Observation condition parameter determination method for granite pegmatite inversion

Abstract

The invention provides an observation condition parameter determination method for granite pegmatite inversion, and relates to the technical field of mineral detection. The method comprises the following steps: acquiring multi-angle reflectivity spectral data of a plurality of particle samples, and determining a plurality of sample data according to the multi-angle reflectivity spectral data; each piece of sample data comprises a dimensionless bi-directional reflection factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to one observation condition parameter under a plurality of characteristic wavelengths; inputting multiple pieces of sample data into the trained convolutional neural network model, outputting an importance score corresponding to each piece of sample data in the multiple pieces of sample data, and determining observation condition parameters included in target sample data as target observation condition parameters, the importance score of the target sample data is the maximum value in the importance scores of the multiple pieces of sample data. And the accuracy and precision of the inversion result of the spectral data obtained by observation based on the target observation condition parameters are improved.

Description

Technical Field

[0001] The invention relates to the technical field of mineral detection, and in particular to a method for determining observation condition parameters for granite pegmatite inversion. Background Art

[0002] Optical remote sensing has become an important prospecting tool in the early stages of geological exploration of rare metal deposits. In the field of remote sensing applications of lithium-bearing pegmatites, the spectral and pixel characteristics of granite pegmatites and their minerals are analyzed from a single perspective, resulting in low remote sensing prospecting accuracy and small range. The ground objects have bidirectional reflection characteristics, which is the basis of optical quantitative remote sensing inversion. The inversion of granite pegmatites depends on the spectral data obtained by observation based on observation condition parameters, where the observation condition parameters include the incident angle of the light source, the observation zenith angle, and the phase angle.

[0003] However, due to the flexibility and variety of observation condition parameters and the numerous combinations, the accuracy and range of the inversion results obtained from the spectral data obtained based on different observation condition parameters are completely different. Therefore, there is an urgent need for a method to determine the observation condition parameters for granite pegmatite inversion, to determine the optimal observation condition parameters from multiple observation condition parameters, so as to improve the accuracy and precision of the inversion results, thereby providing an important reference for multi-angle observation experiments, multi-angle satellite payload design, and surface two-way reflectance inversion. Summary of the invention

[0004] An embodiment of the present invention provides a method for determining observation condition parameters for granite pegmatite inversion, which can determine the optimal observation condition parameters for granite pegmatite inversion, thereby improving the accuracy and precision of the inversion results of spectral data obtained based on the observation condition parameters, thereby providing an important reference for multi-angle observation experiments, multi-angle satellite payload design and surface bidirectional reflectance inversion.

[0005] To achieve the above object, the embodiments of the present invention adopt the following technical solutions:

[0006] In a first aspect, a method for determining observation condition parameters for granite pegmatite inversion is provided, the method comprising: obtaining multi-angle reflectance spectral data of a plurality of particle samples, the particle samples being ore bodies with different particle sizes including one or more end-member minerals, the multi-angle reflectance spectral data comprising the reflectance corresponding to each observation condition parameter in a plurality of observation condition parameters, the observation condition parameters comprising the incident angle of the light source, the observation zenith angle and the phase angle; determining a plurality of sample data according to the multi-angle reflectance spectral data, each sample data comprising a dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to an observation condition parameter at a plurality of characteristic wavelengths; inputting the plurality of sample data into a trained convolutional neural network model, outputting an importance score corresponding to each sample data in the plurality of sample data, the importance score being positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample; determining the observation condition parameters included in the target sample data as the target observation condition parameters, the importance score of the target sample data being the maximum value among the importance scores of the plurality of sample data.

[0007] In a possible implementation of the first aspect, multi-angle reflectance spectral data of multiple particle samples are obtained, including: calibrating and calibrating a portable ground object spectrometer; obtaining spectral data of each particle sample through the portable ground object spectrometer; and performing Savitzky-Golay smoothing preprocessing on the spectral data of each particle sample to obtain multi-angle reflectance spectral data of the multiple particle samples.

[0008] In a possible implementation of the first aspect, the dimensionless bidirectional reflection factor F of each particle sample corresponding to each observation condition parameter at the characteristic wavelength x is NDRF The formula for determining is:

[0009]

[0010] Where R is the reflectivity of each particle sample at the characteristic wavelength x under each observation condition parameter, R max (λ) is the maximum value of the reflectivity of each particle sample at the characteristic wavelength x under multiple observation conditions, R min (λ) is the minimum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation condition parameters.

[0011] In a possible implementation manner of the first aspect, before inputting multiple sample data into a trained convolutional neural network model and outputting the importance score corresponding to each sample data in the multiple sample data, the method further includes: determining a correlation between first sample data and second sample data, where the first sample data and the second sample data are any two of the multiple sample data; and when the correlation between the first sample data and the second sample data is greater than or equal to a first correlation threshold, deleting the first sample data or the second sample data from the multiple sample data.

[0012] In a possible implementation of the first aspect, before inputting multiple sample data into a trained convolutional neural network model and outputting the importance score corresponding to each sample data in the multiple sample data, the method also includes: obtaining a training sample set, the training sample set including multiple training samples, each training sample including a dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of each particle sample in multiple particle samples corresponding to an observation condition parameter at multiple characteristic wavelengths, and the corresponding importance score; training the convolutional neural network model based on the training sample set to obtain a trained convolutional neural network model.

[0013] In a possible implementation manner of the first aspect, the convolutional neural network model is an XGboost model.

[0014] The beneficial effects of the present invention are as follows: the method provided by the present invention determines multiple sample data based on multi-angle reflectance spectral data of multiple particle samples, each sample data corresponds to an observation condition parameter, and then determines the importance scores corresponding to the multiple sample data through a trained neural network model, and finally determines the observation condition parameters corresponding to the sample data with the highest importance score as the target observation condition parameters, thereby improving the accuracy and precision of the inversion results of the spectral data obtained based on the target observation condition parameters, thereby providing an important reference for multi-angle observation experiments, multi-angle satellite payload design and surface two-way reflection inversion.

[0015] In a second aspect, an observation condition parameter determination device for granite pegmatite inversion is provided, the device comprising: an acquisition unit, for acquiring multi-angle reflectance spectral data of a plurality of particle samples, the particle samples being ore bodies with different particle sizes including one or more end-member minerals, the multi-angle reflectance spectral data comprising the reflectance corresponding to each observation condition parameter in a plurality of observation condition parameters, the observation condition parameters comprising the incident angle of the light source, the observation zenith angle and the phase angle; a processing unit, for determining a plurality of sample data according to the multi-angle reflectance spectral data, each sample data comprising a dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to an observation condition parameter at a plurality of characteristic wavelengths; the processing unit, further for inputting the plurality of sample data into a trained convolutional neural network model, and outputting an importance score corresponding to each sample data in the plurality of sample data, the importance score being positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample; the processing unit, further for determining the observation condition parameter included in the target sample data as the target observation condition parameter, the importance score of the target sample data being the maximum value among the importance scores of the plurality of sample data.

[0016] In a possible implementation of the second aspect, the dimensionless bidirectional reflection factor F of each particle sample corresponding to each observation condition parameter at the characteristic wavelength x is NDRF The formula for determining is:

[0017]

[0018] Where R is the reflectivity of each particle sample at the characteristic wavelength x under each observation condition parameter, R max (λ) is the maximum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation conditions, R min (λ) is the minimum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation condition parameters.

[0019] In a third aspect, a computing device is provided, comprising a memory and one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the computing device executes the method for determining observation condition parameters for granite pegmatite inversion as in any implementation of the first aspect.

[0020] In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions, which, when executed on a computing device, enable the computing device to execute a method for determining observation condition parameters for granite pegmatite inversion as in any implementation of the first aspect.

[0021] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computing device, the computing device executes the method for determining observation condition parameters for granite pegmatite inversion as in any implementation of the first aspect.

[0022] It can be understood that the beneficial effects that can be achieved by the observation condition parameter determination device for granite pegmatite inversion of the second aspect provided above, the computing device of the third aspect, the computer-readable storage medium of the fourth aspect, and the computer program product of the fifth aspect can be referred to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the hardware structure of a computing device shown in an embodiment of the present invention;

[0024] Figure 2 A schematic flow chart of a method for determining observation condition parameters for granite pegmatite inversion according to an embodiment of the present invention;

[0025] Figure 3 A schematic flow chart of another method for determining observation condition parameters for granite pegmatite inversion according to an embodiment of the present invention;

[0026] Figure 4 A schematic flow chart of another method for determining observation condition parameters for granite pegmatite inversion according to an embodiment of the present invention;

[0027] Figure 5 The figure is a schematic diagram of the hardware structure of a determination device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution in the embodiment of the present invention will be described below in conjunction with the accompanying drawings in the embodiment of the present invention. Among them, in the description of the present invention, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present invention is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present invention, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items.

[0029] In addition, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the difference.

[0030] Meanwhile, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way for easy understanding.

[0031] Optical remote sensing has become an important prospecting tool in the early stages of geological exploration of rare metal deposits. In the field of remote sensing applications of lithium-bearing pegmatites, the spectral and pixel characteristics of granite pegmatites and their minerals are analyzed from a single perspective, resulting in low remote sensing prospecting accuracy and small range. The ground objects have bidirectional reflection characteristics, which is the basis of optical quantitative remote sensing inversion. The inversion of granite pegmatites depends on the spectral data obtained by observation based on observation condition parameters, where the observation condition parameters include the incident angle of the light source, the observation zenith angle, and the phase angle.

[0032] However, due to the flexibility and variety of observation condition parameters and the numerous combinations, the accuracy and range of the inversion results obtained from the spectral data obtained based on different observation condition parameters are completely different. Therefore, there is an urgent need for a method to determine the observation condition parameters for granite pegmatite inversion, to determine the optimal observation condition parameters from multiple observation condition parameters, so as to improve the accuracy and precision of the inversion results, thereby providing an important reference for multi-angle observation experiments, multi-angle satellite payload design, and surface two-way reflectance inversion.

[0033] In view of this, an embodiment of the present invention provides a method for determining observation condition parameters for granite pegmatite inversion, the method comprising: obtaining multi-angle reflectance spectral data of multiple particle samples, the particle samples are ore bodies with different particle sizes including one or more end-member minerals, the multi-angle reflectance spectral data including the reflectance corresponding to each observation condition parameter in multiple observation condition parameters, the observation condition parameters including the incident angle of the light source, the observation zenith angle and the phase angle; determining multiple sample data according to the multi-angle reflectance spectral data, each sample data including a dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of each particle sample in multiple particle samples corresponding to an observation condition parameter at multiple characteristic wavelengths; inputting the multiple sample data into a trained convolutional neural network model, outputting the importance score corresponding to each sample data in the multiple sample data, the importance score being positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample; determining the observation condition parameters included in the target sample data as the target observation condition parameters, the importance score of the target sample data being the maximum value among the importance scores of the multiple sample data.

[0034] The method provided by the embodiment of the present invention determines multiple sample data based on multi-angle reflectance spectral data of multiple particle samples, each sample data corresponds to an observation condition parameter, and then determines the importance scores corresponding to the multiple sample data through a trained neural network model, and finally determines the observation condition parameter corresponding to the sample data with the highest importance score as the target observation condition parameter, thereby improving the accuracy and precision of the inversion results of the spectral data obtained based on the target observation condition parameter observation, thereby providing an important reference for multi-angle observation experiments, multi-angle satellite payload design and surface two-way reflection inversion.

[0035] In some embodiments, the observation condition parameter determination method for granite pegmatite inversion provided by the embodiments of the present invention can be performed by an observation condition parameter determination device 100 for granite pegmatite inversion (hereinafter referred to as determination device 100). As an example, the determination device 100 can be any computing device 200 with data processing capabilities, such as a general-purpose computer, a personal computer, a laptop computer, a switch or a tablet computer, etc., and the specific implementation method of the determination device 100 is not limited here.

[0036] Figure 1 The hardware structure diagram of the computing device provided by the embodiment of the present invention is shown. The computing device 200 includes a processor 210, a memory 220 and a communication interface 230.

[0037] The processor 210 may include one or more processing cores. The processor 210 uses various interfaces and lines to connect various parts within the computing device 200, and executes various functions and processes data of the computing device 200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Optionally, the processor 210 can be implemented in at least one hardware form of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA).

[0038] The memory 220 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 220 includes a non-transitory computer-readable storage medium. The memory 220 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 220 may include a program storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a data acquisition function, a data processing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.

[0039] The communication interface 230 is used to communicate with other devices, equipment or communication networks, such as data storage devices, image processing equipment or Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0040] In physical implementation, the above-mentioned components (such as processor 210, memory 220 and communication interface 230) can be components in the same device (such as a laptop). Alternatively, at least two of the components can be set in the same device, that is, as different components in one device, similar to the deployment mode of devices or components in a distributed system.

[0041] It is to be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the computing device 200. In other embodiments of the present invention, the computing device 200 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0042] The following describes the method for determining observation condition parameters for granite pegmatite inversion provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0043] Figure 2 A flowchart of a method for determining observation condition parameters for granite pegmatite inversion provided by an embodiment of the present invention. Optionally, the method may be performed by Figure 1 The method is executed by the computing device 200 of the hardware structure shown, that is, by the determination device 100. The method may include the following steps:

[0044] S1. Obtain multi-angle reflectance spectral data of multiple particle samples.

[0045] Specifically, the particle sample is an ore body with different particle sizes including one or more end-member minerals. Exemplarily, the plurality of particle samples include sample A, sample B, sample C and sample D, wherein sample A is end-member mineral A, sample B is end-member mineral B, sample C is end-member mineral C, and sample D is a mixture of end-member mineral A and end-member mineral B. And sample A, sample B, sample C and sample D have different particle sizes respectively. It can also be understood that sample A, sample B, sample C and sample D have different particle sizes respectively.

[0046] The multi-angle reflectance spectrum data includes the reflectance corresponding to each observation condition parameter in the multiple observation condition parameters, and the multi-angle reflectance spectrum data of each particle sample includes the reflectance measured for each particle sample under different observation condition parameters. The observation condition parameters include the light source incident angle, the observation zenith angle, and the phase angle. The light source incident angle is the zenith angle of the light source incident direction; the observation zenith angle is the zenith angle of the observation direction; and the phase angle is the angle between the light source incident direction and the observation direction.

[0047] In one possible implementation, see Figure 3 The above S1 specifically includes the following steps:

[0048] S11. Calibrate and calibrate the portable ground object spectrometer.

[0049] S12. Obtain spectral data of each particle sample using a portable ground object spectrometer.

[0050] S13, performing Savitzky-Golay smoothing preprocessing on the spectral data of each particle sample to obtain multi-angle reflectance spectral data of multiple particle samples.

[0051] Savitzky-Golay smoothing preprocessing is a commonly used spectral data preprocessing method used to smooth the spectral curve and remove the influence of high-frequency noise. It is based on least squares polynomial fitting and calculates the smoothed curve by fitting local data.

[0052] Specifically, the multi-angle reflectance spectrum data of each particle sample includes a spectrum curve of each particle sample determined according to the arithmetic average of multiple spectrum curves of each particle sample.

[0053] It should be understood that the above method of obtaining multi-angle reflectance spectral data is only an exemplary description. The determination device 100 can also obtain the spectral data of each particle sample in other ways, and pre-process the spectral data of each particle sample in any other way to obtain multi-angle reflectance spectral data of multiple particle samples. The embodiment of the present invention does not impose any special restrictions on this.

[0054] S2. Determine a plurality of sample data according to the multi-angle reflectance spectrum data, each sample data including a dimensionless bidirectional reflectance factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to an observation condition parameter at a plurality of characteristic wavelengths.

[0055] In a possible implementation, the dimensionless bidirectional reflection factor F of each particle sample at the characteristic wavelength x corresponding to each observation condition parameter is NDRF The formula for determining is:

[0056]

[0057] Where R is the reflectivity of each particle sample at the characteristic wavelength x under each observation condition parameter, R max (λ) is the maximum value of the reflectivity of each particle sample at the characteristic wavelength x under multiple observation conditions, R min (λ) is the minimum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation condition parameters.

[0058] Exemplarily, in the case where the plurality of particle samples include sample A, sample B, sample C, and sample D, sample data 1 is the dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of sample A, sample B, sample C, and sample D under observation condition parameter 1. Sample data 2 is the dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of sample A, sample B, sample C, and sample D under observation condition parameter 2. Sample data 3 is the dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of sample A, sample B, sample C, and sample D under observation condition parameter 3.

[0059] S3. Input multiple sample data into the trained convolutional neural network model, and output the importance score corresponding to each sample data in the multiple sample data.

[0060] The importance score is positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample.

[0061] In combination with the above example, sample data 1, sample data 2 and sample data 3 are input into the trained convolutional neural network model to obtain the importance scores corresponding to sample data 1, sample data 2 and sample data 3. Among them, the importance score of sample data 1 is 69, the importance score of sample data 2 is 34, and the importance score of sample data 3 is 42, indicating that under the observation condition parameter 1, the numerical difference between the dimensionless bidirectional reflectance factors corresponding to each characteristic wavelength of sample A, sample B, sample C and sample D included in sample data 1 is the highest.

[0062] S4. Determine the observation condition parameters included in the target sample data as the target observation condition parameters, and the importance score of the target sample data is the maximum value among the importance scores of the multiple sample data.

[0063] Exemplarily, since the importance score corresponding to sample data 1 is the highest, observation condition parameter 1 corresponding to sample data 1 is determined as the target observation condition parameter.

[0064] It can be seen from the above S1-S4 that the method provided by the embodiment of the present invention determines multiple sample data based on the multi-angle reflectance spectral data of multiple particle samples, each sample data corresponds to an observation condition parameter, and then determines the importance scores corresponding to the multiple sample data through the trained neural network model, and finally determines the observation condition parameters corresponding to the sample data with the highest importance score as the target observation condition parameters, thereby improving the accuracy and precision of the inversion results of the spectral data obtained based on the target observation condition parameters, thereby providing an important reference for multi-angle observation experiments, multi-angle satellite payload design and surface two-way reflection inversion.

[0065] In some embodiments, before the determining device 100 executes the above S3, see Figure 4 , the method provided by the embodiment of the present invention further includes the following steps:

[0066] S41 . Determine the correlation between first sample data and second sample data, where the first sample data and the second sample data are any two of a plurality of sample data.

[0067] S42: When the correlation between the first sample data and the second sample data is greater than or equal to a first correlation threshold, delete the first sample data or the second sample data from the plurality of sample data.

[0068] It can also be understood that there are similar observation condition parameters 1 in multiple sample data. For example, the first observation condition parameter is the light source incident angle of 30°, the observation zenith angle of 0° and the phase angle of 30°.

[0069] The second observation condition parameter is the light source incident angle of 32°, the observation zenith angle of 0° and the phase angle of 30°. The data correlation of the dimensionless bidirectional reflectance factor obtained by observing the two observation condition parameters is also high. At this time, if the first observation condition parameter and the second observation condition parameter are input into the trained convolutional neural network model, the calculation amount of the convolutional neural network model will increase, affecting the calculation efficiency. Therefore, the correlation of the first observation condition parameter and the second observation condition parameter is determined. When the correlation is equal to the first correlation threshold, one of the first observation condition parameter and the second observation condition parameter is deleted, and every two sample data in the multiple sample data are traversed to reduce the number of sample data and reduce the redundant data in the sample data.

[0070] From the above, it can be seen that the embodiment of the present invention can effectively remove redundant data in the sample data and reduce the amount of sample data by determining the correlation between any two sample data and deleting one of the two sample data with higher correlation, thereby reducing the amount of computation of the trained convolutional neural network model, saving computing resources and improving computing efficiency.

[0071] In some embodiments, before the determining device 100 executes the above S3, the method provided by the embodiment of the present invention further includes the following steps:

[0072] A training sample set is obtained, where the training sample set includes multiple training samples, each training sample includes a dimensionless bidirectional reflectance factor corresponding to each characteristic wavelength of each particle sample in multiple particle samples corresponding to an observation condition parameter at multiple characteristic wavelengths, and a corresponding importance score; a convolutional neural network model is trained based on the training sample set to obtain a trained convolutional neural network model.

[0073] In a possible implementation, the convolutional neural network model is an XGboost model.

[0074] The above mainly introduces the scheme of the embodiment of the present invention from the perspective of the method. It can be understood that in order to realize the above functions, the determination device 100 includes at least one of the hardware structure and software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present invention.

[0075] The embodiment of the present invention can divide the determination device 100 into functional units according to the above method example. For example, the determination device 100 can be divided into functional units corresponding to various functions, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present invention is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0076] For example, Figure 5 A schematic diagram of the hardware structure of a determination device 100 provided in an embodiment of the present invention is shown. The determination device 100 includes: an acquisition unit 111, which is used to acquire multi-angle reflectance spectral data of multiple particle samples, the particle samples are ore bodies with different particle sizes including one or more end-member minerals, the multi-angle reflectance spectral data include the reflectance corresponding to each observation condition parameter in multiple observation condition parameters, and the observation condition parameters include the incident angle of the light source, the observation zenith angle and the phase angle; a processing unit 112, which is used to determine multiple sample data according to the multi-angle reflectance spectral data, each sample data includes a dimensionless bidirectional reflection factor corresponding to each characteristic wavelength of each particle sample in multiple particle samples corresponding to an observation condition parameter at multiple characteristic wavelengths; the processing unit 112 is also used to input the multiple sample data into a trained convolutional neural network model, and output the importance score corresponding to each sample data in the multiple sample data, and the importance score is positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample; the processing unit 112 is also used to determine the observation condition parameter included in the target sample data as the target observation condition parameter, and the importance score of the target sample data is the maximum value among the importance scores of the multiple sample data.

[0077] In a possible implementation of the second aspect, the dimensionless bidirectional reflection factor F of each particle sample corresponding to each observation condition parameter at the characteristic wavelength x is NDRF The formula for determining is:

[0078]

[0079] Where R is the reflectivity of each particle sample at the characteristic wavelength x under each observation condition parameter, R max (λ) is the maximum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation conditions, R min (λ) is the minimum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation condition parameters.

[0080] It should be understood that the specific description of the above optional methods can refer to the above method embodiments, which will not be repeated here. In addition, the explanation of any of the above-provided determination devices 100 and the description of the beneficial effects can refer to the above corresponding method embodiments, which will not be repeated here.

[0081] The embodiment of the present invention further provides a computer-readable storage medium, in which at least one computer instruction is stored, and the at least one computer instruction is loaded and executed by a processor to implement the methods of the above embodiments. For the explanation of the relevant contents and the description of the beneficial effects in any of the above-mentioned computer-readable storage media, reference can be made to the above-mentioned corresponding embodiments, which will not be repeated here.

[0082] The embodiment of the present invention further provides a chip. The chip integrates a control circuit and one or more ports for implementing the functions of the above-mentioned determination device 100. Optionally, the functions supported by the chip can be referred to above and will not be described in detail here.

[0083] Those skilled in the art will appreciate that all or part of the steps of the above embodiments can be implemented by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a random access memory, etc. The above-mentioned processing unit or processor can be a central processing unit, a general-purpose processor, a specific circuit structure (application specific integrated circuit, ASIC), a microprocessor (digital signal processor, DSP), a field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.

[0084] The embodiment of the present invention also provides a computer program product including instructions, when the instructions are run on a computer, the computer executes any one of the methods in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.

[0085] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as but not limited to the above-mentioned memory, computer-readable storage medium and communication chip, etc., all have non-transitory. Those skilled in the art should be aware that in one or more of the above-mentioned examples, the functions described in the embodiments of the present invention can be implemented with hardware, software, firmware or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a general or special-purpose computer can access.

[0086] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for determining observation condition parameters for granite pegmatite inversion, characterized in that: The method comprises: Acquire multi-angle reflectance spectral data of a plurality of particle samples, wherein the particle samples are ore bodies with different particle sizes including one or more end-member minerals, wherein the multi-angle reflectance spectral data include reflectance corresponding to each observation condition parameter in a plurality of observation condition parameters, wherein the observation condition parameters include a light source incident angle, an observation zenith angle, and a phase angle; Determine a plurality of sample data according to the multi-angle reflectance spectrum data, each sample data including a dimensionless bidirectional reflectance factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to an observation condition parameter at a plurality of characteristic wavelengths; Inputting the plurality of sample data into a trained convolutional neural network model, and outputting an importance score corresponding to each sample data in the plurality of sample data, wherein the importance score is positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample; The observation condition parameter included in the target sample data is determined as the target observation condition parameter, and the importance score of the target sample data is the maximum value among the importance scores of the multiple sample data.

2. The method according to claim 1, characterized in that The step of obtaining multi-angle reflectance spectral data of a plurality of particle samples comprises: Calibrate and calibrate the portable ground spectrometer; Obtaining spectral data of each particle sample by means of the portable ground object spectrometer; The spectral data of each particle sample is subjected to Savitzky-Golay smoothing preprocessing to obtain multi-angle reflectivity spectral data of the plurality of particle samples.

3. The method according to claim 2, characterized in that The dimensionless bidirectional reflection factor F of each particle sample at the characteristic wavelength x corresponding to each observation condition parameter NDRF The formula for determining is: Where R is the reflectivity of each particle sample at the characteristic wavelength x under each observation condition parameter, R max (λ) is the maximum value of the reflectivity of each particle sample at the characteristic wavelength x under multiple observation conditions, R min (λ) is the minimum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation condition parameters.

4. The method according to claim 3, characterized in that Before inputting the plurality of sample data into the trained convolutional neural network model and outputting the importance score corresponding to each sample data in the plurality of sample data, the method further includes: Determine a correlation between first sample data and second sample data, wherein the first sample data and the second sample data are any two of the plurality of sample data; When the correlation between the first sample data and the second sample data is greater than or equal to a first correlation threshold, the first sample data or the second sample data is deleted from the plurality of sample data.

5. The method according to claim 4, characterized in that Before inputting the plurality of sample data into the trained convolutional neural network model and outputting the importance score corresponding to each sample data in the plurality of sample data, the method further includes: Acquire a training sample set, the training sample set comprising a plurality of training samples, each training sample comprising a dimensionless bidirectional reflectance factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to an observation condition parameter at a plurality of characteristic wavelengths, and a corresponding importance score; The convolutional neural network model is trained based on the training sample set to obtain the trained convolutional neural network model.

6. The method according to claim 5, characterized in that The convolutional neural network model is an XGboost model.

7. A device for determining observation condition parameters for granite pegmatite inversion, characterized in that: The device comprises: an acquisition unit, for acquiring multi-angle reflectance spectral data of a plurality of particle samples, wherein the particle samples are ore bodies with different particle sizes including one or more end-member minerals, and the multi-angle reflectance spectral data include reflectance corresponding to each observation condition parameter in a plurality of observation condition parameters, wherein the observation condition parameters include a light source incident angle, an observation zenith angle, and a phase angle; A processing unit, used to determine a plurality of sample data according to the multi-angle reflectance spectrum data, each sample data including a dimensionless bidirectional reflectance factor corresponding to each characteristic wavelength of each particle sample in a plurality of particle samples corresponding to an observation condition parameter at a plurality of characteristic wavelengths; The processing unit is further used to input the plurality of sample data into the trained convolutional neural network model, and output an importance score corresponding to each sample data in the plurality of sample data, wherein the importance score is positively correlated with the numerical difference between the bidirectional reflection factors corresponding to each characteristic wavelength of any two particle samples included in each training sample; The processing unit is further used to determine the observation condition parameters included in the target sample data as the target observation condition parameters, and the importance score of the target sample data is the maximum value among the importance scores of the multiple sample data.

8. The device according to claim 7, characterized in that The dimensionless bidirectional reflection factor F of each particle sample at the characteristic wavelength x corresponding to each observation condition parameter NDRF The formula for determining is: Where R is the reflectivity of each particle sample at the characteristic wavelength x under each observation condition parameter, R max (λ) is the maximum value of the reflectivity of each particle sample at the characteristic wavelength x under multiple observation conditions, R min (λ) is the minimum value of the reflectivity corresponding to each particle sample at the characteristic wavelength x under multiple observation condition parameters.

9. A computing device, characterized in that include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining observation condition parameters for granite pegmatite inversion as described in any one of claims 1 to 6.

10. A computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method for determining observation condition parameters for granite pegmatite inversion as claimed in any one of claims 1 to 6.

Images