Method for displaying content distribution of metal elements in rock based on random forest

Abstract

The embodiment of the invention provides a method for displaying the content distribution of metal elements in rock based on a random forest, and can solve the technical problem that the extraction capability of geochemical elements is poor. The method comprises the following steps: confirming spectral data and metal element content of a sample, and preprocessing to obtain an effective wave band; re-sampling the effective wave band according to each sampling interval; establishing a first random forest model according to the resampling wave band and a one-leaving cross validation method, and confirming the optimal spectral width of the target element; based on the optimal spectral width, a second random forest model is established, and the element content value of the target element is obtained through inversion; performing interpolation processing on the element content values to obtain a prediction distribution diagram of the element content values; according to the element content actual measurement value of the target element, an actual measurement distribution diagram of the element content value is obtained through interpolation processing; and if the coincidence value between the predicted distribution diagram and the actually measured distribution diagram accords with a preset range, obtaining an abnormal region based on the predicted distribution diagram.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for displaying the distribution of metal element content in rocks based on random forest. Background Art

[0002] In order to better develop and protect underground and surface resources, it is necessary to quickly obtain geochemical information. For example, in order to detect hidden mineral deposits, it is necessary to detect areas with abnormal chemical elements on the surface.

[0003] At present, by combining elemental geochemistry with hyperspectral remote sensing technology, the rock reflectance spectrum can be used to quickly and easily measure rock properties and quickly obtain its geochemical information without destroying the sample. Combined with this technology, large-area mapping can also be achieved, providing important support for expanding the scale of mineralization belts outside developed mining areas and finding hidden mineral deposits.

[0004] However, although traditional geochemical methods can accurately calibrate element anomaly areas, they are time-consuming, labor-intensive, and costly, and their measurement data are often distributed in a point-like manner with limited coverage. Therefore, how to extract geochemical elements quickly over a large area has become an urgent problem to be solved. Summary of the invention

[0005] The embodiment of the present application provides a method for displaying the distribution of metal element content in rocks based on random forest, which can solve the technical problem of poor extraction ability of geochemical elements.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for displaying the distribution of metal element content in rocks based on random forests, and the method for displaying the distribution of metal element content in rocks based on random forests includes: confirming the spectral data and metal element content of the sample; preprocessing the spectral data and the metal element content to obtain an effective band; resampling the effective band according to each sampling interval to obtain a resampled band corresponding to each sampling interval; establishing a first random forest model according to the resampled band and a leave-one-out cross-validation method; each sampling interval corresponds to a first random forest model; confirming the optimal spectral width of the target element according to the first random forest model; establishing a second random forest model based on the optimal spectral width; inverting the element content value of the target element based on the second random forest model; interpolating the element content value to obtain a predicted distribution map of the element content value; obtaining a measured distribution map of the element content value through interpolation according to the measured value of the element content of the target element; if the match value between the predicted distribution map and the measured distribution map meets the preset range, an abnormal area is obtained based on the predicted distribution map.

[0008] Based on the above description of the random forest-based method for displaying the distribution of metal element content in rocks provided in the embodiment of the present application, it can be known that the random forest-based method for displaying the distribution of metal element content in rocks includes processing the rock samples after they are collected according to the samples actually collected in the field, and obtaining the spectral data of the rock with an ASD spectrometer, and obtaining the metal element content in the rock with an X-ray fluorescence spectrometer. With the development of imaging spectroscopy technology, the spectrum is combined with elemental geochemistry. Then, the measured data of the ASD spectrometer are resampled at different intervals, and a random forest quantitative inversion model is established based on the spectral data of different sampling intervals. The modeling process adopts leave-one-out cross validation. Finally, the specific sampling interval data that makes the random forest accuracy the highest is selected for modeling, and the inversion value of the element content of the sampling point is obtained by inversion. The measured value and the inversion value of the element content of the sampling point are interpolated respectively using the inverse distance weight method to obtain the content distribution map of the inversion value and the measured value. Solve the problem of slow point-to-point sample collection and acquisition of element content. In this way, the abnormal distribution of metal element content in rocks can be quickly displayed, solving the problems of time-consuming, labor-intensive and sample-destructive methods in existing methods, and quickly acquiring the distribution of elements over a large area.

[0009] In a feasible implementation of the first aspect, the sample includes samples of multiple sampling points on multiple sampling lines; wherein the multiple sampling lines are arranged in parallel and evenly spaced, and the multiple sampling points on any sampling line are arranged evenly spaced.

[0010] In a feasible implementation of the first aspect, when executing the step of confirming the spectral data and metal element content of the sample, the method for displaying the distribution of metal element content in rocks based on random forest also includes: obtaining multiple first bands in a preset wavelength range according to a preset spectral resolution, a preset spectral sampling interval and a preset spectral acquisition time.

[0011] In a feasible implementation of the first aspect, when executing the step of confirming the spectral data and metal element content of the sample, the method for displaying the distribution of metal element content in rocks based on random forest also includes: preprocessing each first band to obtain a valid band; wherein the preprocessing includes raw data correction, spectral reflectance averaging and elimination of inversion results.

[0012] In a possible implementation manner of the first aspect, the metal element content includes copper element content.

[0013] In a feasible implementation of the first aspect, each sampling interval includes 5 nm, 10 nm, and 15 nm.

[0014] In a feasible implementation of the first aspect, the model inversion R 2 It is 0.5223.

[0015] In a feasible implementation of the first aspect, when executing the step of establishing a first random forest model according to the resampling bands and the leave-one-out cross-validation method, the method for displaying the distribution of metal element content in rocks based on random forest also includes: using one of the multiple resampling bands as a training sample for the first random forest model, and using other samples except the training samples as verification samples to train the first random forest model.

[0016] In a second aspect, an embodiment of the present application provides a system for displaying the distribution of metal element content in rocks based on random forests, and the system for displaying the distribution of metal element content in rocks based on random forests comprises: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided in the first aspect.

[0017] The random forest-based rock metal element content distribution display system executes the method provided by the first aspect, collects rock samples according to the samples actually collected in the field, processes them after they are collected, and uses an ASD spectrometer to obtain the spectral data of the rock, and an X-ray fluorescence spectrometer to obtain the metal element content in the rock. With the development of imaging spectroscopy technology, the spectrum is combined with elemental geochemistry. Then, the measured data of the ASD spectrometer are resampled at different intervals, and a random forest quantitative inversion model is established based on the spectral data of different sampling intervals. The modeling process adopts leave-one-out cross validation. Finally, the specific sampling interval data that makes the random forest accuracy the highest is selected for modeling, and the inversion value of the element content of the sampling point is obtained by inversion. The measured value and the inversion value of the element content of the sampling point are interpolated respectively by the inverse distance weight method, and the content distribution map of the inversion value and the measured value is obtained. The problem of point-to-point sample collection and slow acquisition of element content is solved. In this way, the abnormal distribution of metal element content in rocks is quickly displayed, the problems of time-consuming, labor-consuming and sample-destructive methods of the existing methods are solved, and the large-area distribution of elements is quickly realized.

[0018] In a third aspect, an embodiment of the present application provides a computer-readable medium having computer program instructions stored thereon, and the computer program instructions can be executed by a processor to implement the method provided in the first aspect.

[0019] The computer program instructions in the computer-readable medium implement the method provided by the first aspect, and according to the samples actually collected in the field, the rock samples are collected and processed, and the spectral data of the rock is obtained by the ASD spectrometer, and the metal element content in the rock is obtained by the X-ray fluorescence spectrometer. With the development of imaging spectroscopy technology, the spectrum is combined with elemental geochemistry. Then the measured data of the ASD spectrometer are resampled at different intervals, and a random forest quantitative inversion model is established based on the spectral data of different sampling intervals. The modeling process adopts leave-one-out cross validation. Finally, the specific sampling interval data that makes the random forest accuracy the highest is selected for modeling, and the inversion value of the element content of the sampling point is obtained by inversion. The measured value and the inversion value of the element content of the sampling point are interpolated respectively by the inverse distance weight method, and the content distribution map of the inversion value and the measured value is obtained. The problem of point-to-point sample collection and slow acquisition of element content is solved. In this way, the abnormal distribution of metal element content in the rock is quickly displayed, the problem of time-consuming, labor-consuming and sample-destroying existing methods is solved, and the large-area distribution of elements is quickly realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the structure of a random forest-based metal element content distribution display system in rocks provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a flow chart of a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of an implementation of a sample spectrum in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of an implementation of a spectral response function in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of an implementation method of an inversion map in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of observed values ​​and partial fitting predicted values ​​in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of an implementation method of predicted value distribution in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of an implementation method of the distribution of measured values ​​in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application;

[0028] Fig. 9 A schematic diagram of an implementation method of sampling lines in a method for displaying the distribution of metal element content in rocks based on random forests provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention. In the description of the embodiments of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0030] In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference. At the same time, in the embodiments of the present invention, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0031] The principles and features of the present application are described below. The examples given are only used to explain the present application and are not used to limit the scope of the present application.

[0032] The embodiment of the present application provides a method for displaying the distribution of metal element content in rocks based on random forests, which is suitable for various scenarios of detecting abnormal areas of chemical elements on the surface. According to the samples actually collected in the field, the rock samples are collected and processed, and the spectral data of the rocks are obtained by using an ASD spectrometer, and the metal element content in the rocks is obtained by using an X-ray fluorescence spectrometer. With the development of imaging spectroscopy technology, the spectrum is combined with elemental geochemistry. Then, the measured data of the ASD spectrometer are resampled at different intervals, and a random forest quantitative inversion model is established based on the spectral data of different sampling intervals. The modeling process adopts leave-one-out cross validation. Finally, the specific sampling interval data that makes the random forest accuracy the highest is selected for modeling, and the inversion value of the element content of the sampling point is obtained by inversion. The measured value and the inversion value of the element content of the sampling point are interpolated respectively by the inverse distance weight method, and a content distribution map of the inversion value and the measured value is obtained. The problem of slow point-to-point sample collection and element content acquisition is solved. In this way, the abnormal distribution of metal element content in rocks is quickly displayed, the problems of time-consuming, labor-consuming and sample-destroying existing methods are solved, and the large-area distribution of elements is quickly realized.

[0033] The embodiment of the present application provides a system for displaying the distribution of metal element content in rocks based on random forest, which can execute the method for displaying the distribution of metal element content in rocks based on random forest provided by the embodiment of the present application. Figure 1 A schematic diagram of the structure of a random forest-based metal element content distribution display system in rocks provided in an embodiment of the present application.

[0034] like Figure 1 As shown, the random forest-based metal element content distribution display system 001 in rocks includes at least one processor 011 and a memory 012 communicatively connected to the at least one processor; wherein the memory 012 stores instructions executable by the at least one processor 011, and the instructions are executed by the at least one processor 011 so that the at least one processor 011 can execute the random forest-based metal element content distribution display method in rocks provided in an embodiment of the present application.

[0035] Figure 2 The present invention provides a flow chart of a method for displaying the distribution of metal element content in rocks based on random forests. Figure 2 As shown, in some embodiments, the method for displaying the distribution of metal element content in rocks based on random forests includes the following steps:

[0036] S1, confirm the spectral data and metal element content of the sample.

[0037] In some embodiments, the sample includes samples at multiple sampling points on multiple sampling lines, wherein the multiple sampling lines are arranged in parallel and evenly spaced, and the multiple sampling points on any sampling line are arranged evenly spaced.

[0038] In some embodiments, the metal element content includes copper element content.

[0039] In some embodiments, when executing the step of confirming the spectral data and metal element content of the sample, the method for displaying the distribution of metal element content in rocks based on random forests further includes:

[0040] S111, obtaining a plurality of first bands in a preset wavelength range according to a preset spectral resolution, a preset spectral sampling interval, and a preset spectral acquisition time.

[0041] For example, in situ rocks with less weathering and erosion were collected near a Yudai porphyry copper deposit as experimental samples. Fig. 9 As shown, 13 sampling lines are set. Each sampling line is about 5 km long. The spacing between sampling lines is about 500 m. The distance between sampling points is about 200 m. 3-5 rock fragments with a diameter of less than 10 cm and a normal degree of weathering are collected at each sampling point, and a total of 338 rock samples are obtained. The collected samples are ground through a 200-mesh sieve to remove contaminated samples and samples with small quantities, and finally 258 valid samples are obtained. After the samples are sent for inspection and analysis, they are directly used for outdoor spectral measurement. The sample state is consistent, which is conducive to comparative analysis.

[0042] The spectral test is conducted outdoors using a portable field spectrometer. In standard mode, the preset spectral resolution is 3nm / 10nm, the preset spectral sampling interval is 1nm, and the preset spectral acquisition time is 0.2 seconds. When the preset wavelength range is 350-2500nm, there are 2151 bands in total, namely, the first band has 2151 bands in total. Figure 3 The spectral data shown is related to the metal element content of the sample, for example, copper (Cu) element.

[0043] S2, preprocess the spectral data and metal element content to obtain the effective band.

[0044] In some embodiments, when executing the step of confirming the spectral data and metal element content of the sample, the method for displaying the distribution of metal element content in rocks based on random forests further includes:

[0045] S211, preprocess each first band to obtain a valid band.

[0046] Preprocessing includes raw data correction, spectral reflectance averaging and deleting water vapor absorption bands. Raw data correction refers to automatically correcting the measured spectral reflectance curve through the ASD spectrometer's built-in software ViewSpecPro. The main steps include: gain calibration of each spectral data channel, wavelength correction and dark current removal in the raw data radiation intensity.

[0047] Spectral reflectance averaging refers to averaging the five spectral reflectances of each sample point measured by the spectrometer using the built-in software ViewSpecPro. The average value is the measured spectrum of the sample. By evaluating the instability of the measurement by measuring the same target multiple times, the measurement results are more representative and reliable, and the signal-to-noise ratio is also enhanced.

[0048] Since water vapor has a significant absorption effect on the spectrum in the bands of 350-399, 1301-1399, 1790-1999 and 2401-2500, causing anomalies, these bands were removed to eliminate the influence of water vapor absorption on the inversion of element content.

[0049] For example, when the preset wavelength range is selected to be 350-2500 nm, there are 2151 bands in total, namely, there are 2151 first bands in total. After preprocessing, there are 1692 valid bands left.

[0050] S3, resampling the effective bands according to each sampling interval to obtain a resampled band corresponding to each sampling interval.

[0051] Resampling converts high-resolution reflectivity into low-resolution reflectivity. For example, the original band width of visible near-infrared is 3nm, the original band width of short-wave infrared is 10nm, and the output of Analytic Spectra Devices (ASD) is all unified to 1nm.

[0052] like Figure 4 As shown, in one implementation, a spreadsheet making software (Excel) and a remote sensing image processing tool (ENVI5.3) are used to resample the original data using the spectral response function.

[0053] In some embodiments, each sampling interval includes equal-interval sampling and non-equal-interval sampling. Exemplarily, each sampling interval includes spectral intervals of 5 nm, 10 nm, 15 nm ... 100 nm, and 150 nm, 200 nm. In the case of 1692 remaining valid bands, the number of bands after resampling is 169, 113, 85, 68 ... 17, and 12, 9 respectively.

[0054] S4, based on the resampling bands and leave-one-out cross-validation method, the first random forest model was established.

[0055] Each sampling interval corresponds to a first random forest model.

[0056] In some embodiments, when executing step S4, the method for displaying the distribution of metal element content in rocks based on random forests further includes:

[0057] S411, using one of the multiple resampled bands as a training sample of the first random forest model, and using other samples except the training sample as validation samples to train the first random forest model.

[0058] Leave-one-out cross-validation means leaving one of the samples as a validation sample and the rest as training samples, and repeating step S411 until all samples have been used as validation samples.

[0059] In this way, the leave-one-out cross-validation method is adopted in the cross-validation method to make full use of the sampled data to obtain a reliable and stable model.

[0060] S5, confirming the optimal spectral width of the target element according to the first random forest model.

[0061] In this way, each sampling interval corresponds to a first random forest model. Among the multiple first random forest models, the first random forest model corresponding to the optimal spectrum width required for the element content of the target element is found, and then the optimal spectrum width is confirmed.

[0062] like Figure 5 As shown, for example, with the change of spectral width, when the spectral resolution is 35nm, the random forest model of Cu element achieves the highest accuracy. It can be understood that this shows that in the future, when designing hyperspectral sensors for rock geochemistry, when the spectral resolution is within the range of 80nm, it is not necessary to have too high a resolution, but when designing fine instruments, the spectral resolution can be designed at 35nm for reference, and the inversion accuracy is higher.

[0063] S6, based on the optimal spectrum width, establish the second random forest model.

[0064] S7, based on the second random forest model, the element content value of the target element is inverted.

[0065] like Figure 6 As shown, in some embodiments, the model inversion R 2 It is 0.5223.

[0066] S8, interpolating the element content values ​​in ArcGIS software to obtain a predicted distribution map of the element content values.

[0067] like Figure 7 As shown, illustratively, the Cu element content values ​​inverted by the model established when the band width is 35 nm are subjected to inverse distance weighted interpolation (IDW) to generate a distribution map of predicted Cu element content values.

[0068] The IDW method works as follows: for each grid node, a weight is assigned to a specific data point, proportional to the specified power node assigned the inverse of the distance. When calculating a grid node, the sum of all weights is 1.0, and the weights assigned to different observation points are fractional. When an observation point coincides with a grid node, this point is assigned a weight value of 1.0, while the remaining observation points that do not coincide with the grid node are assigned weight values ​​close to 0.0. In other words, the value assigned to the node that coincides with the grid node is consistent with the observation point and is an accurate interpolation.

[0069] S9, according to the measured value of the element content of the target element, IDW interpolation is performed to the measured distribution map of the element content value through ArcGIS software.

[0070] like Figure 8 As shown, for example, the measured Cu element content value is interpolated to obtain a measured distribution diagram.

[0071] S10, if the matching value between the predicted distribution map and the measured distribution map meets the preset range, an abnormal area is obtained based on the predicted distribution map.

[0072] like Figure 7 and Figure 8 As shown, exemplarily, the model inversion R2 is 0.5223. From the interpolation diagram comparison results, it can be seen that the inversion value abnormal area and the measured value abnormal area match the preset range, which is considered to be basically consistent, and the Cu element content abnormal area can be delineated. Exemplarily, the spatial position of the high-value area of ​​the inversion value and the high-value area of ​​the measured value meet the threshold requirement, and the spatial position of the low-value area also meets the threshold requirement. It can be understood that the threshold requirement can be preset according to the needs, and the specific value of the threshold requirement is not limited in this application.

[0073] The present invention effectively utilizes hyperspectral data, with a larger and richer data volume, and can extract the content of metal elements. It can well solve the problems of traditional methods that require manual determination of element content and abnormal characteristic areas. The processing level is high, which can greatly reduce the workload of personnel, quickly and roughly delineate element abnormal areas over a large area, and improve efficiency.

[0074] Based on the same application concept, a random forest-based display system for the distribution of metal element content in rocks is also provided in an embodiment of the present application. The method corresponding to the random forest-based display system for the distribution of metal element content in rocks can be the random forest-based display method for the distribution of metal element content in rocks in the aforementioned embodiment, and its principle of solving the problem is similar to that of the method. The random forest-based display system for the distribution of metal element content in rocks provided in an embodiment of the present application includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0075] Another embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of the present application described above.

[0076] Specifically, the present embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0077] Computer readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0078] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0079] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0080] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0081] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0082] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or page components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0085] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0087] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for displaying the distribution of metal element content in rocks based on random forest, characterized in that: include: Confirm the spectral data and metal element content of the sample; Preprocessing the spectral data and the metal element content to obtain an effective band; Resampling the effective band according to each sampling interval to obtain a resampled band corresponding to each sampling interval; According to the resampling bands and the leave-one-out cross-validation method, a first random forest model is established; each sampling interval corresponds to one first random forest model; According to the first random forest model, determining the optimal spectral width of the target element; Based on the optimal spectral width, establishing a second random forest model; Based on the second random forest model, invert and obtain the element content value of the target element; Performing interpolation processing on the element content values ​​to obtain a predicted distribution diagram of the element content values; According to the measured value of the element content of the target element, a measured distribution diagram of the element content value is obtained through interpolation processing; If the matching value between the predicted distribution map and the measured distribution map meets the preset range, an abnormal area is obtained based on the predicted distribution map.

2. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 1, characterized in that: The sample includes samples of multiple sampling points on multiple sampling lines; wherein the multiple sampling lines are arranged in parallel and evenly spaced, and the multiple sampling points on any one of the sampling lines are arranged evenly spaced.

3. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 1 or 2, characterized in that: When executing the step of confirming the spectral data and metal element content of the sample, the method for displaying the distribution of metal element content in rocks based on random forests also includes: According to the preset spectral resolution, the preset spectral sampling interval and the preset spectral acquisition time, a plurality of first bands in the preset wavelength range are obtained.

4. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 3, characterized in that: When executing the step of confirming the spectral data and metal element content of the sample, the method for displaying the distribution of metal element content in rocks based on random forests also includes: Preprocess each of the first wavebands to obtain a valid waveband; The preprocessing includes raw data correction, spectral reflectance averaging and elimination of inversion results.

5. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 1 or 2, characterized in that: The metal element content includes copper element content.

6. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 1 or 2, characterized in that: The sampling intervals include 5nm, 10nm, and 15nm.

7. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 1 or 2, characterized in that: Model Inversion R 2 It is 0.5223.

8. The method for displaying the distribution of metal element content in rocks based on random forest according to claim 1 or 2, characterized in that: When executing the step of establishing the first random forest model according to the resampling bands and the leave-one-out cross-validation method, the method for displaying the distribution of metal element content in rocks based on random forests also includes: One of the multiple resampled bands is used as a training sample of a first random forest model, and other samples except the training sample are used as validation samples to train the first random forest model.

9. A random forest-based display system for the distribution of metal element content in rocks, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 8.

10. A computer readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method according to any one of claims 1 to 8.

Images