Earth sample analyzing system

Abstract

A system for analyzing material samples has a loading station that is configured to receive a plurality of containers holding the material samples. The system further includes a plurality of scanning modules, wherein each scanning module is configured to capture data associated with the material samples. A computing device is configured to receive the data associated with the material samples, the received data corresponding to the data captured by the plurality of scanning modules. The computing device is further configured to coregister the received data associated with the material samples. A conveyor is configured to cany7 the plurality of containers holding the material samples from the loading station to each of the plurality of scanning modules along a conveyance path.

Description

Attorney Docket No. 36362.0259P1EARTH SAMPLE ANALYZING SYSTEMCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to. and the benefit of the filing date of, U.S. Provisional Application No. 63 / 718, 174, filed November 8, 2024, the entirety of which is incorporated by reference herein.FIELD

[0002] This disclosure relates to systems for inspecting earth samples, such as core, rock, rock chips, or rock powder samples.BACKGROUND

[0003] Typically, analysis of core or rock (or other material) samples requires shipping of the samples to a distant laboratory', where the samples are cut and then either crushed or scanned in a controlled environment by specially trained personnel. This analysis process is frequently associated with lengthy sample handling times, delays caused by limited access to the laboratory or limited trained personnel, and delays caused by detailed analysis and reporting. Consequently, from the time the core or rock sample is obtained, it often takes months to complete the analysis of the core or rock sample. Moreover, existing systems for analyzing core or rock samples typically require extensive user training and certification before the systems can be used. Further, although comparative core analysis methods rely on the objective consistency of the location of sample points, existing core analysis systems make it nearly impossible to repeat sampling from a consistent location. Still further, existing portable core analysis systems lack appropriate methods and sufficient precision to produce meaningful data, whereas larger, more powerful core analysis systems require installation in laboratories with controlled environments, where only trained technicians are authorized to work. More generally, existing systems require substantial technician input and oversight for operation.

[0004] Existing systems have a relatively low throughput that can serve as a bottleneck during exploration and analysis. Further, existing systems are limited in terms of customizability for different types of samples, conditions, and desired information to be obtained from the samples.Attorney Docket No. 36362.0259P1

[0005] Thus, there is a need for systems and methods that address one or more of the deficiencies of known systems and methods for analyzing material samples (e.g.. core or rock samples).SUMMARY

[0006] Disclosed herein is a system for analyzing material samples. In exemplary applications, the disclosed system can be particularly useful when processing large volumes of material samples. The system can comprise a loading station that is configured to receive a plurality of containers holding the material samples. The system can further comprise a plurality of scanning modules, wherein each scanning module of the plurality of scanning modules is configured to capture data associated with the material samples. A computing device can be configured to: receive the data associated with the material samples, wherein the received data corresponds to the data captured by the plurality of scanning modules; and coregister the received data associated with the material samples. A conveyor can be configured to cany the plurality of containers holding the material samples from the loading station to each scanning module of the plurality of scanning modules along a conveyance path.

[0007] Additional advantages of the disclosed apparatuses, systems, and methods will be set forth in part in the description that follows, and in part will be obvious from the description, or may be learned by practice of the claimed invention. The advantages of the disclosed devices and systems will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.DESCRIPTION OF THE DRAWINGS

[0008] FIG. 1 is a perspective view of an exemplar}' system for analyzing samples as disclosed herein.

[0009] FIG. 2 is a schematic diagram of an exemplary system for analyzing samples as disclosed herein.Attorney Docket No. 36362.0259P1

[0010] FIG. 3 is a schematic diagram of an exemplary system for analyzing samples as disclosed herein.

[0011] FIG. 4 is a schematic diagram illustrating rearrangement of containers of samples.

[0012] FIG. 5 is a schematic diagram illustrating a loading area wherein samples are rearranged.

[0013] FIG. 6 is a schematic diagram of a robotic arm of a loading area.

[0014] FIG. 7 is a schematic diagram of a gantry of a loading area.

[0015] FIG. 8 is a partial side view of an exemplary scanning module having an electromagnetic data capture assembly scanner and a high-energy scanning head.

[0016] FIG. 9 is a sectional view of a high-energy' scanning head of an exemplary7scanning module.

[0017] FIG. 10 is a schematic diagram of an exemplary sample preparation station.

[0018] FIG. 11 is a perspective view of an exemplary sensing head assembly as disclosed herein.

[0019] FIG. 12 is another perspective view of the exemplary7sensing head assembly of FIG.11.

[0020] FIG. 13 is another perspective view of the exemplary sensing head assembly of FIG.11.

[0021] FIG. 14 is a partial perspective view of a portion of a sensing module as disclosed herein.

[0022] FIG. 15 is a top plan view of the sensing module of FIG. 14.

[0023] FIG. 16 is a perspective view of a belt conveyor of the sensing module of FIG. 14.

[0024] FIG. 17 is a perspective view of the sensing module of FIG. 14 with an enclosure.

[0025] FIG. 18 is a block diagram of a computing system including a computing device for operating the system as disclosed herein.Attorney Docket No. 36362.0259P1

[0026] FIG. 19 is a block diagram of a machine learning system.

[0027] FIG. 20 is a flowchart illustrating an example training method.

[0028] FIG. 21 is a schematic top view of an exemplary load sensing assembly.

[0029] FIG. 22 is a schematic side view of an exemplary load sensing assembly.DETAILED DESCRIPTION

[0030] The present invention now will be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. Indeed, this invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. Like numbers refer to like elements throughout. It is to be understood that this invention is not limited to the particular methodology and protocols described, as such may vary'. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the present invention.

[0031] Many modifications and other embodiments of the invention set forth herein will come to mind to one skilled in the art to which the invention pertains having the benefit of the teachings presented in the foregoing description and the associated drawings. Therefore, it is to be understood that the invention is not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

[0032] As used herein the singular forms “a,” “an,” and “the” include plural referents unless the context clearly dictates otherwise. For example, use of the term “a scanning module” constitutes disclosure of a single scanning module and, unless context dictates otherwise, further constitutes disclosure of two or more scanning modules, and so forth.

[0033] All technical and scientific terms used herein have the same meaning as commonly understood to one of ordinary skill in the art to which this invention belongs unless clearly indicated otherwise.Attorney Docket No. 36362.0259P1

[0034] Ranges can be expressed herein as from “about’' one particular value, and / or to “about” another particular value. When such a range is expressed, another aspect includes from the one particular value and / or to the other particular value. Similarly, when values are expressed as approximations, by use of the antecedent “about,” it will be understood that the particular value forms another aspect, and it will be further understood that use of the term “about” represents disclosure of a range of values that are within 15%, within 10%, or within 5%, or within 1% of the particular value. It will be further understood that the endpoints of each of the ranges are significant both in relation to the other endpoint, and independently of the other endpoint.

[0035] As used herein, the terms “optional” or “optionally” mean that the subsequently described event or circumstance may or may not occur, and that the description includes instances where said event or circumstance occurs and instances where it does not.

[0036] The term “substantially perpendicular” is meant to indicate that elements (e.g., axes) are perpendicular within a given plane or oriented at an angle of less than 15 degrees (optionally, less than 10 degrees) relative to each other within the given plane.

[0037] Disclosed herein, and with reference to FIGS. 1-3, is a system 10 for analyzing material samples (e g., geological samples such as core or rock samples). According to various aspects, the system 10 can acquire data such as image data, geometric data, spectral data (including spectral data outside of the visible spectrum (e.g., hyperspectral data)), and / or emissions in response to sample bombardment with high energy’ photons (e.g., X-ray fluorescence and backscatter). As further disclosed herein, the disclosed system 10 can be configured for high-volume sample processing. In exemplary aspects, the disclosed system 10 can be a fully integrated, autonomous material analysis system that provides repeatable, location-identified, quantifiable sample data that can be produced in a time window (e.g., within minutes or hours) that is far less than that required to complete conventional material sample analysis, particularly during high-volume sample analysis.

[0038] The system 10 can comprise a loading station 12 that is configured to receive a plurality of containers 20 holding the material samples. For example, the loading station 12 can comprise an area that is configured to receive a pallet having a plurality of containers 20 thereon. In other aspects, the loading area 12 can be configured to receive individual containers (e.g., one or more containers 20 placed on the loading area 12). For example, theAttorney Docket No. 36362.0259P1 loading area 12 can comprise a portion of a conveyor onto which an operator can place one or more containers 20.

[0039] In some aspects, the plurality of containers 20 can comprise trays. The trays can be configured to receive material samples (e.g., core or rock samples) therein. In additional aspects, the trays can be configured to hold rock chips or rock powder samples. More generally, the plurality of containers 20 can be configured to hold rock chips or rock powder samples. For example, the plurality of containers 20 can comprise one or more jars (e.g., cylindrical jars). In additional or alternative aspects, the plurality of containers 20 can contain pulp, such as that conventionally processed in a lab. In some aspects, the pulp can be formed from core samples. In other aspects, the pulp can be formed from any other suitable geological source. Optionally, it is contemplated that the containers 20 (e g., trays) can be configured to hold combinations or mixtures of core or rock samples, rock chips, rock powder, and / or pulp. In exemplary' aspects, the plurality of containers 20 can comprise flexible containers that can contain core or rock samples obtained from reverse circulation drilling.

[0040] The system 10 can further comprise a plurality of scanning modules 30. Each scanning module of the plurality of scanning modules 30 can be configured to capture data associated with the material samples. For example, at least one scanning module 30 can be configured to perform high energy' scanning, such as X-ray fluorescence. At least one scanning module 30 can be configured to perform a 3D scan, such as LiDAR scanning. In some optional aspects, the LiDAR can be blue laser LiDAR to provide optimal resolution. At least one scanning module 30 can be configured to perform laser induced breakdown spectroscopy (LIBS). At least one scanning module 30 can be configured to perform UV spectroscopy. At least one scanning module 30 can be configured to perform hyperspectral spectroscopy. Optionally, one module 30 can comprise a plurality' of sensors. For example, a single module can comprise at least one camera 220 and at least one LiDAR sensor 230. In further aspects, each respective module can comprise at least one respective sensor that is configured to permit coregistration between modules. That is, the respective sensors of the modules can be used to associate data captured by each module in the same spatial reference frame. Accordingly, the various data from each module can be superimposed. For example, in some aspects, each module can comprise at least one respective LiDAR sensor 230, and corresponding features captured by LiDAR can be used to coregister data from each module.Attorney Docket No. 36362.0259P1In other aspects, each module can comprise a camera 220, and corresponding features captured by the camera can be used to coregister data from each module (e.g., optionally, associating RGB pixels from each camera). By providing each respective module with these capabilities, it is contemplated that the precision and accuracy of coregistration can be maximized.

[0041] A conveyor 40 can be configured to carry the plurality of containers 20 holding the material samples from the loading station 12 to each of the plurality of scanning modules 30 along a conveyance path 42. In exemplary' aspects, the conveyor 40 can comprise one or more belt conveyors or one or more power rollers or chain drives. In additional aspects, the conveyor 40 can comprise a pin and pull conveyor. Referring also to FIGS. 5-7, the conveyor 40 can comprise a robotic manipulator, such as a multi-axis arm or a gantry. Optionally, the gantry can be a multi-axis gantry. In still additional aspects, the conveyor 40 can comprise a positioner plate, such as an X-Y positioner plate or an X-Y-Z positioner plate. The positioner plate can move with one or more containers resting thereon to carry the one or more containers. In exemplary aspects, the conveyor 40 can comprise at least one loading / unloading apparatus, such as, for example, a multi-axis arm or gantry, for moving containers onto and off of a positioning plate. The conveyor 40 can further comprise one or more belts or rollers for moving the containers between scanning modules 30.

[0042] Referring to FIG. 14, in some aspects, the conveyor 40 can comprise a plurality of driven rollers 46 and a belt conveyor 47. The belt conveyor 47 can extend through at least a portion of the scanning module 30. The plurality of driven rollers 46 can deliver the container to the belt conveyor 47. In some aspects, the belt conveyor 47 can comprise a flexible belt. In other aspects, the belt conveyor can comprise a plurality of chain links. In this way, the belt conveyor can permit dust and dirt to fall therethrough the openings formed between and / or within the chain links. In some aspects, the plurality of chain links can comprise links (e.g., polymer links) with a nonslip (e.g., rubber) coating. In additional or alternative aspects, the conveyor 40 can comprise a chain drive conveyor (e.g., a chain drive roller conveyor). In some aspects, at least a portion of the conveyor 40 (e.g., the belt conveyor 47 or chain drive conveyor) can be configured to move containers in forward and reverse.

[0043] Optionally, at least a portion of the conveyor 40 (e.g., the belt conveyor 47) can be supported by a load sensing assembly 48. For example, referring to the schematic top viewAttorney Docket No. 36362.0259P1 shown in FIG. 21, the load sensing assembly 48 can comprise one or more supports 49 extending between a frame 38 of the sensing module 30 and the portion of the conveyor 40 and respective strain sensors 51 configured to measure strain in the one or more supports, with the measured strain corresponding to or indicative of the load supported by the one or more supports. In additional aspects, and as shown in the schematic side view of FIG. 22, said portion of the conveyor 40 can be supported on one or a plurality of load cells 53. In this way, when the container is received on the portion of the conveyor 40, the load sensing assembly can determine the weight of the container. Optionally, in these aspects, containers 20 having a know n weight can be used to determine a weight of sample material in the container (by deducting the known weight of the container from the measured total w eight of the container and sample). In other aspects, the containers (e.g., jars) can have a known volume. Further, volume can be determined based on topography data of the sample. Exemplary details of how volume can be determined are disclosed in International Patent Application Publication No. WO 2022 / 023404A1, published February73, 2022, the entirety7of which is incorporated by reference herein for all purposes. For example, in some aspects, a geological (e.g., core or rock) sample can be placed in a core tray or other container. The geological sample can be scanned with an electromagnetic 3D scanner (e g., lidar) to obtain a sample surface. The volume can be computed by comparing the sample surface to a reference surface (e.g., an upper surface of the container). In some aspects, the electromagnetic 3D scanner can scan an empty container to provide the reference surface. Accordingly, the difference between the reference surface and the sample surface integrated over the area of the container can provide the volume of the sample. Therefore, density can be determined based on the weight of the sample divided by the volume.

[0044] Referring to FIG. 15, in some aspects, at least one guide surface 70 can be configured to direct movement of a container 20 moving on the conveyor. For example, the at least one guide surface 70 can comprise a pair of converging surfaces 72 that serve as a funnel to position and align the container. In further aspects, a pair of parallel walls can orient the container.

[0045] In some aspects, a positioning assembly 74 can be configured to position the container 20 on the conveyor 40 along a transverse axis 75. For example, a pair of longitudinally- extending rails 77 can move inwardly from opposite transverse sides to push the container toward a centerline (e.g., a longitudinal axis 73). Optionally, in these aspects, the pair ofAttorney Docket No. 36362.0259P1 longitudinally extending rails can be spring-loaded so that the longitudinally extending rails bias the container toward each other, thereby positioning the container at the centerline when the opposed forces equalize. In additional aspects, the pair of longitudinally extending rails can be actuatable (e.g., electrically, pneumatically, or hydraulically) to move toward each other to position the container.

[0046] In further aspects, at least one stop surface 76 can inhibit further movement of the container to set a position of the container within the scanning module. In some aspects, the at least one stop surface 76 can comprise a hard stop. That is, the stop surface can have no give. In other aspects, the stop surface can be a soft stop, permitting some further movement of the container. In this way, the system can prevent jostling of the contents within the container.

[0047] Referring to FIG. 16, in some aspects, a shielding shelf 78 can be embedded within the conveyor. For example, the shielding shelf 78 can be surrounded by the belt of the belt conveyor. In other aspects, the shielding shelf 78 can be below the conveyor. In some aspects, the shielding shelf 78 can comprise lead. The shielding (e.g., lead) shelf can be configured to absorb and dissipate photons from the high energy' photon emitter(s) of an XRF head.

[0048] Further, it is contemplated that two or more scanning modules 30 can be configured to collect the same data. For example, some scanning modules 30 can require longer scanning times (e.g.. XRF modules) than other scanning modules (e.g.. imaging / camera modules). Accordingly, a first scanning module 30a having a shorter scan time can feed containers to, or receive containers from, two or more additional scanning modules (e.g., second and third scanning modules 30b, c upstream or downstream of the first scanning module 30a) having a relatively longer scan time. Referring to FIG. 2, optionally, the two (or more) additional scanning modules can be arranged in series, in which case a first container passes the second scanning module 30b without scanning to arrive at the third scanning module 30c (downstream of the second scanning module 30b), and a second container can then be fed to the second scanning module 30b. In this way, the second and third modules 30a, b can receive samples and perform parallel scanning. In additional aspects, and with reference to FIG. 3, the conveyor 40 can branch to feed multiple scanning modules (e.g., module 30a, 30b, 30c) in parallel. Optionally, in these aspects, the conveyance path 42 can split and converge again downstream. For example, in some aspects, the convey or can split betweenAttorney Docket No. 36362.0259P1 two or more modules 30 arranged in parallel. The conveyor 40 can then move containers from said two or more modules arranged in parallel to a single module 30 downstream.

[0049] In some aspects, one or more modules 30 of the plurality of scanning modules can be bypassed, for example, based on data obtained from at least one other scanning module 30. In this way, certain samples need not consume scanning time when, for example, other scan data indicates the lack of a need for obtaining certain scan data.

[0050] The system 10 can further comprise a computing device 1001 configured to receive the data associated with the material samples, the received data corresponding to the data captured by the plurality of scanning modules. The computing device 1001 can further be configured to coregister the received data associated with the material samples. That is, the computing device 1001 can be configured to associate different data (e.g., data obtained from multiple modules) corresponding to the same portions of the core or rock sample. As one example, image data (e.g., RGB image data) can be associated with X-ray fluorescence (XRF) data in order to associate image data of portions of the core or rock sample with XRF data of the same portion of the core or rock sample. It is contemplated that the coregistered data need not be an exact coregistration (e.g., the coregistered data need not be an exact pixel-by-pixel or point-by-point coregistration). For example, the data can have different resolution size. Further, data need not be associated with identical points in space. For example, XRF data can be obtained along a single axis, whereas image data can be 2- dimensional or three-dimensional. Accordingly, the coregistration refers to association of like areas of the core or rock sample with respective types of data. More generally, different data can be overlaid to collectively permit analysis of the core or rock sample as a whole.

[0051] In some aspects, the system 10 can further comprise at least one preparation station 50 positioned between the loading station 12 and at least one scanning module 30 of the plurality of scanning modules along the conveyance path 42. Optionally, in these aspects, the preparation station(s) 50 can be positioned between the loading station and each scanning module of the plurality of scanning modules along the conveyance path 42. In various aspects, the one or more preparation stations 50 can be configured to perform one or more of: cleaning the samples; degreasing the samples; vacuuming the samples to remove debris, blasting the samples with CO2; applying (e.g., drawing) an orientation line on a core sample; applying an identification tag to the material or the container; or arranging the samples. For example, to arrange the samples, the one or more preparation stations 50 can be configured toAttorney Docket No. 36362.0259P1 level, centralize, and or position the samples within their respective containers 20. For example, in some aspects, the preparation station can comprise a shaker that is configured to permit sample pieces to settle within the container. In other aspects, the preparation station can comprise at least one robotic arm or gantry with an end effector that is configured to pick up, place, shift, move, or otherwise arrange the samples within their respective containers. In some aspects, the one or more preparation stations 50 can be configured to arrange the samples to set gaps between adjacent core segments or rocks. For example, the preparation station 50 can use the robotic arm or gantry with the end effector can then manipulate the samples to obtain a desired arrangmenet. In additional aspects, the preparation station 50 can use topographical data from a sensor as disclosed herein to detect sample positions. In additional aspects, the one or more preparation stations can be configured to arrange an angle of leaning of the material (e.g., core or rock) samples (e.g., leaning the container toward an operator for ergonomics). For example, in some aspects, the preparation station 50 can comprise a movable segment of the conveyor 40 and an actuator configured to pivot the movable segment of the conveyor (toward the operator). Optionally, the actuator can pivot the movable segment of the conveyor 40 about an axis parallel to the conveyance axis 42. The segment of the conveyor 40 can be configured to pivot the container at least 20 degrees, at least 30 degrees, or at least 45 degrees to provide an ergonomic position for the operator to arrange the sample within the container. In this way, the samples can be arranged to provide an optimal scanning path. For example, it is contemplated that scanning, such as X-ray fluorescence, can provide optimal accuracy when incident on certain parts of a sample (e.g., a ridgeline corresponding to a highest portion of the core sample along an axis). Accordingly, in some aspects, at least one preparation station can prepare the samples so that the ridgeline deviates minimally along an axis transverse to a scanning axis of at least one scanning module 30. In some aspects, the preparation station 50 configured to apply an identification tag to the material or the container can comprise a label applicator. The label applicator can comprise a mechanical device (e.g., an arm on a swivel) that engages the container or a robotic arm. In other aspects, the identification tag can be applied by a printer.

[0052] In some aspects, the system 10 can comprise an operator presentation station 60. The operator presentation station 60 can be configured to present core or rock samples to an operator for manipulation of the samples. The operator presentation station 60 can permit an operator to intervene with samples in any way, such as, for example, cleaning the samples; degreasing the samples; vacuuming the samples to remove debris, blasting the samples withAttorney Docket No. 36362.0259P1CO2; applying (e.g., drawing) an orientation line on a core sample; applying an identification tag to the material or the container; or arranging the samples. In some aspects, the operator presentation station 60 can tip the container to the operator. For example, in some aspects, the presentation station 60 can comprise a movable segment of the conveyor 40 and an actuator configured to pivot the movable segment of the conveyor (toward the operator). Optionally, the actuator can pivot the movable segment of the conveyor 40 about an axis parallel to the conveyance axis 42. The segment of the conveyor 40 can be configured to pivot the container at least 20 degrees, at least 30 degrees, or at least 45 degrees to provide an ergonomic position for the operator to work with or operate on the sample within the container. In other aspects, operator presentation station can divert a container from the conveyance path 42. For example, the operator presentation station 60 can comprise a conveyor that moves a container out from the conveyance path 42. Optionally, one or more containers can pass a container received at the operator presentation station 60 along the conveyance path 42, thereby minimizing or eliminating disruption of processing (e.g., scanning at the plurality of scanning modules 30) to maximize throughput. In still additional aspects, the system 10 can comprise a stop input device (e.g., a button) that ceases movement of at least a portion of the conveyor 40 to enable the operator to manipulate a container or a sample within the container.

[0053] In exemplary aspects, the computing device 1001 can be configured to coregister the data to within a resolution of ±5 mm, or within a resolution of ±4 mm, or within a resolution of ±3 mm, or within a resolution of ±2 mm, or w ithin a resolution of ±1 mm. It is further contemplated that the computing device can be configured to coregister the data to within a resolution of ±0.5 mm. or ±0.25 mm, or ±0.1 mm.

[0054] In some aspects, resolution of coregistration can be based on the type of system used for achieving coregistration. For example, in some aspects, coregistration can be maintained within a first resolution (e.g., ±lmm) using mechanical devices such as conveyors with servos having such resolution. In further aspects, digital sensing (e.g., camera and LiDAR) can obtain a second, higher resolution (e.g., ±0.5mm). In still further aspects, resolution can further be improved using mathematical methods, such as artificial intelligence, machine learning, or neural networks (e.g., using RGB images). In some aspects, improving resolution can require extra time and / or processing. Accordingly, it is contemplated that theAttorney Docket No. 36362.0259P1 system 10 can permit selection of a desired resolution to achieve the goals of a particular analysis.

[0055] In some aspects, coregistration can be effected by using known reference points relative to each container. For example, each scanning module 30 can establish a coordinate system relative to one or more markings on each container 20. Accordingly, data acquired by the one or more sensors of each scanning module 30 can be associated with the coordinate system relative to the one or more markings on the container. In additional aspects, coregistration can be effected by using features of the samples themselves. For example, at least one sensor can be configured to capture 3D topographical measurements of the sample. Such a sensor can use, for example, laser (e.g., optionally, blue, red, or green laser), photogrammetry, ultrasound, and / or radar to capture 3D topographical measurements of the sample. One or more features of the 3D topographical measurements of the sample can be used to associate data captured by different sensors of different scanning modules. In some aspects, each scanning module 30 can comprise a respective sensor configured to capture 3D topographical measurements of the sample (e.g., LiDAR). In some aspects, data between each scanning module 30 can be coregistered based on topographical features of the sample captured at each module. Accordingly, in some aspects, a first set of data to be captured following handling by an operator can be 3D topographical measurements. In additional aspects, data from each scanning module 30 or between respective scanning modules 30 can be coregistered based on image data (e g., RGB pixel data). In further aspects, optical data (e.g., LiDAR data or camera images) can be captured before and after scanning to confirm that the sample has not moved. In further aspects, methods disclosed in International Patent Application Publication No. 2011 / 146014A1, which is hereby incorporated by reference herein for all purposes, can be used to associate data captured by different sensors.

[0056] In some aspects, the conveyance path 42 can be linear. That is, the conveyance path 42 can carry the containers 20 from one scanning module 30 to the next in a sequence. Accordingly, the linear conveyance path need not be straight, although, in some aspects, it can be linear along a single axis. In other aspects, the conveyance path 42 can comprise a plurality7of parallel branches 44, as illustrated in FIG. 3. A first branch of the plurality of parallel branches 44 can be configured to transport a first container to a first scanning module of the at least two scanning modules, and a second branch can be configured to transport a second container to a second scanning module of the at least two scanning modules.Attorney Docket No. 36362.0259P1

[0057] Referring to FIG. 3, the system can comprise one or more accumulators 60 configured to hold at least one container 20 until a downstream module is ready to receive the at least one container. An accumulator can be positioned between adjacent modules to permit a container to leave a first module without being received by a second module. In this way, bottlenecks due to relatively slower modules can form a queue of one or more containers 20 without stopping operation of upstream modules. In some aspects, the accumulator can comprise a section of conveyor 40 between tw o scanning modules that is configured to hold a plurality of containers 20. Optionally, in these aspects, the accumulator 62 can comprise an elongated portion of the conveyor 40. In additional aspects, the accumulator 62 can comprise a section of conveyor that extends outwardly from the conveyance path 42. For example, the accumulator 62 can remove one or more containers from the conveyance path 42 and feed the one or more containers back into the conveyance path once space for the container in a scanning module is available.

[0058] In some aspects, at least one scanning module 30 of the plurality of scanning modules can comprise a replaceable head. For example, each scanning module with a replaceable head can comprise a scanning head mount that is configured to receive a modular sensor (e.g., an XRF head, a LiDAR sensor, a LIBS sensor, a UV spectroscopy sensor, one or more spectral sensors configured to obtain hyperspectral data, one or more magnetic susceptibility sensors, one or more gamma sensors, or one or more Raman sensors.). In some aspects, the scanning head mount can provide a known spatial position within the scanning module 30. In further aspects, the scanning head mount can comprise at least one actuator 32 (e.g., a vertical actuator) configured to move the scanning head mount and attached modular sensor(s). In some examples, the scanning head mount can comprise, for example, a 2-way locator or a 4- way locator. In additional examples, the scanning head mount can comprise a V-block or a dovetail attachment structure. More generally, the scanning head mount can permit repeatable coupling of the modular sensor in a know n position.

[0059] Referring to FIGS. 11-13, in various aspects, one or more scanning modules can comprise a sensing head 34, wherein the sensing head comprises a plurality of sensors. For example, the scanning head 34 can comprise a high-energy scanning head 110, a camera 220, a LiDAR sensor 230, and an electromagnetic data capture assembly 200. In some aspects, the sensing head can be coupled to an actuator 32 so that all sensors of the sensing head move together. In some aspects, each sensing head 34 can comprise a LiDAR sensor.Attorney Docket No. 36362.0259P1

[0060] In some aspects, at least one second actuator 36 can move one or more conveyors transversely to the longitudinal axis (e.g., along transverse axis 75). In this way, one or more sensors (e.g., an XRF head) can be positioned relative to each compartment of a core box.

[0061] In some aspects, the loading station 12 can be configured to reorder the plurality of containers. For example, referring to FIGS. 4-5, containers (e.g., core trays) can be stacked on a pallet in an order in which the containers are filled. Accordingly, samples obtained last within a borehole can be on top of samples retrieved earlier. It can be advantageous to scan in order of retrieval. Accordingly, in some aspects, the loading station 12 can be configured to reorient the containers 20. For example, the loading station 12 can comprise a gantry 14 (FIG. 7) or a robotic arm 16 (FIG. 6) that is configured to reorient a plurality of containers. In some aspects, the robotic arm can be a multi-axis robotic arm, such as, for example, a 3- axis robotic arm, a 4-axis robotic arm, or a 5-axis robotic arm. In some aspects, the robotic arm or the gantry can be configured to rearrange the containers in accordance with a predetermined routine, as illustrated in FIG. 4, in which an order of containers within a stack is inverted.

[0062] In additional aspects, the loading station 12 can be configured to identify each container. For example, the loading station 12 can comprise a scanner that is configured to obtain an identifier (e.g., alphanumeric code, barcode, QR code, data matrix, RGB code, or RFID (optionally, BLUETOOTH RFID)) of each container. Optionally, in these aspects, an identify of each container can be used to determine a proper position of each container. For example, the gantry 14 (FIG. 7) or the robotic arm 16 (FIG. 6) can arrange containers based on the identifier of each container. In further aspects, the computing device 1001 can be configured to associate the identifier associated with the container with at least one attribute of the container. For example, the at least one attribute can comprise a drill site, a drill hole, a rill depth (e.g., a start depth or an end depth), and / or a container sequence number.

[0063] In some aspects, the computing device 1001 can be configured to determine at least one of: a correct order of containers; an incorrect order of containers; or an absence of a container. In further aspects, the computing device 1001 can be configured to determine if a container is unfit for the system to handle, has a loading error (e.g.. is improperly oriented), or cannot be transported by the conveyor.Attomey Docket No. 36362.0259P1

[0064] In some aspects, the loading station can comprise at least one imaging device (e.g., a camera or an electromagnetic detector such as LiDAR). In some aspects, the at least one imaging device can comprise a camera that is configured to capture color image data. Images from the imaging device can be used to identify samples and / or to perform quality control checks, such as determining if a container is unfit for the system to handle, has a loading error (e.g., being improperly oriented), or cannot be transported by the conveyor.

[0065] In some aspects, the system 10 can comprise an unloading station 18. In some aspects, the unloading station 18 can be proximate to the loading station 12. Optionally, in these aspects, the gantry 14 (FIG. 7) or the robotic arm 16 (FIG. 6) of the loading station 12 can also be configured to remove containers from the loading station.

[0066] Referring to FIG. 16, in some aspects, at least one scanning module can comprise an enclosure 80 having an interior. In some aspects, the enclosure can be configured to inhibit light from traveling between the interior and the exterior of the scanning module. For example, the enclosure 80 can comprise doors that form light seals with a remainder of the enclosure. In this way, operators can be protected from UV light inside the enclosure. Further, the interior can be protected from light outside the enclosure. In additional aspects, the enclosure can be configured to mitigate noise. More generally, portions of the system 10 (e.g., the conveyors 40) can be enclosed or can comprise noise-mitigating components. For example, the enclosure can comprise a dense material for absorbing sound. In other aspects, the enclosure can comprise sound insulating foam. In other aspects, portions of the system (e.g., the conveyors) can be supported on dampers that reduce noise.Exemplary Stations and Modules

[0067] Referring to FIGS. 8-9, at least one scanning module 30 can comprise a high-energy scanning head 110 (e.g., an XRF head). The high-energy scanning head 110 can comprise at least one high-energy photon emitter 112 configured to emit high-energy photons at the sample, and at least one corresponding detector 114 (e.g., a photodiode) configured to detect photons excited by the emitted high-energy photons and emitted from the analyte (e.g., response X-rays such as fluorescence and backscatter). In some aspects, the XRF subassembly 110 can comprise a plurality of high-energy photon emitters 112 and respective detectors 114. For example, the plurality of high-energy photon emitters 112 can be configured to emit photons with different respective energies. In some aspects, the high-Attorney Docket No. 36362.0259P1 energy photon emitter(s) 112 can emit photons having an energy level from about 5 KeV to about lOKev, or from about lOKeV to about 20KeV (e.g., about 15KeV), or from about 40KeV to about 60 KeV (e.g., about 50 KeV), or above 50 KeV.

[0068] Referring to FIG. 8, at least one scanning module 30 can comprise an electromagnetic data capture assembly 200. The electromagnetic data capture assembly 200 can be configured to capture spectral data. In some aspects, an actuator effect movement between the electromagnetic data capture assembly 200 and the sample to scan across the sample. For example, the actuator can comprise a movable stage that is configured to move the container relative to the electromagnetic data capture assembly 200. In other aspects, the electromagnetic data capture assembly 200 can be movable. In some aspects, and as shown schematically in FIG. 8, the electromagnetic data capture assembly 200 can comprise a first spectral band sensor 202a that is configured to capture spectral data within a first frequency range. A first optical pathway 204a can direct light between a first sample capture area 206a and the first spectral band sensor. In some aspects, the electromagnetic data capture assembly 200 can further comprise a second optical sensor 202b that is configured to capture spectral data within a second frequency range. A second optical pathway 204b can direct light between a second sample capture area 206b and the second spectral band sensor 202b. The second sample capture area can overlap with the first sample capture area along an axis along which the core or rock sample is moved relative to the electromagnetic data capture assembly 200. In this way, spectral data (e.g., hyperspectral data) from the spectral band sensors can be coregistered. Optionally, and as shown, the first and second optical pathways 204a, b can be incident on an overlapping region. For example, light from a single region can be split into the first and second optical pathways 204a.b (e.g., via a prism or partially reflective mirror) and then directed (e.g., via mirrors) to the respective first and second optical sensors 202a, b.

[0069] The spectral data can be coregistered with the high-energy (e.g., XRF) data to provide amalgamated data of the core or rock sample. The spectral data can be hyperspectral data. For example, the spectral data can include data outside of the visible spectrum (e.g., ultraviolet and / or infrared). The spectral data can then be associated with XRF data from the XRF subassembly 110. Optionally, spectral data and XRF data can be captured by the same scanning module 30. In other aspects, spectral data and XRF data can be captured by separate scanning modules 30.Attorney Docket No. 36362.0259P1

[0070] PCT Application Nos. PCT / US2024054709;filed November 6, 2024, and PCT / US2024 / 030793, filed May 23. 2024, each of which is incorporated by reference herein in its respective entirety, describes additional aspects of high-energy scanning and spectral data scanning consistent with the present disclosure.

[0071] Referring to FIG. 10. in some aspects, an exemplary preparation station 50 can comprise or be a CO2 blasting station 300. The CO2 blasting station 300 can comprise a nozzle 330 in communication with a supply of solid CO2 particles and a compressed air supply 336 configured to accelerate the solid CO2 particles to the nozzle 330. The sample and nozzle can be moved relative to each other to clean at least a portion of the sample. In some aspects, the CO2 blasting station 300 can further comprise a heat gun 340 or a desiccated air supply 342 configured to impinge the sample. In various further aspects, the sample and the nozzle 330 can be contained within a controlled environment 550 (e.g., vacuum or nitrogen-purged / Ch-free environment). Optionally, a fume hood can draw' dust and debris from the CO2 blasting station 300.

[0072] In additional aspects, the preparation station 50 can be configured to w ash or otherwise remove dirt from the sample. For example, the preparation station 50 can be configured to spray washing fluid (e.g., water) on the sample. The preparation station 50 can comprise a nozzle (or a plurality of nozzles) that is configured to deliver washing fluid on the sample. The preparation station 50 can further comprise a fluid source (e.g., a fluid tank or a conduit in communication with a w ater source). The preparation station 50 can further comprise a pump that is configured to pump the washing fluid to the nozzle. Further, the preparation station 50 can comprise an actuator that is configured to effect relative movement between the sample and the nozzle (e.g., moving the nozzle relative to the sample or moving the sample relative to the nozzle).Computing System

[0073] FIG. 18 shows an exemplary' computing system 1000 that can be configured to control operation of various aspects of the system 10, such as, for example, coordinating movement of the conveyor, operation of the various scanning modules, and data processing (e.g., coregistration) and storage.

[0074] Computing system 1000 can include a computing device 1001 (or a plurality of computing devices) and a display 1011 in electronic communication with the computingAttorney Docket No. 36362.0259P1 device, which can be any conventional computing device, such as, for example and without limitation, a personal computer, computing station (e.g., workstation), portable computer (e.g., laptop, mobile phone, tablet device), smart device (e.g., smartphone, smart watch, activity tracker, smart apparel, smart accessory), security and / or monitoring device, a server, a router, a network computer, a peer device, edge device or other common network node, and so on. In some optional embodiments, a smart phone, tablet, or computer (i.e., a laptop or desktop computer) can comprise both the computing device 1001 and the display 1011. Alternatively, it is contemplated that the display 1011 can be provided as a separate component from the computing device 1001. For example, it is contemplated that the display 1011 can be in wireless communication with the computing device 1001, thereby allowing usage of the display 1011 in a manner consistent with that of the display of the smartphone as disclosed herein. In various aspects, the computing system 1000 can comprise a single computing device 1001 or a plurality of computing devices 1001 that cooperate to perform the various processes disclosed herein.

[0075] The computing device 1001 may comprise one or more processors 1003, a system memory 1012, and a bus 1013 that couples various components of the computing device 1001 including the one or more processors 1003 to the system memory 1012. In the case of multiple processors 1003, the computing device 1001 may utilize parallel computing.

[0076] The bus 1013 may comprise one or more of several possible types of bus structures, such as a memory bus, memory7controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures.

[0077] The computing device 1001 may operate on and / or comprise a variety of computer readable media (e.g., non-transitory). Computer readable media may be any available media that is accessible by the computing device 1001 and comprises, non-transitory, volatile and / or non-volatile media, removable and non-removable media. The system memory 1012 has computer readable media in the form of volatile memory, such as random access memory (RAM), and / or non-volatile memory7, such as read only memory' (ROM). The system memory71012 may store data such as scan data 1007 and / or program modules such as operating system 1005 and coregistration software 1006 that are accessible to and / or are operated on by the one or more processors 1003.Attorney Docket No. 36362.0259P1

[0078] The computing device 1001 may also comprise other removable / non-removable, volatile / non-volatile computer storage media. A mass storage device 1004 may provide nonvolatile storage of computer code, computer readable instructions, data structures, program modules, and other data for the computing device 1001. The mass storage device 1004 may be a hard disk, a removable magnetic disk, a removable optical disk, magnetic cassettes or other magnetic storage devices, flash memory cards, CD-ROM, digital versatile disks (DVD) or other optical storage, random access memories (RAM), read only memories (ROM), electrically erasable programmable read-only memory (EEPROM), and the like.

[0079] Any number of program modules may be stored on the mass storage device 1004. An operating system 1005 and the coregistration software 1006 may be stored on the mass storage device 1004. One or more of the operating system 1005 and the coregistration software 1006 (or some combination thereof) may comprise program modules and the coregistration software 1006. The scan data 1007 may also be stored on the mass storage device 1004. The scan data 1007 may be stored in any of one or more databases known in the art. The databases may be centralized or distributed across multiple locations within the network 1015.

[0080] A user may enter commands and information into the computing device 1001 via an input device (not shown). Such input devices comprise, but are not limited to, a keyboard, pointing device (e.g., a computer mouse, remote control), a microphone, a joystick, a scanner, tactile input devices such as gloves, and other body coverings, motion sensor, and the like These and other input devices may be connected to the one or more processors 1003 via a human machine interface 1002 that is coupled to the bus 1013, but may be connected by other interface and bus structures, such as a parallel port, game port, an IEEE 1394 Port (also known as a Firewire port), a serial port, network adapter 1008, and / or a universal serial bus (USB).

[0081] A display 101 1 may also be connected to the bus 1013 via an interface, such as a display adapter 1009. It is contemplated that the computing device 1001 may have more than one display adapter 1009 and the computing device 1001 may have more than one display 1011. A display 1011 may be a monitor, an LCD (Liquid Crystal Display), light emitting diode (LED) display, television, smart lens, smart glass, and / or a projector. In addition to the display 1011, other output peripheral devices may comprise components such as speakers (not shown) and a printer (not shown) which may be connected to the computing device 1001Attorney Docket No. 36362.0259P1 via Input / Output Interface 1010. Any step and / or result of the methods may be output (or caused to be output) in any form to an output device. Such output may be any form of visual representation, including, but not limited to, textual, graphical, animation, audio, tactile, and the like. The display 1011 and computing device 1001 may be part of one device, or separate devices.

[0082] The computing device 1001 may operate in a networked environment using logical connections to one or more remote computing devices 1014a,b,c. A remote computing device 1014a, b,c may be a personal computer, computing station (e.g., workstation), portable computer (e.g., laptop, mobile phone, tablet device), smart device (e.g.. smartphone, smart watch, activity tracker, smart apparel, smart accessory), security and / or monitoring device, a server, a router, a network computer, a peer device, edge device or other common network node, and so on. Logical connections between the computing device 1001 and a remote computing device 1014a, b,c may be made via anetwork 1015, such as a local areanetwork (LAN) and / or a general wide area network (WAN). Such network connections may be through a network adapter 1008. A network adapter 1008 may be implemented in both wired and wireless environments. Such networking environments are conventional and commonplace in dwellings, offices, enterprise-wide computer networks, intranets, and the Internet. In further exemplary aspects, it is contemplated that the computing device 1001 can be in communication with the remote computing devices 1014a, b,c through a Cloud-based network.

[0083] Application programs and other executable program components such as the operating system 1005 are shown herein as discrete blocks, although it is recognized that such programs and components may reside at various times in different storage components of the computing device 1001, and are executed by the one or more processors 1003 of the computing device 1001. An implementation of the module software 1006 may be stored on or sent across some form of computer readable media. Any of the disclosed methods may be performed by processor-executable instructions embodied on computer readable media.Machine Learning

[0084] Turning now to FIG. 19, a system 1100 is shown. The system 1100 may be configured to use machine learning techniques to train, based on an analysis of one or more training data sets 1150A-1150B by a training module 1200. at least one machine learningbased classifier 1300 that is configured to classify sample data as coregistered or notAttorney Docket No. 36362.0259P1 coregistered. The at least one machine learning-based classifier 1300 may comprise the machine learning module 1104B (e.g.. a segmentation model and / or a structural data model).

[0085] The system 1100 may determine (e.g., access, receive, retrieve, etc.) the training data set 1150A. The training data set 1150A may comprise first data sets (e.g., sets of sample data consistent with what is to be captured by the plurality of scanning modules 30 (FIG. 1)) associated with material samples (e.g., containers and / or geological samples ). The system 1 100 may determine (e.g., access, receive, retrieve, etc.) the training data set 1150B. The training data set 1150B may comprise second data sets (e.g., sample data consistent with what is to be captured by the plurality of scanning modules 30) associated with material samples. The first data sets and the second data sets may each contain one or more result datasets associated with material samples, and each result dataset may be associated with one or more data attributes. The one or more data attributes may include a threshold number points within a predetermined range, or one or more points within an absolute or average predetermined range, a combination thereof, and / or the like. Each result dataset may include a labeled list of results. The labels may comprise ‘'attribute data” (corresponding to data that indicates coregistered data) and “non-attribute data” (corresponding to data that is not coregistered).

[0086] Sample data sets may be randomly assigned to the training data set 1150B or to a testing data set. In some implementations, the assignment of data to a training data set or a testing data set may not be completely random. In this case, one or more criteria may be used during the assignment, such as ensuring that similar numbers of geological sample data sets are in each of the training and testing data sets. In general, any suitable method may be used to assign the data to the training or testing data sets, while ensuring that the distributions of sufficient quality and insufficient quality labels are somewhat similar in the training data set and the testing data set.

[0087] The training module 1200 may train the machine learning-based classifier 1300 by extracting a feature set from the training data set 1150 A according to one or more feature selection techniques. The training module 1200 may further define the feature set obtained from the training data set 1150A by applying one or more feature selection techniques to the training data set 1150B that includes statistically significant features of positive examples (e.g., data indicating sample data is coregistered) and statistically significant features of negative examples (e.g., data not indicating coregistered sample data). The feature setAttorney Docket No. 36362.0259P1 extracted from the training data set 1150A and / or the training dataset 115OB may comprise segmentation data and / or structural data as described herein. For example, the feature set may comprise features associated with data that are indicative of the one or more physical features described herein. The feature set may be derived from the segmentation data indicated by sample data and / or the structural data disclosed herein.

[0088] The training module 1200 may extract the feature set from the training data set 1150A and / or the training data set 1150B in a variety of ways. The training module 1200 may perform feature extraction multiple times, each time using a different feature-extraction technique. In an embodiment, the feature sets generated using the different techniques may each be used to generate different machine learning-based classification models 1350. For example, the feature set with the highest quality metrics may be selected for use in training. The training module 1200 may use the feature set(s) to build one or more machine learningbased classification models 1350A-1350N that are configured to indicate whether or not new sample data sets contain or do not contain data indicating a particular attribute(s) corresponding to coregistered data.

[0089] The training data set 1150A and / or the training data set 1150B may be analyzed to determine any dependencies, associations, and / or correlations between extracted features and the sufficient quality / insufficient quality labels in the training data set 1150 A and / or the training data set 1150B. The identified correlations may have the form of a list of features that are associated with labels for data indicating a particular attribute(s) of a corresponding sample and labels for data not indicating the particular attribute(s) of the corresponding sample. The features may be considered as variables in the machine learning context. The term ’‘feature,” as used herein, may refer to any characteristic of an item of data that may be used to determine whether the item of data falls within one or more specific categories. By way of example, the features described herein may comprise the one or more data attributes. The one or more data attributes may include threshold number points within a predetermined range, or one or more points within an absolute or average predetermined range, a combination thereof, and / or the like.

[0090] A feature selection technique may comprise one or more feature selection rules. The one or more feature selection rules may comprise a data attribute and a data attribute occurrence rule. The data attribute occurrence rule may comprise determining which data attributes in the training data set 1150 A occur over a threshold number of times andAttorney Docket No. 36362.0259P1 identifying those data attributes that satisfy' the threshold as candidate features. For example, any data attributes that appear greater than or equal to 8 times in the training data set 1150A may be considered as candidate features. Any data attributes appearing less than 8 times may be excluded from consideration as a feature. Any threshold amount may be used as needed.

[0091] A single feature selection rule may be applied to select features or multiple feature selection rules may be applied to select features. The feature selection rules may be applied in a cascading fashion, with the feature selection rules being applied in a specific order and applied to the results of the previous rule. For example, the data attribute occurrence rule may be applied to the training data set 1150A to generate a first list of data attributes. A final list of candidate features may be analyzed according to additional feature selection techniques to determine one or more candidate groups (e g., groups of data attributes). Any suitable computational technique may be used to identify the candidate feature groups using any feature selection technique such as filter, wrapper, and / or embedded methods. One or more candidate feature groups may be selected according to a filter method. Filter methods include, for example, Pearson’s correlation, linear discriminant analysis, analysis of variance (ANOVA), chi-square, combinations thereof, and the like. The selection of features according to filter methods are independent of any machine learning algorithms. Instead, features may be selected on the basis of scores in various statistical tests for their correlation with the outcome variable (e.g., data that indicate or do not indicate a particular attnbute(s) of a corresponding geological sample).

[0092] As another example, one or more candidate feature groups may be selected according to a wrapper method. A wrapper method may be configured to use a subset of features and train a machine learning model using the subset of features. Based on the inferences that drawn from a previous model, features may be added and / or deleted from the subset. Wrapper methods include, for example, forward feature selection, backward feature elimination, recursive feature elimination, combinations thereof, and the like. In an embodiment, forward feature selection may be used to identify one or more candidate feature groups. Forward feature selection is an iterative method that begins with no features in the machine learning model. In each iteration, the feature which best improves the model is added until an addition of a new feature does not improve the performance of the machine learning model. In an embodiment, backward elimination may be used to identify one or more candidate feature groups. Backward elimination is an iterative method that begins withAttorney Docket No. 36362.0259P1 all features in the machine learning model. In each iteration, the least significant feature is removed until no improvement is observed on removal of features. Recursive feature elimination may be used to identify one or more candidate feature groups. Recursive feature elimination is a greedy optimization algorithm which aims to find the best performing feature subset. Recursive feature elimination repeatedly creates models and keeps aside the best or the worst performing feature at each iteration. Recursive feature elimination constructs the next model with the features remaining until all the features are exhausted. Recursive feature elimination then ranks the features based on the order of their elimination.

[0093] As a further example, one or more candidate feature groups may be selected according to an embedded method. Embedded methods combine the qualities of filter and w rapper methods. Embedded methods include, for example. Least Absolute Shrinkage and Selection Operator (LASSO) and ridge regression which implement penalization functions to reduce overfitting. For example, LASSO regression performs LI regularization which adds a penalty equivalent to absolute value of the magnitude of coefficients and ridge regression performs L2 regularization which adds a penalty equivalent to square of the magnitude of coefficients.

[0094] After the training module 1200 has generated a feature set(s), the training module 1200 may generate a machine learning-based classification model 1350 based on the feature set(s). A machine learning-based classification model may refer to a complex mathematical model for data classification that is generated using machine-learning techniques. In one example, this machine learning-based classifier may include a map of support vectors that represent boundary features. By way of example, boundary features may be selected from, and / or represent the highest-ranked features in, a feature set.

[0095] The training module 1200 may use the feature sets extracted from the training data set 1150A and / or the training data set 1150B to build a machine learning-based classification model 1350A-1350N for each classification category (e.g., each attribute of a corresponding geological sample). In some examples, the machine learning-based classification models 1350A-1350N may be combined into a single machine learning-based classification model 1350. Similarly, the machine learning-based classifier 1300 may represent a single classifier containing a single or a plurality of machine learning-based classification models 1350 and / or multiple classifiers containing a single or a plurality of machine learning-based classification models 1350.Attorney Docket No. 36362.0259P1

[0096] The extracted features (e.g., one or more data attributes) may be combined in a classification model trained using a machine learning approach such as discriminant analysis; decision tree; a nearest neighbor (NN) algorithm (e.g., k-NN models, replicator NN models, etc.); statistical algorithm (e.g., Bayesian networks, etc.); clustering algorithm (e.g., k-means, mean-shift, etc.); neural networks (e g., reservoir networks, artificial neural networks, etc.); support vector machines (SVMs); logistic regression algorithms; linear regression algorithms; Markov models or chains; principal component analysis (PCA) (e.g., for linear models); multi-layer perceptron (MLP) ANNs (e.g., for non-linear models); replicating reservoir networks (e.g., for non-linear models, typically for time series); random forest classification; a combination thereof and / or the like. The resulting machine learning-based classifier 1300 may comprise a decision rule or a mapping for each candidate data attribute to assign one or more data to a class (e.g., indicating or not indicating a particular attribute(s) of a corresponding sample).

[0097] The candidate data attributes and the machine learning-based classifier 1300 may be used to predict a label (e.g., indicating or not indicating a particular attribute(s) of a coregistered data) for results in the testing data set (e.g., in a portion of the sample data sets). In one example, the prediction for each result in the testing data set includes a confidence level that corresponds to a likelihood or a probability that the corresponding data indicates or does not indicate a particular attribute(s) of a corresponding sample. The confidence level may be a value between zero and one, and it may represent a likelihood that the corresponding data belongs to a particular class. In one example, when there are two statuses (e.g., indicating or not indicating a particular attribute(s) of a corresponding sample data set), the confidence level may correspond to a value p. which refers to a likelihood that a particular data belongs to the first status (e.g., indicating the particular attribute(s)). In this case, the value 1-p may refer to a likelihood that the particular data belongs to the second status (e.g., not indicating the particular attribute(s)). In general, multiple confidence levels may be provided for each element of data and for each candidate data attribute when there are more than two statuses. A top performing candidate data attribute may be determined by comparing the result obtained for each data with the known sufficient quality / insufficient quality7status for each corresponding high energy photon data set associated with a geological sample in the testing data set (e.g., by comparing the result obtained for each data with the labeled data sets). In general, the top performing candidate data attribute for a particularAttorney Docket No. 36362.0259P1 attribute(s) of the corresponding set of data associated with a geological sample will have results that closely match the known indicating / not indicating statuses.

[0098] The top performing data attribute may be used to predict the indication / non-indication of data of a new set of data to confirm coregistry. For example, a new set of data may be determined / received. The new set of data may be provided to the machine learning-based classifier 1300 which may, based on the top performing data attribute for the particular attribute(s) of the corresponding geological sample, classify the data of the new set of high energy photon data associated with a geological sample as indicating or not indicating the particular attribute(s) (e.g.. indicating coregistry or not indicating coregistry).

[0099] As noted above, the application may provide an indication of one or more user edits made to any of the attributes indicated by the segmentation mask / overlay (or any created or deleted attributes) to the server 1104. For example, the user may edit any of the attributes indicated by the segmentation mask / overlay by dragging some of its points to desired positions via mouse movements in order to optimally delineate depictions of boundaries of the attribute(s). As another example, the user may draw or redraw parts of the segmentation mask / overlay via a mouse. Other input devices or methods of obtaining user commands may also be used. The one or more user edits may be used by the machine learning module 1104B to optimize the segmentation model and / or the structural data model. For example, the training module 1200 may extract one or more features from output high energy photon data containing one or more user edits as discussed above. The training module 1200 may use the one or more features to retrain the machine learning-based classifier 1300 and thereby continually improve results provided by the machine learning-based classifier 1300.

[0100] Turning now7to FIG. 5, a flowchart illustrating an example training method 1400 is shown. The method 1400 may be used for generating the machine learning-based classifier 1300 using the training module 1200. The training module 1200 can implement supervised, unsupervised, and / or semi-supervised (e.g., reinforcement based) machine learning-based classification models 1350. The method 1400 illustrated in FIG. 5 is an example of a supervised learning method; variations of this example of training method are discussed below, however, other training methods can be analogously implemented to train unsupervised and / or semi-supervised machine learning models.Attorney Docket No. 36362.0259P1

[0101] The training method 1400 may determine (e.g., access, receive, retrieve, etc.) a first data set and a second data set at step 1410. The first data set and the second data set may each contain one or more result datasets associated with geological samples, and each result dataset may be associated with one or more data attributes. The one or more data attributes may include a threshold number of points within a predetermined range, or one or more points within an absolute or average predetermined range, a combination thereof, and / or the like. Each result dataset may include a labeled list of results. The labels may comprise “attribute data’’ and “non-attribute data.”

[0102] The training method 1400 may generate, at step 1420, a training data set and a testing data set. The training data set and the testing data set may be generated by randomly assigning labeled results from the data sets to either the training data set or the testing data set. In some implementations, the assignment of labeled results as training or test samples may not be completely random. In an embodiment, only the labeled results for a specific geological sample type and / or class (e.g., geological samples having a particular degree of coregistry) may be used to generate the training data set and the testing data set. In an embodiment, a majority of the labeled results for the specific sample type and / or class may be used to generate the training data set. For example, 75% of the labeled results for the specific geological sample type and / or class may be used to generate the training data set and 25% may be used to generate the testing data set.

[0103] The training method 1400 may determine (e.g., extract, select, etc.), at step 1430, one or more features that can be used by, for example, a classifier to differentiate among different classifications (e.g., “attribute data” vs. “non-attribute data.”). The one or more features may comprise a set of one or more data attributes. The one or more data attributes may include a threshold number of detected photons having a particular energy or within a particular energy range, a spectral signature, a combination thereof, and / or the like. In an embodiment, the training method 1400 may determine a set of features from the data set (e.g., a plurality of points from corresponding sets of data that are associated with being coregistered. In another embodiment, the training method 1400 may determine a set of features from the data set. In a further embodiment, a set of features may be determined from labeled results from a geological sample type and / or class different than the type and / or class associated with the labeled results of the training data set and the testing data set. In other words, labeled results from the different geological sample type and / or class may be used for feature determination,Attorney Docket No. 36362.0259P1 rather than for training a machine learning model. The training data set may be used in conjunction with the labeled results from the different sample type and / or class to determine the one or more features. The labeled results from the different sample type and / or class maybe used to determine an initial set of features, which may be further reduced using the training data set.

[0104] The training method 1400 may train one or more machine learning models using the one or more features at step 1440. In one embodiment, the machine learning models may be trained using supervised learning. In another embodiment, other machine learning techniques may be employed, including unsupervised learning and semi-supervised. The machine learning models trained at 1440 may be selected based on different criteria depending on the problem to be solved and / or data available in the training data set. For example, machine learning classifiers can suffer from different degrees of bias. Accordingly, more than one machine learning model can be trained at 1440, and then optimized, improved, and crossvalidated at step 1450.

[0105] The training method 1400 may select one or more machine learning models to build a predictive model at 1460 (e.g., the at least one machine learning-based classifier 1300). The predictive model may be evaluated using the testing data set. The predictive model may analyze the testing data set and generate classification values and / or predicted values at step 1470. Classification and / or prediction values may be evaluated at step 1480 to determine whether such values have achieved a desired accuracy level.

[0106] Performance of the predictive model described herein may be evaluated in a number of ways based on a number of true positives, false positives, true negatives, and / or false negatives classifications of data in data sets of geological samples. For example, the false positives of the predictive model may refer to a number of times the predictive model incorrectly classified data as indicative of a particular attribute that in reality did not indicate the particular attribute. Conversely, the false negatives of the machine learning model(s) may refer to a number of times the predictive model classified one or more data of a data set of sample as not indicating a particular attribute when, in fact, the one or more data did indicate the particular attribute. True negatives and true positives may refer to a number of times the predictive model correctly classified one or more data sets as having sufficient indicating of a particular attribute or not indicating the particular attribute. Related to these measurements are the concepts of recall and precision. Generally, recall refers to a ratio of true positives to aAttorney Docket No. 36362.0259P1 sum of true positives and false negatives, which quantifies a sensitivity of the predictive model. Similarly, precision refers to a ratio of true positives to a sum of true positives and false positives. Further, the predictive model may be evaluated based on a level of mean error and a level of mean percentage error. Once a desired accuracy level of the predictive model is reached, the training phase ends and the predictive model may be output at step 1490.However, when the desired accuracy level is not reached a subsequent iteration of the method 1400 may be performed starting at step 1410 with variations such as, for example, considering a larger collection of high energy photon data sets.EXEMPLARY ASPECTS

[0107] In view of the described products, systems, and methods and variations thereof, herein below are described certain more particularly described aspects of the invention. These particularly recited aspects should not however be interpreted to have any limiting effect on any different claims containing different or more general teachings described herein, or that the “particular"’ aspects are somehow limited in some way other than the inherent meanings of the language literally used therein.

[0108] Aspect 1 : A system for analyzing material samples, the system comprising: a loading station that is configured to receive a plurality of containers holding the material samples; a plurality of scanning modules, wherein each scanning module of the plurality of scanning modules is configured to capture data associated with the material samples; a computing device configured to: receive the data associated with the material samples, wherein the received data corresponds to the data captured by the plurality of scanning modules; and coregister the received data associated with the material samples; and a conveyor that is configured to cany' the plurality of containers holding the material samples from the loading station to each of the plurality of scanning modules along a conveyance path.

[0109] Aspect 2: The system of aspect 1, wherein the plurality of containers are trays configured to receive core or rock samples therein.Attorney Docket No. 36362.0259P1

[0110] Aspect 3: The system of aspect 1 or aspect 2, further comprising a preparation station positioned between the loading station and at least one scanning module of the plurality of scanning modules along the conveyance path.

[0111] Aspect 4: The system of aspect 3, wherein the preparation station is positioned between the loading station and each scanning module of the plurality of scanning modules along the conveyance path.

[0112] Aspect 5: The system of aspect 4, wherein the preparation station comprises one or more of a cleaning module, a degreaser, a vacuum, a CO2 blaster, a device configured to arrange a sample within the container, a marker configured to draw an orientation line, or a module configured to apply an identification tag to a container.

[0113] Aspect 6: The system of any one of the preceding aspects, wherein the computing device is configured to coregister the data to within a resolution of 1 mm.

[0114] Aspect 7: The system of any one of the preceding aspects, wherein the computing device is configured to apply machine learning to coregister the data.

[0115] Aspect 8: The system of any one of the preceding aspects, wherein the system is configured to coregister data based on 3D topographical measurements of the sample.

[0116] Aspect 9: The system of any one of the preceding aspects, wherein the conveyance path is linear.

[0117] Aspect 10: The system of any one of the preceding aspects, wherein the loading station is configured to reorder the plurality of containers.

[0118] Aspect 11: The system of any one of the preceding aspects, wherein the loading station comprises a robotic arm.

[0119] Aspect 12: The system of aspect 11, wherein the robotic arm is a multi-axis robotic arm.

[0120] Aspect 13: The system of any one of the preceding aspects, wherein the loading station comprises a multi-axis gantry.Attorney Docket No. 36362.0259P1

[0121] Aspect 14: The system of any one of the preceding aspects, wherein the loading station comprises a scanner that is configured to read an identifier associated with a container of the plurality of containers.

[0122] Aspect 15: The system of aspect 13, wherein the computing device is configured to associate the identifier associated with the container with at least one attribute of the container.

[0123] Aspect 16: The system of aspect 14, wherein the at least one attribute of the container comprises a drilling site, a drilling depth, a drill site, a drill hole, a drill depth, or a container sequence number.

[0124] Aspect 17: The system of any one of aspects 14-16, wherein the computing device is configured to determine at least one of: a correct order of containers; an incorrect order of containers; an absence of a container; or an improperly loaded container.

[0125] Aspect 18: The system of any one of the preceding aspects, wherein the loading station comprises at least one imaging device.

[0126] Aspect 19: The system of aspect 18, wherein the at least one imaging device comprises one or more of: a camera or LiDAR.

[0127] Aspect 20: The system of aspect 19, wherein the at least one imaging device comprises a camera, wherein the camera is configured to capture color image data.

[0128] Aspect 21: The system of any one of the preceding aspects, wherein the plurality of scanning modules comprise at least one of: a camera, LiDAR, an XRF scanner, an ultraviolet scanner, LIBS, a magnetic susceptibility sensor, a gamma sensor, or a Raman sensor.

[0129] Aspect 22: The system of any one of the preceding aspects, wherein at least one scanning module of the plurality of scanning modules comprises a replaceable head.Attorney Docket No. 36362.0259P1

[0130] Aspect 23: The system of aspect 22, wherein the replaceable head comprises a dovetail or a v-block.

[0131] Aspect 24: The system of any one of the preceding aspects, wherein the plurality of scanning modules comprise at least two scanning modules, wherein each scanning module of the at least two scanning modules comprises duplicate sensors that are configured to capture like data, wherein the at least two scanning modules are configured to capture the like data in parallel.

[0132] Aspect 25: The system of aspect 24, wherein the conveyor is configured to cause a first container to bypass a first scanning module of the at least two scanning modules and position the first container at a second module of the at least two scanning modules.

[0133] Aspect 26: The system of aspect 24, wherein the conveyor is configured to selectively deliver each container to one of the at least two scanning modules.

[0134] Aspect 27: The system of aspect 26, wherein the conveyor comprises a plurality of branches, the plurality of branches comprising a first branch and a second branch, wherein a first branch of the plurality of branches is configured to transport a first container to a first scanning module of the at least two scanning modules, wherein the second branch of the plurality of branches is configured to transport a second container to a second scanning module of the at least two scanning modules.

[0135] Aspect 28: The system of any one of the preceding aspects, wherein the conveyor comprises one or more of: at least one belt conveyor; at least one power roller; a pin and pull conveyor; robotic manipulator; or a positioner plate.

[0136] Aspect 29: The system of any one of the preceding aspects, wherein each module of the plurality of scanning modules comprises a respective sensor configured to capture topographical data, wherein the computing device is configured to coregister the received data associated with the material samples based on the topographical data captured by the respective sensor of each scanning module.

[0137] Aspect 30: The system of aspect 29, wherein each of the respective sensors configured to capture topographical data comprises a LiDAR sensor.Attorney Docket No. 36362.0259P1

[0138] Aspect 31: The system of any one of the preceding aspects, wherein each module of the plurality of scanning modules comprises a respective sensor configured to capture image data, wherein the computing device is configured to coregister the received data associated with the material samples based on the image data captured by the respective sensor of each scanning module.

[0139] Aspect 32: The system of aspect 31, wherein each of the respective sensors configured to capture image data comprises a camera.

[0140] Aspect 33: The system of aspect 32, wherein the camera is an RGB camera.

[0141] Aspect 34: The system of any one of the preceding aspects, wherein at least one sensing module comprises a camera, wherein the camera is configured to capture image data, wherein the computing device is configured to apply machine learning to analyze the image data.

[0142] Although the foregoing invention has been described in some detail by way of illustration and example for purposes of clarity of understanding, certain changes and modifications may be practiced within the scope of the appended claims.

Claims

Attorney Docket No. 36362.0259P1What is claimed is:

1. A system for analyzing material samples, the system comprising: a loading station that is configured to receive a plurality of containers holding the material samples; a plurality of scanning modules, wherein each scanning module of the plurality of scanning modules is configured to capture data associated with the material samples; a computing device configured to: receive the data associated with the material samples, wherein the received data corresponds to the data captured by the plurality of scanning modules; and coregister the received data associated with the material samples; and a conveyor that is configured to carry the plurality of containers holding the material samples from the loading station to each of the plurality of scanning modules along a conveyance path.

2. The system of claim 1, wherein the plurality of containers are trays configured to receive core or rock samples therein.

3. The system of claim 1, further comprising a preparation station positioned between the loading station and at least one scanning module of the plurality of scanning modules along the conveyance path.

4. The system of claim 3. wherein the preparation station is positioned between the loading station and each scanning module of the plurality of scanning modules along the conveyance path.

5. The system of claim 4, wherein the preparation station comprises one or more of: a cleaning module, a degreaser, a vacuum, a CO2 blaster, a device configured to arrange a sample within the container, a marker configured to draw an orientation line, or a module configured to apply an identification tag to a container.

6. The system of claim 1, wherein the computing device is configured to coregister the data to within a resolution of 1 mm.

7. The system of claim 1. wherein the computing device is configured to apply machine learning to coregister the data.

8. The system of claim 1, wherein the system is configured to coregister data based on 3D topographical measurements of the sample.Attorney Docket No. 36362.0259P19. The system of claim 1, wherein the conveyance path is linear.

10. The system of claim 1, wherein the loading station is configured to reorder the plurality of containers.

11. The system of claim 1 , wherein the loading station comprises a robotic arm.

12. The system of claim 11, wherein the robotic arm is a multi-axis robotic arm.

13. The system of claim 1, wherein the loading station comprises a multi-axis gantry.

14. The system of claim 1, wherein the loading station comprises a scanner that is configured to read an identifier associated with a container of the plurality of containers.

15. The system of claim 13, wherein the computing device is configured to associate the identifier associated with the container with at least one attribute of the container.

16. The system of claim 14, wherein the at least one attribute of the container comprises a drilling site, a drilling depth, a drill site, a drill hole, a drill depth, or a container sequence number.

17. The system of claim 14, wherein the computing device is configured to determine at least one of: a correct order of containers; an incorrect order of containers; an absence of a container; or an improperly loaded container.

18. The system of claim 1, wherein the loading station comprises at least one imaging device.

19. The system of claim 18, wherein the at least one imaging device comprises one or more of: a camera or LiDAR.

20. The system of claim 19, wherein the at least one imaging device comprises a camera, wherein the camera is configured to capture color image data.

21. The system of claim 1, wherein the plurality of scanning modules comprise at least one of: a camera, LiDAR, an XRF scanner, an ultraviolet scanner, LIBS, a magnetic susceptibility sensor, a gamma sensor, or a Raman sensor.Attorney Docket No. 36362.0259P122. The system of claim 1, wherein at least one scanning module of the plurality of scanning modules comprises a replaceable head.

23. The system of claim 22, wherein the replaceable head comprises a dovetail or a v- block.

24. The system of claim 1, wherein the plurality of scanning modules comprise at least two scanning modules, wherein each scanning module of the at least two scanning modules comprises duplicate sensors that are configured to capture like data, wherein the at least two scanning modules are configured to capture the like data in parallel.

25. The system of claim 24, wherein the conveyor is configured to cause a first container to bypass a first scanning module of the at least two scanning modules and position the first container at a second module of the at least two scanning modules.

26. The system of claim 24, wherein the conveyor is configured to selectively deliver each container to one of the at least two scanning modules.

27. The system of claim 26, wherein the conveyor comprises a plurality of branches, the plurality of branches comprising a first branch and a second branch, wherein a first branch of the plurality of branches is configured to transport a first container to a first scanning module of the at least two scanning modules, wherein the second branch of the plurality7of branches is configured to transport a second container to a second scanning module of the at least tw o scanning modules.

28. The system of claim 1, wherein the conveyor comprises one or more of: at least one belt conveyor; at least one power roller; a pin and pull conveyor; robotic manipulator; or a positioner plate.

29. The system of claim 1, wherein each module of the lurality of scanning modules comprises a respective sensor configured to capture topographical data, wherein the computing device is configured to coregister the received data associated with the material samples based on the topographical data captured by the respective sensor of each scanning module.

30. The system of claim 29, wherein each of the respective sensors configured to capture topographical data comprises a LiDAR sensor.

31. The system of claim 1, wherein each module of the plurality7of scanning modules comprises a respective sensor configured to capture image data, yvherein the computingAttorney Docket No. 36362.0259P1 device is configured to coregister the received data associated with the material samples based on the image data captured by the respective sensor of each scanning module.

32. The system of claim 31, wherein each of the respective sensors configured to capture image data comprises a camera.

33. The system of claim 32, wherein the camera is an RGB camera.

34. The system of claim 1, wherein at least one sensing module comprises a camera, wherein the camera is configured to capture image data, wherein the computing device is configured to apply machine learning to analyze the image data.

Images