Wavenumber-based particle identification

Abstract

In some examples, an apparatus may include an environmental sample analyzer that is executed by at least one hardware processor to analyze an environmental sample at a plurality of wavenumbers. A particle type identifier that is executed by the at least one hardware processor may isolate, based on the analysis of the environmental sample at the plurality of wavenumbers, particle types for a plurality of particles in the environmental sample.

Description

20230176-02 WAVENUMBER-BASED PARTICLE IDENTIFICATION CROSS-REFERENCE TO RELATED APPLICATION(S)

[0001] This application claims priority to U.S. Provisional Patent Application Serial Number 63 / 673,052, filed July 18, 2024, titled “WAVENUMBER-BASED PARTICLE IDENTIFICATION”, which is incorporated by reference in its entirety. BACKGROUND

[0002] With respect to particles, such as polymers, the particles may need to be identified in a sample, such as an environmental sample. In some cases, the particles may be separate, while in other cases, the particles may be in contact with each other.20230176-02 BRIEF DESCRIPTION OF DRAWINGS

[0003] Features of the present disclosure are illustrated by way of example and not limited in the following figure(s), in which like numerals indicate like elements, in which:

[0004] Figure 1 illustrates a layout of a wavenumber-based particle identification apparatus in accordance with an example of the present disclosure;

[0005] Figure 2 illustrates an infrared radiation (IR) image scan to search for polystyrene, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0006] Figure 3 illustrates identification from the image stack of Figure 2 for the search for polystyrene, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0007] Figure 4 illustrates examples of particles that are in contact with each other and separated, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0008] Figure 5 illustrates steps for targeted analysis, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0009] Figure 6 illustrates further details of targeted analysis, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0010] Figure 7 illustrates laser offset and low signal / noise ratio, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with20230176-02 an example of the present disclosure;

[0011] Figure 8 illustrates further details related to targeted analysis, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0012] Figure 9 illustrates further details related to targeted analysis where QLC chips are not aligned, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0013] Figure 10 illustrates a distinctive spectral scan for each particle, to illustrate operation of the wavenumber-based particle identification apparatus of Figure 1, in accordance with an example of the present disclosure;

[0014] Figure 11 illustrates an example block diagram for wavenumber-based particle identification, in accordance with an example of the present disclosure;

[0015] Figure 12 illustrates a flowchart of an example method for wavenumber-based particle identification, in accordance with an example of the present disclosure; and

[0016] Figure 13 illustrates a further example block diagram for wavenumber-based particle identification, in accordance with another example of the present disclosure.20230176-02 DETAILED DESCRIPTION

[0017] For simplicity and illustrative purposes, the present disclosure is described by referring mainly to examples. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. It will be readily apparent however, that the present disclosure may be practiced without limitation to these specific details. In other instances, some methods and structures have not been described in detail so as not to unnecessarily obscure the present disclosure.

[0018] Throughout the present disclosure, the terms "a" and "an" are intended to denote at least one of a particular element. As used herein, the term "includes" means includes but not limited to, the term "including" means including but not limited to. The term "based on" means based at least in part on.

[0019] Wavenumber-based particle identification apparatuses, methods for wavenumber-based particle identification, and non-transitory computer readable media having stored thereon machine readable instructions to provide wavenumber-based particle identification are disclosed herein. The apparatuses, methods, and non-transitory computer readable media disclosed herein provide for improvement in application of targeted wavenumber analysis to a microplastic automated workflow with respect to speed of analysis. The apparatuses, methods, and non-transitory computer readable media disclosed herein further provide for higher particle load densities per measurement, while still maintaining high identification fidelity.

[0020] As disclosed herein, with respect to particles, such as polymers, particles may need to be identified in a sample, such as an environmental sample. In some cases, the particles may be separate, while in other cases, the particles may in be in contact with20230176-02 (e.g., touching) each other. In this regard, in some cases, specific particle spectral sweep information may be needed for each particle conglomerate to be identified. Moreover, it is technically challenging to separate particles that are in contact with each other without preforming sweeps on all particles.

[0021] In order to address at least the aforementioned technical challenges, according to examples disclosed herein, wavenumbers may be selected based on targeting unique fingerprints in a spectral range using at least three wavenumber scans for relative information to uniquely identify a relevant constituent. For example, a principal components analysis (PCA) or discriminant analysis may be utilized to select wavenumbers that have a highest informational content that includes a particular set of material types of interest, with unique features in the spectral range of interest. The wavenumbers to be imaged in order to identify constituents are selected using a PCA technique. The PCA or discriminant analysis may be performed as a continuous list and return wavenumbers. Further, to determine the effectiveness of the matching, conditional probability of misidentification may be determined for each fingerprint region identified that conveys particular information about a constituent of interest. This can then be analyzed in terms of the relative likelihood that the components are unique within the set as well as with respect to general noise of the sampled wavenumbers.

[0022] With respect to operation of apparatuses, methods, and non-transitory computer readable media disclosed herein, once wavenumbers of interest are identified (e.g., by a wavenumber selector as disclosed herein), a user may select a region of interest for analysis based on visible images of a sample, such as an environmental sample.20230176-02

[0023] Next, the apparatus as disclosed herein may be instructed to search (e.g., by a particle type identifier of the apparatus as disclosed herein) for particles from the list of wavenumbers. The polymers identified may be ranked according to the conditional probabilities determined before and the confidence of matching items in the predefined list determined. The discrete sampled images will produce sparse representations of the full spectral sweep at the relative position in the image. In this regard, the particle type identifier may perform image scans at the wavenumbers on the list applicable to the particles the user may be interested in identifying. The particle type identifier may apply the wavenumbers, and then utilize image processing to identify all the particles of interest in an image. In this regard, images may be scanned at the wavenumbers. A user may trust the hyperspectral imaging analysis or choose to perform full spectrum sweeps at the points where the particles are identified.

[0024] If the additional step of full spectrum sweeps is bypassed and the image analysis is of high quality (e.g., as defined by mathematical analysis for instrument control parameters), then there may be no need to perform further analysis of the particle and a significant speed boost is acquired.

[0025] According to examples disclosed herein, the particle type identifier may be directed to find specific particles in an image and any aggregated particles that typically would receive a poor classification.

[0026] The particle type identifier may cluster each of the particles into a conglomerate and then assign a classifier. In this regard, the physical sampling process creates clusters of polymers of different types that are either overlapping or touching each other. The classifier may be obtained by rescanning the best position identified by a mathematical20230176-02 technique within the conglomerate to perform a full spectral sweep. The sweep may be matched to known libraries and databases to identify the particle. In this regard, the full spectral sweep, at the points identified from the image analysis, can be matched to known instrument based libraries or referenced to more well known general industry available spectral database data using industry accepted matching techniques.

[0027] With respect to separation of conglomerates into unique constituents, an image may provide a set of coordinates that may be a particle and another set of coordinates that may not be a particle. The clustering groups may be identified at a single point. In this regard, the particle type identifier may separate unique classifiers in the event that they are in intimate contact (e.g., an overlapping PTFE and PVC).

[0028] For the apparatuses, methods, and non-transitory computer readable media disclosed herein, a secondary scan to perform a spectral sweep at a point in the particle may not be needed, and depending on particle counts, omission of a secondary scan may provide significant time savings. If full spectral sweeps are still utilized to guarantee data fidelity, then particles that are readily identifiable as of no interest may be removed and the sweep speeds may still be significantly improved.

[0029] The apparatuses, methods, and non-transitory computer readable media disclosed herein thus provide improvements with respect to particle identification counts, particle area identification, speed of analysis, and enhanced performance. For example, image scans may take several seconds (e.g., 16 seconds for a 9 mm2area). In this regard, for the apparatuses, methods, and non-transitory computer readable media disclosed herein, optimization may be dependent on the number of particles identified in a scan region. Given that an analysis needs to scan each region at least once, additional20230176-02 scans at different wavenumbers may be used to compare the relative improvement. In a common scan area of 150 mm2, the expected number of particles found in an environmental sample is in the region of 8000 particles. The particle scan on a relatively fast instrument with the required physical movements may take around 5 to 8 seconds per particle, representing 13 to 18 hours of processing time. Typically, the number of wavenumbers for each identification type of interest is 4 wavenumbers. In a typical microplastic run, 42 wavenumbers may be needed to identify the 10 most common types of plastics. This represents a time of less than 3 hours to acquire enough information to separate and identify the polymers. Thus, the apparatuses, methods, and non-transitory computer readable media disclosed herein provide a minimum improvement ratio of 5 with respect to speed of analysis, and may be tailored to suit the number of classifiers and speed of analysis.

[0030] For the apparatuses, methods, and non-transitory computer readable media disclosed herein, the particle type identifier may implement conditional probability of finding relative intensities in image sweeps which are not baselines corrected in terms of a spectral correction (e.g., the relative laser intensity may be estimated). In this regard, the laser characteristics combined with the identified fingerprint range will determine the discriminatory ability of the technique. The material probabilities may then enable ratio images to create conditional probabilities that are above defined thresholds with respect to the material of interest, or sufficiently chemically similar, to be of interest. These probabilities will then enable the ranking of the results in terms of the confidence of actual matches to the classifier of interest and direct further analysis if needed.

[0031] The apparatuses, methods, and non-transitory computer readable media20230176-02 disclosed herein provide technical improvements such as increased speed of analysis, improved analysis accuracy, and larger sample load density measurement capabilities. In this regard, the apparatuses, methods, and non-transitory computer readable media disclosed herein provide improved isolation of particles within an image for separation and enhanced statistical analysis of sample identification. Further, the apparatuses, methods, and non-transitory computer readable media disclosed herein provide for improved analysis speed through presorted identification using images at predefined wavenumbers that are identified from the known spectra of the particles of interest determined through prior analysis.

[0032] According to examples of an apparatus disclosed herein, the apparatus may include an environmental sample analyzer that is executed by at least one hardware processor to analyze an environmental sample at a plurality of wavenumbers. A particle type identifier that is executed by the at least one hardware processor may isolate, based on the analysis of the environmental sample at the plurality of wavenumbers, particle types for a plurality of particles in the environmental sample.

[0033] According to examples disclosed herein, the environmental sample may include aggregated particles.

[0034] According to examples disclosed herein, the plurality of wavenumbers may represent selected wavenumbers. In this regard, a wavenumber selector that is executed by the at least one hardware processor may select, from a plurality of available wavenumbers, the selected wavenumbers. Further, the wavenumber selector may select, from the plurality of available wavenumbers, the selected wavenumbers by identifying wavenumbers that include a highest informational content.20230176-02

[0035] According to examples disclosed herein, the apparatus may further include a matching analyzer that is executed by the at least one hardware processor to determine, for the isolated particle types, a conditional probability of misidentification. In this regard, the identification confidence is determined by the laser noise characteristics and the fingerprint region of the particle of interest. The discriminatory ability of the matching analyzer is dependent on the informational content of the spectra of interest and number of wavenumbers used to analyze the result.

[0036] According to examples of a method disclosed herein, the method may include scanning, by at least one hardware processor, an environmental sample at a plurality of wavenumbers. The method may further include determining, by the at least one hardware processor, based on the scanning of the environmental sample at the plurality of wavenumbers, whether a specified particle is in the environmental sample. Further, based on a determination that the specified particle is in the environmental sample, the method may include generating an indication that the specified particle is in the environmental sample.

[0037] According to examples of a non-transitory computer readable medium disclosed herein, the non-transitory computer readable medium may include stored thereon machine readable instructions, the machine readable instructions, when executed by at least one hardware processor, cause the at least one hardware processor to receive, for at least one image of an environmental sample, selection of at least one region of interest for analysis. The machine readable instructions, when executed by the at least one hardware processor, further cause the at least one hardware processor to scan, based on the at least one selected region of interest for analysis, the at least one20230176-02 image of the environmental sample at a plurality of wavenumbers. Further, the machine readable instructions, when executed by the at least one hardware processor, further cause the at least one hardware processor to identify, based on the scanning of the at least one image of the environmental sample at the plurality of wavenumbers, particles in the environmental sample.

[0038] According to examples disclosed herein, the machine readable instructions to scan, based on the at least one selected region of interest for analysis, the at least one image of the environmental sample at the plurality of wavenumbers, when executed by at least one hardware processor, further cause the at least one hardware processor to apply, based on the at least one selected region of interest for analysis, the plurality of wavenumbers to the at least one image of the environmental sample. With respect to application of the plurality of wavenumbers to the at least one image, each pixel in the image represents that physical position of the sample, and wavenumber images are aligned and corrected for focal differences. After the pre-processing of the images, each wavenumber image scan creates spectral information about the physical position defined for that pixel in each wavenumber scan. This information, when analyzed correctly, identifies the constituents with a calculable confidence.

[0039] According to examples disclosed herein, the machine readable instructions to identify, based on the scanning of the environmental sample at the plurality of wavenumbers, the particles in the environmental sample, when executed by at least one hardware processor, further cause the at least one hardware processor to perform image processing to identify, based on the scanning of the environmental sample at the plurality of wavenumbers, the particles in the environmental sample. With respect to performance20230176-02 of image processing, particles in the environmental sample are matched in the images using each pixel. This informational content is sorted and matched to the classifier determined by how well it matches, with wavenumber list, to the data.

[0040] For the apparatuses, methods, and non-transitory computer readable media disclosed herein, the elements of the apparatuses, methods, and non-transitory computer readable media disclosed herein may be any combination of hardware and programming to implement the functionalities of the respective elements. In some examples described herein, the combinations of hardware and programming may be implemented in a number of different ways. For example, the programming for the elements may be processor executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the elements may include a processing resource to execute those instructions. In these examples, a computing device implementing such elements may include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separately stored and accessible by the computing device and the processing resource. In some examples, some elements may be implemented in circuitry.

[0041] Figure 1 illustrates a layout of an example wavenumber-based particle identification apparatus (hereinafter also referred to as “apparatus 100”).

[0042] Referring to Figure 1, the apparatus 100 may include an environmental sample analyzer 102 that is executed by at least one hardware processor (e.g., the hardware processor 1102 of Figure 1, and / or the hardware processor 1304 of Figure 13) to analyze an environmental sample 104 at a plurality of wavenumbers 106.

[0043] A particle type identifier 108 that is executed by at least one hardware20230176-02 processor (e.g., the hardware processor 1102 of Figure 1, and / or the hardware processor 1304 of Figure 13) may isolate, based on the analysis of the environmental sample 104 at the plurality of wavenumbers 106, particle types 110 for a plurality of particles 112 in the environmental sample 104. The particle types 110 may also be designated as isolated particle types 110. Moreover, an example of a particle may include a polymer, and other types of particles.

[0044] According to examples disclosed herein, the environmental sample 104 may include aggregated particles.

[0045] According to examples disclosed herein, the plurality of wavenumbers 106 may represent selected wavenumbers 106. In this regard, a wavenumber selector 114 that is executed by the at least one hardware processor (e.g., the hardware processor 1102 of Figure 1, and / or the hardware processor 1304 of Figure 13) may select, from a plurality of available wavenumbers 116, the selected wavenumbers 106. Further, the wavenumber selector 114 may select, from the plurality of available wavenumbers 116, the selected wavenumbers 106 by identifying wavenumbers that include a highest informational content.

[0046] A matching analyzer 118 that is executed by the at least one hardware processor (e.g., the hardware processor 1102 of Figure 1, and / or the hardware processor 1304 of Figure 13) may determine, for the isolated particle types 110, a conditional probability of misidentification 120.

[0047] According to examples disclosed herein, the environmental sample analyzer 102 may scan an environmental sample 104 at a plurality of wavenumbers 106. In this regard, the particle type identifier 108 may determine, based on the scanning of the20230176-02 environmental sample 104 at the plurality of wavenumbers 106, whether a specified particle 122 is in the environmental sample 104. Further, based on a determination that the specified particle 122 is in the environmental sample 104, the particle type identifier 108 may generate an indication that the specified particle 122 is in the environmental sample 104.

[0048] According to examples disclosed herein, the environmental sample analyzer 102 may receive, for at least one image 124 of an environmental sample 104, selection of at least one region of interest 126 for analysis. The environmental sample analyzer 102 may scan, based on the at least one selected region of interest 126 for analysis, the at least one image 124 of the environmental sample 104 at a plurality of wavenumbers 106. Further, the particle type identifier 108 may identify, based on the scanning of the at least one image 124 of the environmental sample 104 at the plurality of wavenumbers 106, particles 128 in the environmental sample 104.

[0049] Figure 2 illustrates an infrared radiation (IR) image scan to search for polystyrene, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0050] Referring to Figure 2, an IR image scan 200 is shown to search for a particle, such as polystyrene at 202. In this regard, as disclosed herein, the environmental sample analyzer 102 may analyze an environmental sample 104 represented by the image scan 200 at a plurality of wavenumbers 106.

[0051] Figure 3 illustrates identification from the image stack of Figure 2 for the search for polystyrene, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.20230176-02

[0052] Referring to Figure 3, compared to the IR image scan 200 of Figure 2, polystyrene is shown as identified at 300. In this regard, the particle type identifier 108 may isolate, based on the analysis of the environmental sample 104 at the plurality of wavenumbers 106, particle types 110 for a plurality of particles 112 in the environmental sample 104. In this example, a particle type may include polystyrene. Compared to Figure 3, the image in Figure 2 is the survey scan image at a single wavelength. In order to accurately define the polystyrene particles, the area is imaged at 6 specific wavenumbers. The per pixel positive indication of polystyrene is indicated in Figure 3, and is an overlay reference map of where polystyrene is identified in the sample. The survey scan images show several overlapping polymers of unknown type and then the separation into the single polymer of interest, polystyrene.

[0053] Figure 4 illustrates examples of particles that are in contact with each other and separated, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0054] Referring to Figure 4, as disclosed herein, particles that are to be identified may be separate as shown at 400, while in other cases, the particles may be in contact with each other as shown at 402. In this regard, as disclosed herein, the particle type identifier 108 may perform image scans at wavenumbers on a list applicable to the particles. Further, the particle type identifier 108 may apply the wavenumbers, and then utilize image processing to identify all the particles of interest in an image.

[0055] Figure 5 illustrates steps for targeted analysis, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0056] Referring to Figure 5, after images for an environmental sample are collected20230176-02 at 500, at 502, the particle type identifier 108 may isolate, based on the analysis of the environmental sample 104 at a plurality of wavenumbers 106, particle types 110 for a plurality of particles 112 in the environmental sample 104. In one example, at 500, the images may be collected between 975 – 1800 cm-¹ in steps of four. At 502, each pixel inside and outside of a particle may be compared by the particle type identifier 108. At 504, utilizing principal components analysis (PCA) the particle type identifier 108 may identify the spectral regions that contribute to the most separation. Further, at 506, the analysis by the particle type identifier 108 may be narrowed down for the appropriate wavenumbers.

[0057] Figure 6 illustrates further details of targeted analysis, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0058] Referring to Figure 6, lowest and highest absorbance images are shown at 600 and 602. In this regard, values such as peak cm-¹ of 1462, baseline of 1420 cm-¹, functional group C-H, and polymers targeted PE and PP may obtained from the images 600 and 602. Figure 6 further highlights how points of differentiation are defined by the chemical bonds of the polymer identified to create a classifier with high specificity.

[0059] Figure 7 illustrates laser offset and low signal / noise ratio, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0060] Referring to Figure 7, as shown at 700, a laser offset indicates tilting of a laser (e.g., where a laser is not perpendicular to a surface). One factor that may affect an image includes spectral shifts where peaks are either shifted to the right or left, so as to absorb the incorrect wavenumber. Another factor that may affect an image includes spectral distortion where peaks are boarder and there is possible overlapping of key20230176-02 spectral features. Another factor that may affect an image includes spatial accuracy that may make it challenging to highlight a particle. Yet further, another factor that may affect an image includes a low signal / noise ratio that may negatively affect the power and stability of a laser. Plots with a low signal-to-noise ratio are shown at 702 and 704. Specific unwanted characteristics of noise and chemical bonds and thus spectral response can cause technical challenges in the ability to uniquely identify polymers. Difficulties in the physics means that there are small subtle pointing changes in the lasers outputs as the wavelength is varied, where these small subtle pointing changes need to be accounted for in the algorithms that create the images from the wavenumber scans for identification.

[0061] Figure 8 illustrates further details related to targeted analysis, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0062] Referring to Figure 8, with respect to a moving image at 800, even though the same square is selected, when a scan begins, an IR image may move. With respect to lensing issue at 802 such as focusing of the laser beam, the Polymethyl Methacrylate (PMMA) counts are plotted against the counts of the background. The discrete sampling proposed for identification and laser characteristics mean that extra post processing of the images is needed to equalize laser power and sample dependent characteristics.

[0063] Figure 9 illustrates further details related to targeted analysis where QLC chips are not aligned, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0064] Referring to Figure 9, as shown at 900 and 902, images may include spectral stepping. In this regard, the images at 900 and 902 show significant jumps in the acquired20230176-02 spectra. Typical QCLs cover a narrow region of interest, and multiple QCL chips can be staggered to enable a larger portion of the wavelength to be investigated.

[0065] Figure 10 illustrates a distinctive spectral scan for each particle, to illustrate operation of the apparatus 100, in accordance with an example of the present disclosure.

[0066] Referring to Figure 10, as disclosed herein, the particle type identifier 108 may isolate, based on the analysis of the environmental sample 104 at the plurality of wavenumbers 106, particle types 110 for a plurality of particles 112 in the environmental sample 104. In another example disclosed herein, the particle type identifier 108 may determine, based on the scanning of the environmental sample 104 at the plurality of wavenumbers 106, whether a specified particle 122 is in the environmental sample 104. In a further example disclosed herein, the particle type identifier 108 may identify, based on the scanning of the at least one image 124 of the environmental sample 104 at the plurality of wavenumbers 106, particles 128 in the environmental sample 104. In this regard, a spectral scan generator 130 that is executed by at least one hardware processor (e.g., the hardware processor 1102 of Figure 1, and / or the hardware processor 1304 of Figure 13) may generate, with respect to the particle types 110, the specified particle 122, or the particles 128, a scan, such as the scan 132, that illustrates the particle types 110, the specified particle 122, or the particles 128. For example, the scan 132 may illustrate the particle types 110, the specified particle 122, or the particles 128.

[0067] Figures 11-13 respectively illustrate an example block diagram 1100, a flowchart of an example method 1200, and a further example block diagram 1300 for wavenumber-based particle identification, according to examples. The block diagram 1100, the method 1200, and the block diagram 1300 may be implemented on the20230176-02 apparatus 100 described above with reference to Figure 1 by way of example and not of limitation. The block diagram 1100, the method 1200, and the block diagram 1300 may be practiced in other apparatus. In addition to showing the block diagram 1100, Figure 11 shows hardware of the apparatus 100 that may execute the instructions of the block diagram 1100. The hardware may include a processor 1102, and a memory 1104 storing machine readable instructions that when executed by the processor cause the processor to perform the instructions of the block diagram 1100. The memory 1104 may represent a non-transitory computer readable medium. Figure 12 may represent an example method for wavenumber-based particle identification, and the steps of the method. Figure 13 may represent a non-transitory computer readable medium 1302 having stored thereon machine readable instructions to provide wavenumber-based particle identification according to an example. The machine readable instructions, when executed, cause a processor 1304 to perform the instructions of the block diagram 1300 also shown in Figure 13.

[0068] The processor 1102 of Figure 11 and / or the processor 1304 of Figure 13 may include a single or multiple processors or other hardware processing circuit, to execute the methods, functions and other processes described herein. These methods, functions and other processes may be embodied as machine readable instructions stored on a computer readable medium, which may be non-transitory (e.g., the non-transitory computer readable medium 1302 of Figure 13), such as hardware storage devices (e.g., RAM (random access memory), ROM (read only memory), EPROM (erasable, programmable ROM), EEPROM (electrically erasable, programmable ROM), hard drives, and flash memory). The memory 1104 may include a RAM, where the machine readable20230176-02 instructions and data for a processor may reside during runtime.

[0069] Referring to Figures 1-11, and particularly to the block diagram 1100 shown in Figure 11, the memory 1104 may include instructions 1106 to analyze an environmental sample 104 at a plurality of wavenumbers 106.

[0070] The processor 1102 may fetch, decode, and execute the instructions 1108 to isolate, based on the analysis of the environmental sample 104 at the plurality of wavenumbers 106, polymer types (e.g., particle types 110) for a plurality of polymers (e.g., particles 112) in the environmental sample 104.

[0071] Referring to Figures 1-10 and 12, and particularly Figure 12, for the method 1200, at block 1202, the method may include scanning, by at least one hardware processor, an environmental sample 104 at a plurality of wavenumbers 106.

[0072] At block 1204, the method may include determining, by the at least one hardware processor, based on the scanning of the environmental sample 104 at the plurality of wavenumbers 106, whether a specified particle 122 is in the environmental sample 104.

[0073] At block 1206, based on a determination that the specified particle 122 is in the environmental sample 104, the method may include generating an indication that the specified particle 122 is in the environmental sample 104.

[0074] Referring to Figures 1-10 and 13, and particularly Figure 13, for the block diagram 1300, the non-transitory computer readable medium 1302 may include instructions 1306 to receive, for at least one image 124 of an environmental sample 104, selection of at least one region of interest 126 for analysis.20230176-02

[0075] The processor 1304 may fetch, decode, and execute the instructions 1308 to scan, based on the at least one selected region of interest 126 for analysis, the at least one image 124 of the environmental sample 104 at a plurality of wavenumbers 106.

[0076] The processor 1304 may fetch, decode, and execute the instructions 1310 to identify, based on the scanning of the at least one image 124 of the environmental sample 104 at the plurality of wavenumbers 106, particles in the environmental sample 104.

[0077] What has been described and illustrated herein is an example along with some of its variations. The terms, descriptions and figures used herein are set forth by way of illustration only and are not meant as limitations. Many variations are possible within the spirit and scope of the subject matter, which is intended to be defined by the following claims -and their equivalents -in which all terms are meant in their broadest reasonable sense unless otherwise indicated.

Claims

20230176-02 What is claimed is:

1. An apparatus comprising: an environmental sample analyzer, executed by at least one hardware processor, to analyze an environmental sample at a plurality of wavenumbers; and a particle type identifier, executed by the at least one hardware processor, to isolate, based on the analysis of the environmental sample at the plurality of wavenumbers, particle types for a plurality of particles in the environmental sample.

2. The apparatus according to claim 1, wherein the environmental sample includes aggregated particles.

3. The apparatus according to claim 1, wherein the plurality of wavenumbers represent selected wavenumbers, further comprising: a wavenumber selector, executed by the at least one hardware processor, to select, from a plurality of available wavenumbers, the selected wavenumbers.

4. The apparatus according to claim 3, wherein the wavenumber selector is executed by the at least one hardware processor to select, from the plurality of available wavenumbers, the selected wavenumbers by: identifying wavenumbers that include a highest informational content.20230176-02 5. The apparatus according to claim 1, further comprising: a matching analyzer, executed by the at least one hardware processor, to determine, for the isolated particle types, a conditional probability of misidentification.

6. A method comprising: scanning, by at least one hardware processor, an environmental sample at a plurality of wavenumbers; determining, by the at least one hardware processor, based on the scanning of the environmental sample at the plurality of wavenumbers, whether a specified particle is in the environmental sample; and based on a determination that the specified particle is in the environmental sample, generating, by the at least one hardware processor, an indication that the specified particle is in the environmental sample.

7. The method according to claim 6, wherein the environmental sample includes aggregated particles.

8. The method according to claim 6, wherein the plurality of wavenumbers represent selected wavenumbers, further comprising: selecting, by the at least one hardware processor, from a plurality of available20230176-02 wavenumbers, the selected wavenumbers.

9. The method according to claim 8, wherein selecting, by the at least one hardware processor, from the plurality of available wavenumbers, the selected wavenumbers further comprises: identifying, by the at least one hardware processor, wavenumbers that include a highest informational content.

10. The method according to claim 6, further comprising: determining, by the at least one hardware processor, based on the determination that the specified particle is in the environmental sample, a conditional probability of misidentification.

11. A non-transitory computer readable medium having stored thereon machine readable instructions, the machine readable instructions, when executed by at least one hardware processor, cause the at least one hardware processor to: receive, for at least one image of an environmental sample, selection of at least one region of interest for analysis; scan, based on the at least one selected region of interest for analysis, the at least one image of the environmental sample at a plurality of wavenumbers; identify, based on the scanning of the at least one image of the environmental20230176-02 sample at the plurality of wavenumbers, particles in the environmental sample.

12. The non-transitory computer readable medium according to claim 11, wherein the machine readable instructions to scan, based on the at least one selected region of interest for analysis, the at least one image of the environmental sample at the plurality of wavenumbers, when executed by at least one hardware processor, further cause the at least one hardware processor to: apply, based on the at least one selected region of interest for analysis, the plurality of wavenumbers to the at least one image of the environmental sample.

13. The non-transitory computer readable medium according to claim 12, wherein the machine readable instructions to identify, based on the scanning of the environmental sample at the plurality of wavenumbers, the particles in the environmental sample, when executed by at least one hardware processor, further cause the at least one hardware processor to: perform image processing to identify, based on the scanning of the environmental sample at the plurality of wavenumbers, the particles in the environmental sample.

14. The non-transitory computer readable medium according to claim 11, wherein the environmental sample includes aggregated particles.20230176-02 15. The non-transitory computer readable medium according to claim 11, wherein the plurality of wavenumbers represent selected wavenumbers, and wherein the machine readable instructions, when executed by at least one hardware processor, further cause the at least one hardware processor to: select, from a plurality of available wavenumbers, the selected wavenumbers.

16. The non-transitory computer readable medium according to claim 15, wherein the machine readable instructions to select, from the plurality of available wavenumbers, the selected wavenumbers, when executed by at least one hardware processor, further cause the at least one hardware processor to: identify wavenumbers that include a highest informational content.

17. The non-transitory computer readable medium according to claim 11, wherein the machine readable instructions, when executed by at least one hardware processor, further cause the at least one hardware processor to: determine, for the identified particles, a conditional probability of misidentification.

Images