ion population size; and updates the machine learning model via backpropagation based on the error. A computer-aided method comprising: accessing, through an operationally processor-connected device, a requested ion population size; and causing a mass analyzer, through the device, to perform a scan using an injection time correlated with the requested ion population size by an ion trap filling function, wherein a coefficient set of the ion trap filling function is predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. A computer-aided method according to claim 10, further comprising: forwarding the current operating parameter configuration from the device as input to the machine learning model, wherein the machine learning model generates the set of coefficients as output. A computer-aided method according to claim 11, further comprising: supervised training of the machine learning model by the facility using a training dataset, wherein the training dataset comprises: multiple operating parameter configurations that can be implemented by the mass analyzer; and multiple ground truth coefficient sets, each corresponding to one of the multiple operating parameter configurations. A computer-aided method according to claim 11, further comprising: accessing, by the device, an ion flow estimate comprising a flow injection time and a flow ion population size achieved by the flow injection time; applying, by the device, the ion trap filling function to the requested ion population size, resulting in a first value; applying, by the device, the ion trap filling function to the flow ion population size, resulting in a second value; dividing, by the device, the first value by the second value, resulting in a ratio; and calculating, by the device, the injection time based on scaling the flow injection time by the ratio. A computer-aided method according to claim 11, further comprising: accessing, by the device, an ion flux estimate comprising a flux injection time and a flux ion population size achieved by the flux injection time; accessing, by the device, an ion distribution specifying a respective contribution percentage for each of the multiple ion species used by the mass analyzer; scaling, by the device, for each of the multiple ion species, the requested ion population size by a respective contribution percentage, resulting in multiple scaled ion population sizes; applying, by the device, the ion trap filling function to each of the multiple scaled ion population sizes, resulting in multiple first values; summing, by the device, the multiple first values, resulting in a second value;Apply, by the device, the ion trap filling function to the flux ion population size, resulting in a third value; divide, by the device, the second value by the third value, resulting in a ratio; and calculate, by the device, the injection time based on scaling the flux injection time with the ratio. Computer-aided method according to claim 11, wherein the current operating parameter configuration comprises: an initial mass, final mass, center mass or width of a scan area currently implemented by the mass analyzer; an initial mass, final mass, center mass or width of a passage area currently implemented by an ion trap of the mass analyzer; or a number of stacked ring ion conductor injections currently implemented by the mass analyzer. Computer-aided method according to claim 10, wherein the machine learning model is a random forest regressor or a neural network for deep learning. Computer-aided method according to claim 10, wherein the ion trap filling function is non-linear. A computer-aided method according to claim 10, further comprising: measuring, by the device, an actual ion population size achieved within the injection time; calculating an error between the actual ion population size and the requested ion population size; and updating, by the device and via backpropagation, the machine learning model based on the error. A computer program product for supporting the prediction of ion trap filling functions by machine learning, wherein the computer program product comprises a non-transitory computer-readable memory containing embodied program instructions, the program instructions being executable by a processor to cause the processor to: access a requested ion population size; and cause a mass analyzer to perform a scan using an injection time correlated with the requested ion population size by an ion trap filling function, wherein a set of coefficients of the ion trap filling function is predicted by a machine learning model based on a current operating parameter configuration of the mass analyzer. Computer program product according to claim 19, wherein the program instructions are further executable to cause the processor to do the following: forward the current operating parameter configuration as input to the machine learning model, wherein the machine learning model generates the set of coefficients as output.

Images