Weathering crust rare earth resource assessment methods, systems, equipment, media and program products

Abstract

The present invention discloses a method, system, equipment, medium and program product for evaluating weathering crust rare earth resources, including: firstly, using a seismic station within the scope of the mining area to be evaluated to collect first seismic signal data; preprocessing the first seismic signal data to obtain second seismic signal data; segmenting the second seismic signal data to obtain third seismic signal data; marking the transient interference occurrence point of the seismic signal based on a multi-window long-short time window ratio algorithm, and obtaining fourth seismic signal data according to the marking result; obtaining the peak frequency of the spectrum ratio curve according to the three-component vibration spectrum density of the fourth seismic signal data, and calculating the thickness of the weathering crust in the corresponding area; constructing a rare earth ore prediction model based on geological exploration data; inputting the thickness of the weathering crust into the prediction model to obtain the evaluation result of the weathering crust rare earth resources in the mining area to be evaluated. The present invention effectively improves the evaluation efficiency and accuracy of the evaluation of weathering crust rare earth resources.

Description

Technical Field

[0001] The present invention relates to the field of geological exploration, and in particular to a method, system, equipment, medium and program product for evaluating rare earth resources in a weathering crust. Background Art

[0002] The existing assessment of weathering crust-type rare earth resources is constrained by conditions such as the degree of geological exploration, drilling density, topography and regional geological structure, and has great limitations. While existing technologies consume a lot of time and resources, it is difficult to achieve rapid assessment of large areas and cannot meet the needs of efficient and accurate exploration.

[0003] Therefore, it is urgent to invent a new method for assessing the rare earth resources in weathering crust to solve the problems of low efficiency and poor accuracy of traditional methods for assessing the rare earth resources in weathering crust. Summary of the invention

[0004] In view of this, the embodiments of the present invention provide a method, system, device, medium and program product for assessing weathering crust rare earth resources, which at least partially solve the problems existing in the prior art.

[0005] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0006] In order to achieve the above purpose, the embodiment of the present invention provides the following technical solutions:

[0007] According to a first aspect of an embodiment of the present invention, a method for assessing rare earth resources in a weathering crust is provided, the method comprising:

[0008] Using seismic stations within the mining area to be evaluated, first seismic signal data of the area corresponding to each seismic station is collected;

[0009] Performing data preprocessing on the first seismic signal data to obtain second seismic signal data;

[0010] According to a preset time interval, performing data segmentation processing on the second seismic signal data to obtain third seismic signal data;

[0011] Based on a multi-window long-short time window ratio algorithm, marking the transient interference occurrence point in the third seismic signal data, and obtaining fourth seismic signal data according to the marking result;

[0012] Obtaining a peak frequency of a spectrum ratio curve corresponding to the fourth seismic signal data according to a horizontal vibration spectrum density and a vertical vibration spectrum density of the fourth seismic signal data in a frequency domain;

[0013] Using the peak frequency of the spectral ratio curve, the thickness of the weathering crust in the area corresponding to the seismic station is obtained;

[0014] Based on the geological exploration data, a first weathering crust rare earth mineral content prediction model to be trained is constructed, the first weathering crust rare earth mineral content prediction model is trained using a model training set to obtain a trained second weathering crust rare earth mineral content prediction model, the second weathering crust rare earth mineral content prediction model is evaluated using a model test set, and a third weathering crust rare earth mineral content prediction model that has passed the model evaluation is obtained according to the model evaluation result;

[0015] The thickness of the weathering crust in the area corresponding to each seismic station is input into the third weathering crust rare earth mineral content prediction model to obtain the weathering crust rare earth resource assessment result within the mining area to be assessed.

[0016] Further, performing data preprocessing on the first seismic signal data to obtain second seismic signal data includes:

[0017] Performing format conversion processing on the first seismic signal data to obtain first preprocessed intermediate data;

[0018] Performing a mean removal process on the first preprocessed intermediate data to obtain second preprocessed intermediate data;

[0019] performing instrument response removal processing on the second preprocessed intermediate data to obtain third preprocessed intermediate data;

[0020] Performing detrending processing on the third preprocessed intermediate data to obtain fourth preprocessed intermediate data;

[0021] An adaptive filter is constructed based on wavelet transform, and the adaptive filter is used to perform adaptive filtering processing on the fourth preprocessed intermediate data to obtain the second seismic signal data after preprocessing.

[0022] Further, based on the multi-window long-short time window ratio algorithm, the transient interference occurrence point in the third seismic signal data is marked, and the fourth seismic signal data is obtained according to the marking result, including:

[0023] Generate a short-time window of a first length according to the period of the seismic signal;

[0024] Based on the first length, generating a long time window of a second length;

[0025] Using the short time window and the long time window to overlap the third seismic signal data;

[0026] For each short-time window, the short-time window is used as the short-time window to be detected, and the long-time window corresponding to the short-time window to be detected is used as the long-time window to be detected;

[0027] According to the signal change within the coverage range of the short time window to be detected and the signal change within the coverage range of the long time window to be detected, a ratio of the long and short time window signal change is calculated;

[0028] Determine whether the ratio of the long-time window signal change to the short-time window signal change is greater than a preset ratio threshold;

[0029] If the ratio of the long-time window signal change to the short-time window signal change is greater than a preset ratio threshold, the position of the short-time window to be detected is marked as a transient interference occurrence point;

[0030] If the ratio of the long-time window signal change to the short-time window signal change is less than or equal to a preset ratio threshold, the position of the short-time window to be detected is not marked as a transient interference occurrence point;

[0031] Performing marking result evaluation on the transient interference occurrence point to obtain a marking evaluation result;

[0032] Optimizing the time window length, time window position and preset ratio threshold value by using the marking evaluation result in real time;

[0033] The first data cleaning process is performed on the third seismic signal according to the transient interference occurrence point, and the signal at the position corresponding to the transient interference occurrence point is cleared to obtain the cleaned fourth seismic signal data.

[0034] Further, according to the horizontal vibration spectrum density and the vertical vibration spectrum density of the fourth seismic signal data in the frequency domain, the peak frequency of the spectrum ratio curve corresponding to the fourth seismic signal data is obtained, including:

[0035] According to the period of the seismic signal and the research requirements of the low-frequency seismic signal, a spectrum analysis time window of the third length is generated;

[0036] Using the spectrum analysis time window to slide select the fourth seismic signal data, and select a first time window signal;

[0037] Performing smoothing on the first time window signal to obtain a second time window signal;

[0038] Based on a preset window function, performing fast Fourier transform processing on the second time window signal to obtain frequency domain information corresponding to the second time window signal;

[0039] Using the frequency domain information corresponding to the second time window signal, calculate the horizontal vibration spectrum density and the vertical vibration spectrum density of the second time window signal in the frequency domain, wherein the horizontal vibration spectrum density includes the north-south component spectrum density and the east-west component spectrum density;

[0040] The horizontal vibration spectrum density and the vertical vibration spectrum density are used to obtain the three-component vibration spectrum density ratio corresponding to the second time window signal. The calculation formula of the three-component vibration spectrum density ratio is:

[0041]

[0042] Where, f(c) is the three-component vibration spectrum density ratio, A EW (f) is the power spectrum density of the east-west component, A NS (f) is the spectrum density of the north-south component, A UD (f) is the vertical component spectral density;

[0043] A spectrum ratio curve is obtained by plotting the three-component vibration spectrum density ratio;

[0044] The spectrum ratio curve is used to obtain the peak frequency of the spectrum ratio curve.

[0045] Furthermore, the peak frequency of the spectral ratio curve is used to obtain the thickness of the weathering crust in the area corresponding to the seismic station, including:

[0046] Determine whether there is an average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station;

[0047] If there is an average shear wave velocity of the weathering crust stratum in the area corresponding to the seismic station, the first weathering crust thickness in the area corresponding to the seismic station is calculated using the average shear wave velocity of the weathering crust stratum and the corresponding peak frequency of the spectrum ratio curve. The calculation formula of the first weathering crust thickness is:

[0048]

[0049] Where H is the thickness of the first weathering crust, V s is the average shear wave velocity of the weathering crust in the area corresponding to the seismic station, f c is the peak frequency of the spectrum ratio curve;

[0050] If there is no average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station, a part of the area corresponding to the seismic station is selected as the sample area;

[0051] According to the geological exploration data of the sample area, a sample value of the weathering crust thickness corresponding to the sample area is obtained;

[0052] Using the weathering crust thickness sample value corresponding to the sample area and the peak frequency of the spectrum ratio curve corresponding to the sample area to perform fitting processing, the fitting parameters of the area corresponding to the seismic station are obtained;

[0053] The thickness of the second weathering crust in the area corresponding to the seismic station is calculated by using the fitting parameters of the area corresponding to the seismic station and the peak frequency of the spectral ratio curve corresponding to the area corresponding to the seismic station. The calculation formula of the thickness of the second weathering crust is:

[0054] lgH=lgk+ilgf c

[0055] Where H' is the thickness of the second weathering crust, k and i are fitting parameters, and f c is the peak frequency of the spectrum ratio curve

[0056] Further, based on the geological exploration data, a first weathering crust rare earth ore content prediction model to be trained is constructed, and the first weathering crust rare earth ore content prediction model is trained using a model training set to obtain a trained second weathering crust rare earth ore content prediction model, and the second weathering crust rare earth ore content prediction model is evaluated using a model test set, and a third weathering crust rare earth ore content prediction model with qualified model evaluation is obtained according to the model evaluation result, including:

[0057] Acquire first geological exploration data from a public database, wherein the first geological exploration data includes rare earth content data, weathering crust thickness data, geological structure data, terrain data, and remote sensing image data;

[0058] Performing data format standardization processing on the first geological exploration data to obtain second geological exploration data;

[0059] Performing abnormal data inspection processing on the second geological exploration data, and performing second data cleaning processing according to the inspection processing result to obtain third geological exploration data after data cleaning;

[0060] Using the third geological exploration data to construct a feature list, the feature list includes geological features, topographic features, remote sensing image features, weathering crust thickness features, and rare earth content features;

[0061] Normalizing the features in the feature list to obtain normalized features;

[0062] Constructing a three-dimensional feature matrix using the normalized features, the longitude information corresponding to the normalized features, and the latitude information corresponding to the normalized features;

[0063] Constructing a first weathering crust rare earth mineral content prediction model to be trained based on the three-dimensional feature matrix;

[0064] Generate a model data set according to the weathering crust thickness characteristics and the rare earth content characteristics, and divide the model data set into a model training set and a model test set;

[0065] Using the model training set to perform model training on the first weathering crust rare earth mineral content prediction model to obtain a trained second weathering crust rare earth mineral content prediction model;

[0066] Using the model test set to perform model evaluation on the second weathering crust rare earth mineral content prediction model to obtain a model evaluation result;

[0067] Determine whether the model evaluation result meets the preset model evaluation standard;

[0068] If the model evaluation result meets the preset model evaluation standard, the second weathering crust rare earth mineral content prediction model is used as the third weathering crust rare earth mineral content prediction model;

[0069] If the model evaluation result does not meet the preset model evaluation standard, the second weathering crust rare earth mineral content prediction model is optimized and re-evaluated.

[0070] According to a second aspect of an embodiment of the present invention, a weathering crust rare earth resource assessment system is provided, the system comprising:

[0071] A seismic signal acquisition module, used to acquire first seismic signal data of the area corresponding to each seismic station by using seismic stations within the mining area to be evaluated;

[0072] A data preprocessing module, used for performing data preprocessing on the first seismic signal data to obtain second seismic signal data;

[0073] A data segmentation module, used for performing data segmentation processing on the second seismic signal data according to a preset time interval to obtain third seismic signal data;

[0074] A transient interference marking module, used for marking the transient interference occurrence points in the third seismic signal data based on a multi-window long-short time window ratio algorithm, and obtaining fourth seismic signal data according to the marking result;

[0075] A seismic signal frequency domain analysis module, used to obtain a peak frequency of a spectrum ratio curve corresponding to the fourth seismic signal data according to a horizontal vibration spectrum density and a vertical vibration spectrum density of the fourth seismic signal data in the frequency domain;

[0076] A weathering crust thickness analysis module, used to obtain the weathering crust thickness of the area corresponding to the seismic station using the peak frequency of the spectral ratio curve;

[0077] A rare earth content prediction model construction module is used to construct a first weathering crust rare earth ore content prediction model to be trained based on geological exploration data, use a model training set to perform model training on the first weathering crust rare earth ore content prediction model to obtain a trained second weathering crust rare earth ore content prediction model, use a model test set to perform model evaluation on the second weathering crust rare earth ore content prediction model, and obtain a third weathering crust rare earth ore content prediction model that has passed the model evaluation according to the model evaluation result;

[0078] The rare earth resource assessment module is used to input the weathering crust thickness of the area corresponding to each seismic station into the third weathering crust rare earth ore content prediction model to obtain the weathering crust rare earth resource assessment result within the mining area to be assessed.

[0079] According to a third aspect of an embodiment of the present invention, there is provided a weathering crust rare earth resource assessment device, the device comprising: a processor and a memory;

[0080] The memory is used to store one or more program instructions;

[0081] The processor is used to run one or more program instructions to execute the steps of a weathering crust rare earth resource assessment method as described in any one of the above items.

[0082] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for assessing rare earth resources in a weathering crust as described in any one of the above items are implemented.

[0083] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which, when executed by a computer, enable the computer to implement the steps of a weathering crust rare earth resource assessment method as described in any of the above items.

[0084] The embodiments of the present invention have the following advantages:

[0085] The weathering crust rare earth resource assessment method, system, equipment, medium and program product disclosed in the present invention realizes rapid identification of the interface between the weathering crust containing rare earth ore and bedrock by non-invasive means through the three-component spectral ratio method based on seismic stations and the weathering crust rare earth resource assessment model based on machine learning, thereby quickly and accurately assessing the distribution state of underground rare earth weathering crust ore bodies, and then realizing rapid assessment of the weathering crust rare earth ore resources. The weathering crust rare earth resource assessment method provided by the present invention is simple to operate and fast in data processing. It is suitable for various geological conditions, complex terrains and complex structural areas, and provides an efficient and accurate assessment method for rare earth mineral exploration. It has great application potential in the field of geological exploration. At the same time, it solves the problem of large limitations of traditional assessment methods and provides a new technical approach for the assessment of weathering crust rare earth resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0087] Figure 1 A schematic diagram of the logical structure of a weathering crust rare earth resource assessment system provided by an embodiment of the present invention;

[0088] Figure 2 A schematic flow chart of a method for assessing rare earth resources in a weathering crust provided by an embodiment of the present invention;

[0089] Figure 3 A schematic diagram of a process for preprocessing seismic signal data provided by an embodiment of the present invention;

[0090] Figure 4 A schematic diagram of a process for marking transient interference on seismic signal data provided by an embodiment of the present invention;

[0091] Figure 5 A schematic diagram of a process for performing frequency domain analysis on seismic signal data provided by an embodiment of the present invention;

[0092] Figure 6 A schematic diagram of a process for analyzing the thickness of a weathering crust provided by an embodiment of the present invention;

[0093] Figure 7 A schematic diagram of a process for constructing a weathering crust rare earth ore content prediction model provided by an embodiment of the present invention;

[0094] Figure 8 A schematic flowchart of the process of weathering crust rare earth resource assessment provided by an embodiment of the present invention;

[0095] Fig. 9 A schematic diagram of the effect of weathering crust depth calculation provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0096] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0097] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0098] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement a device and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0099] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0100] Figure 1 The figure shows a schematic diagram of the logical structure of a weathering crust rare earth resource evaluation system according to an embodiment of the present invention.

[0101] Specifically, Figure 1As shown, the seismic signal acquisition module 1 is used to use the seismic stations within the scope of the mining area to be evaluated to collect the first seismic signal data of the corresponding area of ​​each seismic station; the data preprocessing module 2 is used to perform data preprocessing on the first seismic signal data to obtain the second seismic signal data; the data segmentation module 3 is used to perform data segmentation processing on the second seismic signal data according to a preset time interval to obtain the third seismic signal data; the transient interference marking module 4 is used to mark the transient interference occurrence points in the third seismic signal data based on a multi-window long-short time window ratio algorithm, and obtain the fourth seismic signal data according to the marking result; the seismic signal frequency domain analysis module 5 is used to obtain the peak value of the spectrum ratio curve corresponding to the fourth seismic signal data according to the horizontal vibration spectrum density and the vertical vibration spectrum density of the fourth seismic signal data in the frequency domain. frequency; the weathering crust thickness analysis module 6 is used to use the peak frequency of the spectral ratio curve to obtain the weathering crust thickness of the area corresponding to the seismic station; the rare earth content prediction model construction module 7 is used to construct a first weathering crust rare earth ore content prediction model to be trained based on geological exploration data, and use the model training set to train the first weathering crust rare earth ore content prediction model to obtain a trained second weathering crust rare earth ore content prediction model, and use the model test set to evaluate the second weathering crust rare earth ore content prediction model, and obtain a third weathering crust rare earth ore content prediction model that is qualified according to the model evaluation result; the rare earth resource assessment module 8 is used to input the weathering crust thickness of the area corresponding to each seismic station into the third weathering crust rare earth ore content prediction model, and predict the weathering crust rare earth resource assessment result within the mining area to be evaluated.

[0102] Corresponding to the above-disclosed weathering crust rare earth resource evaluation system, the embodiment of the present invention further discloses a weathering crust rare earth resource evaluation method. The following describes in detail the weathering crust rare earth resource evaluation method disclosed in the embodiment of the present invention in combination with the above-described weathering crust rare earth resource evaluation system.

[0103] Figure 2 The figure shows a flow chart of a method for assessing rare earth resources in a weathering crust according to an embodiment of the present invention.

[0104] like Figure 2 As shown, the weathering crust rare earth resource assessment method according to an embodiment of the present invention may include step S100, step S200, step S300, step S400, step S500, step S600, step S700 and step S800.

[0105] In step S100, the seismic stations within the mining area to be evaluated are used to collect first seismic signal data of the area corresponding to each seismic station.

[0106] Seismic stations are deployed within the scope of the mining area to be evaluated. The topography should be taken into consideration when selecting the site for the seismic station to avoid continuous specific noise environments such as wind vents, flowing water and river banks. The seismic station is a three-component seismograph. The natural earthquake background noise data is continuously recorded by the above-mentioned seismic station according to the preset acquisition period to obtain the first seismic signal data, wherein the seismic station is capable of receiving vibration signals in the horizontal and vertical directions. The above-mentioned preset acquisition period is greater than 24 hours to obtain richer data samples, which is helpful to more accurately analyze the statistical characteristics of the earthquake background noise. The increase in acquisition time can better identify and filter out periodic or temporary interference signals.

[0107] In step S200, the first seismic signal data is preprocessed to obtain second seismic signal data.

[0108] In one example, the Figure 3 The process shown pre-processes the seismic signal data.

[0109] Figure 3 A flowchart of preprocessing seismic signal data according to an embodiment of the present invention is illustrated.

[0110] like Figure 3 As shown, in step S201, the first seismic signal data collected is batch-formatted and processed using automated scripts and open source software, such as Obspy, PASSCAL, etc., to obtain first pre-processed intermediate data after format conversion. For example, the first seismic signal data is converted into SAC, SEED, MiniSEED and other formats. At the same time, parallel processing technology is used in the conversion process to improve data conversion efficiency.

[0111] In step S202, the first preprocessed intermediate data is subjected to a mean removal process to obtain second preprocessed intermediate data.

[0112] In step S203, the second preprocessed intermediate data is processed to remove the instrument response, so as to obtain third preprocessed intermediate data.

[0113] In step S204, detrending processing is performed on the third preprocessed intermediate data to obtain fourth preprocessed intermediate data.

[0114] Finally, in step S205, an adaptive filter is constructed based on wavelet transform, and the fourth preprocessed intermediate data is adaptively filtered using the adaptive filter to obtain the second seismic signal data after preprocessing, wherein the wavelet transform is a signal processing technology based on time-frequency analysis, which can provide information in both time and frequency domains, and the adaptive filter can automatically adjust the filtering parameters according to the dynamic characteristics of the data, thereby improving the efficiency and flexibility of the preprocessing.

[0115] Return to reference Figure 2 In step S300, the second seismic signal data is segmented according to a preset time interval to obtain segmented third seismic signal data, wherein the preset time interval is i (i=1-24) hours; data segmentation is an important step in seismic data processing, which is used to prepare for the subsequent comparison to select a suitable time period for spectral ratio calculation.

[0116] For example, if the preset time interval is 1 hour, then 0-1 hours is one segment, and 1-2 hours is one segment; if the preset time interval is 2 hours, then 0-2 hours is one segment, and 2-4 hours is one segment.

[0117] In step S400, based on a multi-window long-short time window ratio algorithm, the transient interference occurrence points in the third seismic signal data are marked, and the fourth seismic signal data are obtained according to the marking result.

[0118] In one example, this can be done by Figure 4 The process shown acquires fourth seismic signal data.

[0119] Figure 4 The figure shows a flow chart of the steps of marking the transient interference occurrence points in the third seismic signal data and obtaining the fourth seismic signal data based on the marking results.

[0120] like Figure 4 As shown, in step S401, a short time window (STA) of a first length is generated according to the main period of the seismic signal, wherein the short time window is set to 2-3 times the main period of the seismic signal.

[0121] In step S402, based on the first length, a long time window (LTA) of a second length is generated, wherein the long time window is set to 5-10 times of the first length.

[0122] In step S403, the third seismic signal data is overlapped using short-time windows and long-time windows of different lengths.

[0123] In step S404, for each short time window, the short time window is used as a short time window to be detected, and the long time window corresponding to the short time window to be detected is used as a long time window to be detected.

[0124] In step S405, based on the signal changes within the coverage of the short-time window to be detected and the corresponding signal changes within the coverage of the long-time window to be detected, the long-short time window signal change ratio (STA / LTA ratio) corresponding to the short-time window to be detected is calculated, wherein the long-short time window signal change ratio reflects the relative size of the signal change within the coverage of the short-time window to be detected and the signal change within the coverage of the long-time window to be detected.

[0125] In step S406, it is determined whether the ratio of the change of each long-time window signal to the short-time window signal is greater than a preset ratio threshold.

[0126] If the long-short time window signal change ratio is greater than the preset ratio threshold, step S407 is executed to mark the position of the short time window to be detected corresponding to the long-short time window signal change ratio as the transient interference occurrence point.

[0127] If the long-short time window signal change ratio is less than or equal to the preset ratio threshold, step S408 is executed to not mark the position of the short time window to be detected corresponding to the long-short time window signal change ratio as the transient interference occurrence point.

[0128] Next, in step S409, a marking result evaluation is performed on the marked transient interference occurrence point to obtain a marking evaluation result.

[0129] In step S410, the mark evaluation results are detected in real time, and the window lengths and window positions of the short and long windows are optimized using the latest mark evaluation results. At the same time, the mark evaluation results are used to optimize the preset ratio threshold, so that the method of steps S401 to S409 can adapt to signal changes and environmental interference.

[0130] For example, if the labeling evaluation results show that the labeling results of certain time window positions are very accurate, the weights of these positions can be increased or other time windows can be adjusted to better capture interference.

[0131] Finally, in step S411, the third seismic signal is subjected to a first data cleaning process using the transient interference occurrence point, the signal at the transient interference occurrence point is cleared, and the cleaned fourth seismic signal data is obtained.

[0132] The embodiment of the present invention detects and marks the transient interference of the third seismic signal data through an improved multi-window long-short time window ratio algorithm. The short time window is used to quickly respond to the sudden change signal, and the long time window is used to reflect the average background level of the seismic signal. It can capture the transient interference in the seismic signal from multiple angles and improve the sensitivity and accuracy of detection. At the same time, by using the marking evaluation result to optimize the parameters, the improved multi-window long-short time window ratio algorithm can be applied to situations where the signal is complex or the noise level changes greatly. Since the signal-to-noise ratio of the transient interference is low, the signal corresponding to the position of the transient interference occurrence point is cleared and is not allowed to participate in the subsequent spectrum ratio calculation.

[0133] In step S500, the corresponding peak frequency of the spectrum ratio curve is obtained according to the horizontal vibration spectrum density and the vertical vibration spectrum density of the fourth seismic signal data in the frequency domain.

[0134] In one example, this can be done by Figure 5 The process shown obtains the peak frequency of the spectral ratio curve.

[0135] Figure 5 The figure shows a flow chart of the steps of obtaining the corresponding peak frequency of the spectrum ratio curve according to the three-component frequency spectrum density of the fourth seismic signal data.

[0136] like Figure 5 As shown, in step S501, a frequency domain analysis time window of a third length is generated according to the period of the seismic signal and the research requirements of the low-frequency signal, wherein the above-mentioned frequency domain analysis time window contains at least 10 seismic signal periods. The longer the frequency domain analysis time window, the more complete and stable the obtained signal low-frequency information is. However, if it is too long, it may bring a large amount of random noise, causing certain interference to the data processing results.

[0137] For example, if the preset time interval for data segmentation is 4 hours and the low-frequency research requirement is 0.2 Hz, the generated frequency domain analysis time window is at least 50 seconds, and a series of time window lengths are selected (from 50 seconds to 80 seconds, each time increasing by 10 seconds).

[0138] In step S502, the fourth seismic signal is subjected to sliding selection using the above-mentioned spectrum analysis time window to obtain sliding selected first time window signals.

[0139] In step S503, each first time window signal is smoothed to obtain a second time window signal. For example, the first time window signal is smoothed using the Konno & Ohmachi smoothing method to obtain a smoothed second time window signal.

[0140] In step S504, based on a preset window function, a fast Fourier transform (FFT) process is performed on the second time window signal to obtain frequency domain information corresponding to the second time window signal. For example, a Hanning window function is applied to each second time window signal.

[0141] In step S505, the frequency domain information corresponding to the second time window signal is used to calculate the horizontal vibration spectrum density and the vertical vibration spectrum density of the second time window signal in the frequency domain, wherein the above-mentioned horizontal vibration spectrum density includes the north-south component spectrum density and the east-west component spectrum density.

[0142] In step S506, the horizontal vibration spectrum density and the vertical vibration spectrum density are used to calculate the three-component vibration spectrum density ratio corresponding to the second time window signal, and the calculation formula is:

[0143]

[0144] Where, f(c) is the three-component vibration spectrum density ratio, A EW (f) is the power spectrum density of the east-west component, A NS (f) is the spectrum density of the north-south component, AUD (f) is the vertical component spectral density.

[0145] In step S507, a spectrum ratio curve is drawn according to the above three-component vibration spectrum density ratio, and the average value and standard deviation are calculated.

[0146] In step S508, the spectral ratio curve is used to analyze and obtain the peak frequency of the spectral ratio curve.

[0147] In step S600, the weathering crust thickness of the area corresponding to the seismic station is obtained using the peak component of the spectral ratio curve.

[0148] In one example, this can be done by Figure 6 The process shown obtains the weathering crust thickness in the area corresponding to the seismic station.

[0149] Figure 6 The figure shows a flow chart of the steps of obtaining the weathering crust thickness of the area corresponding to the seismic station using the peak component of the spectral ratio curve.

[0150] like Figure 6 As shown, in step S601, it is determined whether there is an average shear wave velocity of the weathering crust strata in the area corresponding to the seismic station.

[0151] If the average shear wave velocity of the weathering crust stratum in the area corresponding to the seismic station can be obtained by collecting existing data and literature, seismic refraction and reflection seismic data in the area, then step S602 is executed, using the average shear wave velocity of the weathering crust stratum in the area corresponding to the seismic station and the corresponding peak frequency of the spectrum ratio curve, assuming that under resonance conditions, the thickness of the weathering crust is approximately one-quarter of the wavelength of the shear wave, and the first weathering crust thickness in the area corresponding to the seismic station is calculated. The calculation formula of the above-mentioned first weathering crust thickness is:

[0152]

[0153] Where H is the thickness of the first weathering crust, V s is the average shear wave velocity of the weathering crust sedimentary layer in the area corresponding to the seismic station, f c is the peak frequency of the spectral ratio curve.

[0154] If the average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station is unknown, or the known average shear wave velocity of the weathered crust strata is not accurate enough, step S603 is executed to select a part of the area corresponding to the seismic station as a sample area.

[0155] In step S604, in the sample area, the geological exploration data are used to calibrate the sample value of the thickness of the ore-bearing weathering crust, wherein the geological exploration data include the results of drilling, trenching and profile.

[0156] In step S605, the weathering crust thickness sample values ​​corresponding to the sample area are fitted with the peak frequencies of the spectrum ratio curves corresponding to the sample area to obtain fitting parameters i and k, which are used as parameters for the area corresponding to the seismic station.

[0157] In step S606, the second weathering crust thickness of the area corresponding to the seismic station is calculated according to the empirical formula (Delgado et al. 2000) using the fitting parameters of the area corresponding to the seismic station and the peak frequency of the spectral ratio curve corresponding to the area corresponding to the seismic station. The calculation formula of the second weathering crust thickness is:

[0158] lgH'=lgk+i lgf c

[0159] The above formula is a logarithmic power function relationship, H' is the thickness of the second weathering crust, k and i are fitting parameters, and f c is the peak frequency of the spectral ratio curve, and lg is the logarithm with base 10.

[0160] The weathering crust depth is obtained by subtracting the corresponding weathering crust thickness from the altitude of the corresponding area of ​​the seismic station. Fig. 9 Figure shows a schematic diagram of the weathering crust depth calculation.

[0161] In step S700, a first weathering crust rare earth mineral content prediction model to be trained is constructed based on geological exploration data, the first weathering crust rare earth mineral content prediction model is trained using a model training set to obtain a trained second weathering crust rare earth mineral content prediction model, the second weathering crust rare earth mineral content prediction model is evaluated using a model test set, and a third weathering crust rare earth mineral content prediction model that passes the model evaluation is obtained according to the model evaluation result.

[0162] In one example, this can be done by Figure 7 The process shown obtains the prediction model of rare earth mineral content in the third weathering crust.

[0163] Figure 7 The figure shows a flow chart of the steps of constructing a prediction model for rare earth mineral content in weathering crust.

[0164] like Figure 7 As shown, in step S701, first geological exploration data is obtained from a public database, and the first geological exploration data includes rare earth content data, weathering crust thickness data, geological structure data, terrain data and remote sensing image data.

[0165] For example, geological survey institutions, scientific research institutes and government open data websites are used to collect the first geological exploration data on rare earth content, weathering crust thickness, geological structure, topography and remote sensing images from geological survey reports, published articles and existing exploration data. Among them, rare earth content data include rare earth element content data in soil, rock and water samples analyzed in the laboratory; weathering crust thickness data include weathering crust thickness information, usually obtained through geological drilling cataloging; geological structure data include geological age, rock type, stratum dip and inclination and its contact relationship, geological structure and other information; terrain data include high-resolution SRTM and LiDAR data, and terrain features such as elevation, slope, and gully density are extracted from terrain data; remote sensing image data include high-resolution Sentinel-2 or QuickBird images, which analyze vegetation index and soil moisture distribution and other features.

[0166] In step S702, the first geological exploration data is sorted and processed to obtain second geological exploration data.

[0167] For example, the first geological exploration data is uniformly converted into Excel or CSV format, and the sorted second geological exploration data includes at least the following columns: sample ID, collection location (longitude, latitude), rock type, rare earth element content, soil moisture, altitude, etc.

[0168] In step S703, the second geological exploration data is checked for abnormal data, and a second data cleaning process is performed on the second geological exploration data according to the inspection result. The second data cleaning process includes deleting abnormal, missing or incomplete data to ensure that no erroneous data is mixed therein, thereby obtaining the cleaned third geological exploration data.

[0169] In step S704, a feature list that may affect the rare earth content and the thickness of the weathering crust is created using the third geological exploration data, the feature list including geological features, topographic features, remote sensing image features, Thickness of Mineralized Weathering Crust (TW) features and Rare Earth Element Content (RE) features. The geological features include rock type (RockType, RT), stratigraphic chronology (Sedimentary Geochronology, SG), dip (Dip, DP) and striker (SK); the topographic features include altitude (Altitude, AL), slope (Slope, SL) and ruggedness (Ruggedness, RU); the remote sensing image features include vegetation coverage (Vegetation Coverage, VC) and soil moisture (Soil Moisture, SM).

[0170] In step S705, for some machine learning algorithms, such as support vector machine (SVM) and K-nearest neighbor (KNN), since these algorithms are very sensitive to feature scale, it is necessary to normalize the features. The numerical range of all features in the feature list is adjusted to a specific interval so that the model can treat each feature more fairly and obtain normalized features.

[0171] For example, based on the Min-Max Scaling method, the features in the feature list are normalized. For each feature column that needs to be normalized, the minimum and maximum values ​​of the column are found, and the normalized features are calculated. The formula is:

[0172]

[0173] Among them, X norm is the normalized eigenvalue, X is the original eigenvalue, X min is the minimum value of the feature column, X max is the maximum value of the feature column.

[0174] In addition, randomly checking normalized features to verify whether the normalized results are reliable can be achieved through feature_column in Pandas.

[0175] In step S706, a three-dimensional array is constructed using the normalized features, the longitude information corresponding to the normalized features, and the latitude information corresponding to the normalized features to obtain a three-dimensional feature matrix, and the rare earth content features and the weathering crust thickness features are separated in the process.

[0176] Alternatively, the above steps can be implemented using Pandas and Sklearn.

[0177] In step S707, a first weathering crust rare earth mineral content prediction model to be trained is constructed based on the three-dimensional feature matrix.

[0178] In step S708, a model data set is constructed using the weathering crust thickness characteristics and the rare earth content characteristics, and the above model data set is divided into a model training set and a model test set, so as to train the model and independently evaluate its performance. The generalization ability of the model is evaluated through an independent test set to ensure that the model will not overfit.

[0179] In step S709, the necessary library for model training is loaded first, and then the model training set is used to perform instance memory training on the first weathering crust rare earth mineral content prediction model to be trained. Through model training, the prediction model will learn the pattern and method of the data in the model training set to obtain the trained second weathering crust rare earth mineral content prediction model.

[0180] For example, load the SVM or KNN model training and evaluation library of Sklearn, use support vector machine (SVM) and K-nearest neighbor (KNN) as the model architecture, and adjust the hyperparameters of the SVM and KNN models (such as C and epsilon of SVM, n_neighbors of KNN) according to actual conditions to obtain the best performance. The above process can use cross-validation, grid search and other techniques to find the optimal hyperparameter combination.

[0181] In step S710, the model training set is input into the trained second weathering crust rare earth mineral content prediction model for prediction, and the prediction result is used as the model evaluation result. The above model evaluation result can be used to evaluate the generalization ability of the model on unknown data.

[0182] In step S711, it is determined whether the model evaluation result meets the preset model evaluation standard, for example, it is determined whether the prediction accuracy in the model evaluation result is greater than 90%.

[0183] If the model evaluation result meets the preset model evaluation standard, step S713 is executed to determine that the second weathering crust rare earth mineral content model has good generalization ability, and the second weathering crust rare earth mineral content prediction model is used as the third weathering crust rare earth mineral content prediction model.

[0184] If the model evaluation result does not meet the preset model evaluation standard, step S712 is executed to optimize and re-evaluate the second weathering crust rare earth mineral content prediction model.

[0185] In addition, the predictive performance of the prediction model can be quantified by calculating the mean square error (MSE) and the coefficient of determination (R^2).

[0186] In step S800, the thickness of the weathering crust in the area corresponding to each seismic station is input into the third weathering crust rare earth mineral content prediction model to predict the rare earth mineral content, and the rare earth mineral content of each three-dimensional grid in the area corresponding to the seismic station is obtained. According to the rare earth mineral content of each three-dimensional grid in the area corresponding to each seismic station, the weathering crust rare earth mineral resources within the mining area to be evaluated are obtained.

[0187] The embodiment of the present invention discloses a method, system, device, medium and program product for evaluating weathering crust rare earth resources, including: firstly, using a seismic station within the scope of the mining area to be evaluated to collect first seismic signal data; preprocessing the first seismic signal data to obtain second seismic signal data; segmenting the second seismic signal data to obtain third seismic signal data; marking the transient interference occurrence point of the seismic signal based on a multi-window long-short time window ratio algorithm, and obtaining fourth seismic signal data according to the marking result; obtaining the peak frequency of the spectrum ratio curve according to the three-component vibration spectrum density of the fourth seismic signal data, and calculating the thickness of the weathering crust in the corresponding area; constructing a rare earth ore prediction model based on geological exploration data; inputting the thickness of the weathering crust into the prediction model to obtain the evaluation result of the weathering crust rare earth resources in the mining area to be evaluated. The embodiment of the present invention effectively improves the evaluation efficiency and accuracy of the evaluation of weathering crust rare earth resources.

[0188] In addition, an embodiment of the present invention also provides a weathering crust rare earth resource assessment device, which includes: a processor and a memory; the memory is used to store one or more program instructions; the processor is used to run one or more program instructions to execute the steps of a weathering crust rare earth resource assessment method as described in any of the above items.

[0189] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a weathering crust rare earth resource assessment method as described in any of the above items are implemented.

[0190] In addition, an embodiment of the present invention further provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the steps of a weathering crust rare earth resource assessment method as described in any one of the above items are implemented.

[0191] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware. The storage medium may be a memory, for example, a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DRRAM).The storage medium described in the embodiment of the present invention is intended to include but is not limited to these and any other suitable types of memory. Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by a combination of hardware and software. When the software is applied, the corresponding function can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a general or special-purpose computer can access. Although the present invention has been described in detail above with general descriptions and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to it on the basis of the present invention. Therefore, these modifications or improvements made on the basis of not departing from the spirit of the present invention all belong to the scope of protection claimed in the present invention.

Claims

1. A method for assessing rare earth resources in weathering crust, characterized in that: The method comprises: Using seismic stations within the mining area to be evaluated, first seismic signal data of the area corresponding to each seismic station is collected; Performing data preprocessing on the first seismic signal data to obtain second seismic signal data; According to a preset time interval, performing data segmentation processing on the second seismic signal data to obtain third seismic signal data; Based on a multi-window long-short time window ratio algorithm, marking the transient interference occurrence point in the third seismic signal data, and obtaining fourth seismic signal data according to the marking result; Obtaining a peak frequency of a spectrum ratio curve corresponding to the fourth seismic signal data according to a horizontal vibration spectrum density and a vertical vibration spectrum density of the fourth seismic signal data in a frequency domain; The peak frequency of the spectral ratio curve is used to obtain the thickness of the weathering crust in the area corresponding to the seismic station, including: Determine whether there is an average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station; If there is an average shear wave velocity of the weathering crust stratum in the area corresponding to the seismic station, the first weathering crust thickness in the area corresponding to the seismic station is calculated using the average shear wave velocity of the weathering crust stratum and the corresponding peak frequency of the spectrum ratio curve. The calculation formula of the first weathering crust thickness is: Where H is the thickness of the first weathering crust, V s is the average shear wave velocity of the weathering crust in the area corresponding to the seismic station, f c is the peak frequency of the spectrum ratio curve; If there is no average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station, a part of the area corresponding to the seismic station is selected as the sample area; According to the geological exploration data of the sample area, a sample value of the weathering crust thickness corresponding to the sample area is obtained; Using the weathering crust thickness sample value corresponding to the sample area and the peak frequency of the spectrum ratio curve corresponding to the sample area to perform fitting processing, the fitting parameters of the area corresponding to the seismic station are obtained; The thickness of the second weathering crust in the area corresponding to the seismic station is calculated by using the fitting parameters of the area corresponding to the seismic station and the peak frequency of the spectral ratio curve corresponding to the area corresponding to the seismic station. The calculation formula of the thickness of the second weathering crust is: <h2 style=";text-align:left;direction:ltr">lgH′=lgk+i lgf<h2 style=";text-align:left;direction:ltr"> c Where H' is the thickness of the second weathering crust, k and i are fitting parameters, and f c is the peak frequency of the spectrum ratio curve; Based on the geological exploration data, a first weathering crust rare earth mineral content prediction model to be trained is constructed, the first weathering crust rare earth mineral content prediction model is trained using a model training set to obtain a trained second weathering crust rare earth mineral content prediction model, the second weathering crust rare earth mineral content prediction model is evaluated using a model test set, and a third weathering crust rare earth mineral content prediction model that has passed the model evaluation is obtained according to the model evaluation result; The thickness of the weathering crust in the area corresponding to each seismic station is input into the third weathering crust rare earth mineral content prediction model to obtain the weathering crust rare earth resource assessment result within the mining area to be assessed.

2. A method for assessing rare earth resources in weathering crust according to claim 1, characterized in that: Performing data preprocessing on the first seismic signal data to obtain second seismic signal data includes: Performing format conversion processing on the first seismic signal data to obtain first preprocessed intermediate data; Performing a mean removal process on the first preprocessed intermediate data to obtain second preprocessed intermediate data; performing instrument response removal processing on the second preprocessed intermediate data to obtain third preprocessed intermediate data; Performing detrending processing on the third preprocessed intermediate data to obtain fourth preprocessed intermediate data; An adaptive filter is constructed based on wavelet transform, and the adaptive filter is used to perform adaptive filtering processing on the fourth preprocessed intermediate data to obtain the second seismic signal data after preprocessing.

3. A method for assessing rare earth resources in weathering crust according to claim 1, characterized in that: Based on a multi-window long-short time window ratio algorithm, the transient interference occurrence point in the third seismic signal data is marked, and fourth seismic signal data is obtained according to the marking result, including: Generate a short-time window of a first length according to the period of the seismic signal; Based on the first length, generating a long time window of a second length; Using the short time window and the long time window to overlap the third seismic signal data; For each short-time window, the short-time window is used as the short-time window to be detected, and the long-time window corresponding to the short-time window to be detected is used as the long-time window to be detected; According to the signal change within the coverage range of the short time window to be detected and the signal change within the coverage range of the long time window to be detected, a ratio of the long and short time window signal change is calculated; Determine whether the ratio of the long-time window signal change to the short-time window signal change is greater than a preset ratio threshold; If the ratio of the long-time window signal change to the short-time window signal change is greater than a preset ratio threshold, the position of the short-time window to be detected is marked as a transient interference occurrence point; If the ratio of the long-time window signal change to the short-time window signal change is less than or equal to a preset ratio threshold, the position of the short-time window to be detected is not marked as a transient interference occurrence point; Performing marking result evaluation on the transient interference occurrence point to obtain a marking evaluation result; Optimizing the time window length, time window position and preset ratio threshold value by using the marking evaluation result in real time; The first data cleaning process is performed on the third seismic signal according to the transient interference occurrence point, and the signal at the position corresponding to the transient interference occurrence point is cleared to obtain the cleaned fourth seismic signal data.

4. A method for assessing rare earth resources in weathering crust according to claim 1, characterized in that: Obtaining a peak frequency of a spectrum ratio curve corresponding to the fourth seismic signal data according to the horizontal vibration spectrum density and the vertical vibration spectrum density of the fourth seismic signal data in the frequency domain, including: According to the period of the seismic signal and the research requirements of the low-frequency seismic signal, a spectrum analysis time window of the third length is generated; Using the spectrum analysis time window to slide select the fourth seismic signal data, and select a first time window signal; Performing smoothing on the first time window signal to obtain a second time window signal; Based on a preset window function, performing fast Fourier transform processing on the second time window signal to obtain frequency domain information corresponding to the second time window signal; Using the frequency domain information corresponding to the second time window signal, calculate the horizontal vibration spectrum density and the vertical vibration spectrum density of the second time window signal in the frequency domain, wherein the horizontal vibration spectrum density includes the north-south component spectrum density and the east-west component spectrum density; The horizontal vibration spectrum density and the vertical vibration spectrum density are used to obtain the three-component vibration spectrum density ratio corresponding to the second time window signal. The calculation formula of the three-component vibration spectrum density ratio is: Where, f(c) is the three-component vibration spectrum density ratio, A EW (f) is the power spectrum density of the east-west component, A NS (f) is the spectrum density of the north-south component, A UD (f) is the vertical component spectral density; A spectrum ratio curve is obtained by plotting the three-component vibration spectrum density ratio; The spectrum ratio curve is used to obtain the peak frequency of the spectrum ratio curve.

5. A method for assessing rare earth resources in weathering crust according to claim 1, characterized in that: A first weathering crust rare earth ore content prediction model to be trained is constructed based on geological exploration data, the first weathering crust rare earth ore content prediction model is trained using a model training set to obtain a trained second weathering crust rare earth ore content prediction model, the second weathering crust rare earth ore content prediction model is evaluated using a model test set, and a third weathering crust rare earth ore content prediction model with qualified model evaluation is obtained according to the model evaluation result, including: Acquire first geological exploration data from a public database, wherein the first geological exploration data includes rare earth content data, weathering crust thickness data, geological structure data, terrain data, and remote sensing image data; Performing data format standardization processing on the first geological exploration data to obtain second geological exploration data; Performing abnormal data inspection processing on the second geological exploration data, and performing second data cleaning processing according to the inspection processing result to obtain third geological exploration data after data cleaning; Using the third geological exploration data to construct a feature list, the feature list includes geological features, topographic features, remote sensing image features, weathering crust thickness features, and rare earth content features; Normalizing the features in the feature list to obtain normalized features; Constructing a three-dimensional feature matrix using the normalized features, the longitude information corresponding to the normalized features, and the latitude information corresponding to the normalized features; Constructing a first weathering crust rare earth mineral content prediction model to be trained based on the three-dimensional feature matrix; Generate a model data set according to the weathering crust thickness characteristics and the rare earth content characteristics, and divide the model data set into a model training set and a model test set; Using the model training set to perform model training on the first weathering crust rare earth mineral content prediction model to obtain a trained second weathering crust rare earth mineral content prediction model; Using the model test set to perform model evaluation on the second weathering crust rare earth mineral content prediction model to obtain a model evaluation result; Determine whether the model evaluation result meets the preset model evaluation standard; If the model evaluation result meets the preset model evaluation standard, the second weathering crust rare earth mineral content prediction model is used as the third weathering crust rare earth mineral content prediction model; If the model evaluation result does not meet the preset model evaluation standard, the second weathering crust rare earth mineral content prediction model is optimized and re-evaluated.

6. A weathering crust rare earth resource assessment system, characterized in that: The system comprises: A seismic signal acquisition module, used to acquire first seismic signal data of the area corresponding to each seismic station by using seismic stations within the mining area to be evaluated; A data preprocessing module, used for performing data preprocessing on the first seismic signal data to obtain second seismic signal data; A data segmentation module, used for performing data segmentation processing on the second seismic signal data according to a preset time interval to obtain third seismic signal data; A transient interference marking module, used for marking the transient interference occurrence points in the third seismic signal data based on a multi-window long-short time window ratio algorithm, and obtaining fourth seismic signal data according to the marking result; A seismic signal frequency domain analysis module, used to obtain a peak frequency of a spectrum ratio curve corresponding to the fourth seismic signal data according to a horizontal vibration spectrum density and a vertical vibration spectrum density of the fourth seismic signal data in the frequency domain; The weathering crust thickness analysis module is used to obtain the weathering crust thickness of the area corresponding to the seismic station by using the peak frequency of the spectral ratio curve, including: Determine whether there is an average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station; If there is an average shear wave velocity of the weathering crust stratum in the area corresponding to the seismic station, the first weathering crust thickness in the area corresponding to the seismic station is calculated using the average shear wave velocity of the weathering crust stratum and the corresponding peak frequency of the spectrum ratio curve. The calculation formula of the first weathering crust thickness is: Where H is the thickness of the first weathering crust, V s is the average shear wave velocity of the weathering crust in the area corresponding to the seismic station, f c is the peak frequency of the spectrum ratio curve; If there is no average shear wave velocity of the weathered crust strata in the area corresponding to the seismic station, a part of the area corresponding to the seismic station is selected as the sample area; According to the geological exploration data of the sample area, a sample value of the weathering crust thickness corresponding to the sample area is obtained; Using the weathering crust thickness sample value corresponding to the sample area and the peak frequency of the spectrum ratio curve corresponding to the sample area to perform fitting processing, the fitting parameters of the area corresponding to the seismic station are obtained; The thickness of the second weathering crust in the area corresponding to the seismic station is calculated by using the fitting parameters of the area corresponding to the seismic station and the peak frequency of the spectral ratio curve corresponding to the area corresponding to the seismic station. The calculation formula of the thickness of the second weathering crust is: lgH′=lgk+ilgf c Where H' is the thickness of the second weathering crust, k and i are fitting parameters, and f c is the peak frequency of the spectrum ratio curve; A rare earth content prediction model construction module is used to construct a first weathering crust rare earth ore content prediction model to be trained based on geological exploration data, use a model training set to perform model training on the first weathering crust rare earth ore content prediction model to obtain a trained second weathering crust rare earth ore content prediction model, use a model test set to perform model evaluation on the second weathering crust rare earth ore content prediction model, and obtain a third weathering crust rare earth ore content prediction model that has passed the model evaluation according to the model evaluation result; The rare earth resource assessment module is used to input the weathering crust thickness of the area corresponding to each seismic station into the third weathering crust rare earth ore content prediction model to obtain the weathering crust rare earth resource assessment result within the mining area to be assessed.

7. A weathering crust rare earth resource assessment device, characterized in that: The device comprises: a processor and a memory; The memory is used to store one or more program instructions; The processor is used to run one or more program instructions to execute the steps of a weathering crust rare earth resource assessment method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for assessing weathering crust rare earth resources as described in any one of claims 1 to 5 are implemented.

9. A computer program product, characterized in that The computer program product includes computer program instructions, which, when executed by a processor, implement the steps of a weathering crust rare earth resource assessment method as described in any one of claims 1 to 5.

Images