Muon absorption imaging geological interpretation method, device, equipment, medium and product

Abstract

The invention discloses a muon absorption imaging geological interpretation method and device, equipment, a medium and a product, and relates to the field of mineral resource exploration, and the method comprises the steps: obtaining muon absorption imaging data, geological data and geophysical prospecting data of a research area; according to the muon absorption imaging data, performing feature extraction by adopting a visual feature extraction method and a machine learning algorithm to obtain gradient features, continuity features, morphological features and clustering features; according to the gradient features, the continuity features, the morphological features and the clustering features, interpreting the metallogenic favorable fracture, the lithologic interface and the ore control rock mass to determine the spatial morphology and attribute parameters of the geology in the research area; according to the geological data and the geophysical prospecting data, reliability verification is carried out on interpretation results of the metallogenic favorable fracture, the lithologic interface and the ore control rock mass, and the feature extraction process is adjusted according to the reliability verification result and then interpreted again. The method is high in automation degree and adaptability, and improves the precision and reliability of geological interpretation.

Description

Technical Field

[0001] This application relates to the field of mineral resource exploration technology, and in particular to a method, apparatus, equipment, medium and product for muon absorption imaging geological interpretation. Background Technology

[0002] With the increasing demand for deep mineral resource exploration, accurate detection of concealed geological targets (deep mineralization faults, concealed rock masses, lithological interfaces, etc.) has become a core challenge. Current mainstream deep geological exploration technologies (drilling exploration, traditional geophysical exploration, and conventional geological interpretation techniques) and their verification mechanisms have significant shortcomings, making it difficult to meet the demands of high-precision exploration. Specific problems and limitations of existing solutions are as follows: (1) Borehole exploration: Its advantage is that the data is intuitive and reliable. The core problems are high cost, long cycle, and limited spatial coverage, making it impossible to continuously explore large areas of concealed areas. Although the existing solution of densified borehole networks improves coverage, it further increases costs, and there are "point-to-surface" inference errors in complex structural areas, making it difficult to accurately depict the three-dimensional distribution of geological targets.

[0003] (2) Traditional geophysical exploration: Gravity, magnetic and electrical methods can achieve large-area coverage, but they have problems such as strong ambiguity and insufficient resolution (e.g., gravity anomalies are difficult to distinguish between rock masses and strata with similar density, and electrical methods have limited penetration into high-resistivity strata). Existing multi-method joint inversion schemes lack a unified data fusion standard, the spatial matching error of data exceeds 1m, the reliability of inversion results is insufficient, and it is impossible to accurately locate hidden faults and lithological interfaces.

[0004] (3) Conventional geological interpretation techniques: These rely on human visual interpretation and experience accumulation, resulting in strong subjectivity and non-quantitative feature extraction. Imaging data such as density cross sections are mostly qualitative descriptions, lacking precise quantitative representations such as fracture dip angles and lithological interface gradient thresholds. Although some studies have introduced simple algorithms to assist interpretation, a fusion system of "visual experience + intelligent algorithm" has not been formed, making it difficult to achieve objective and standardized extraction of geological features, resulting in poor consistency and low accuracy of interpretation results.

[0005] (4) The interpretation results verification mechanism is imperfect: verification is mostly done using a single data source (such as a small number of boreholes), lacking a closed loop of cross-verification of multi-source data, which cannot effectively correct interpretation errors. When the interpretation results conflict with local borehole data, it is difficult to determine the source of error (data or method error), resulting in insufficient credibility of the results and inability to support subsequent mineral exploration decisions. Summary of the Invention

[0006] The purpose of this application is to provide a method, apparatus, equipment, medium, and product for geological interpretation using muon absorption imaging, which can improve the accuracy and reliability of geological interpretation.

[0007] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for geological interpretation using muon absorption imaging, including: Acquire muon absorption imaging data, geological data, and geophysical data for the study area; Based on the muon absorption imaging data, visual feature extraction methods and machine learning algorithms are used to extract features, resulting in gradient features, continuity features, morphological features, and clustering features. Based on the gradient characteristics, continuity characteristics, morphological characteristics, and clustering characteristics, the favorable faults for mineralization, lithological interfaces, and ore-controlling rock masses are interpreted to determine the spatial morphology and attribute parameters of the geology within the study area. Based on the geological data and geophysical data, the reliability of the interpretation results of favorable faults, lithological interfaces and ore-controlling rock masses was verified, and the feature extraction process was adjusted and reinterpreted based on the reliability verification results.

[0008] Secondly, this application provides a muon absorption imaging geological interpretation device, comprising: The data acquisition module is used to acquire muon absorption imaging data, geological data, and geophysical data of the study area; The feature extraction module is used to extract features from the muon absorption imaging data using visual feature extraction methods and machine learning algorithms to obtain gradient features, continuity features, morphological features and clustering features. The interpretation module is used to interpret the favorable faults, lithological interfaces and ore-controlling rock masses based on the gradient features, the continuity features, the morphological features and the clustering features, so as to determine the spatial morphology and attribute parameters of the geology in the study area. The verification module is used to verify the reliability of the interpretation results of favorable faults, lithological interfaces and ore-controlling rock masses based on the geological data and the geophysical data, and to reinterpret the feature extraction process after adjusting it according to the reliability verification results.

[0009] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described muon absorption imaging geological interpretation method.

[0010] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described muon absorption imaging geological interpretation method.

[0011] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described muon absorption imaging geological interpretation method.

[0012] According to the specific embodiments provided in this application, this application achieves the following technical effects: By fusing muon absorption imaging data, geological data, and geophysical data, the accuracy and reliability of geological interpretation are significantly improved. Visual feature extraction and machine learning algorithms are employed to automatically extract gradient, continuity, morphology, and clustering multi-dimensional features, reducing subjective errors and improving the efficiency and objectivity of feature recognition compared to traditional manual interpretation. Based on multi-feature joint interpretation, favorable faults, lithological interfaces, and ore-controlling rock masses can be accurately delineated, clearly depicting the spatial morphology and attribute parameters of geological bodies, providing a reliable basis for mineralization prediction and geological exploration. The introduction of geological and geophysical data for cross-validation forms a closed-loop process of "interpretation-validation-adjustment-reinterpretation," effectively reducing the bias of single data points and improving the credibility and stability of interpretation results. The overall solution has a high degree of automation and strong adaptability, efficiently supporting fine exploration under complex geological conditions and reducing exploration costs and risks. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is an application environment diagram of a muon absorption imaging geological interpretation method according to an embodiment of this application.

[0015] Figure 2 This is a schematic flowchart of a muon absorption imaging geological interpretation method provided in an embodiment of this application.

[0016] Figure 3 This is a block diagram of intelligent feature extraction based on K-means in one embodiment of this application.

[0017] Figure 4 This is a schematic diagram of the functional modules of a muon absorption imaging geological interpretation device provided in an embodiment of this application.

[0018] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] Mun absorption imaging technology, with its strong penetrating power and sensitivity to density differences, has become an effective means of detecting concealed geological targets. Based on this, this application constructs a geological interpretation technology workflow of "multi-source data fusion - quantitative feature extraction - intelligent and precise interpretation - multi-source closed-loop verification." This workflow uses mun absorption imaging data as its core, integrating visual recognition, intelligent algorithms, and multi-source geological data to accurately interpret favorable faults, lithological interfaces, and ore-controlling rock masses, forming geological results that support exploration. The workflow includes five closely linked and traceable core steps: data preparation and preprocessing, feature extraction (visual + intelligent), core geological target interpretation, multi-source data comprehensive verification, and interpretation result output. This approach can compensate for the shortcomings of existing technologies in data integration, feature extraction, target location, and result verification, achieving high-precision detection and interpretation of concealed geological targets and providing reliable technical support for deep mineral exploration.

[0021] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] The muon absorption imaging geological interpretation method provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be set up independently, integrated into server 102, or placed in the cloud or on another server. Terminal 101 can send muon absorption imaging data, geological data, and geophysical data of the study area to server 102. After receiving the muon absorption imaging data, geological data, and geophysical data of the study area, server 102 performs feature extraction and interpretation. Server 102 can then send the interpretation results back to terminal 101.

[0023] The terminal 101 can be, but is not limited to, various desktop computers, laptops, smartphones, and tablets. The server 102 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0024] In one exemplary embodiment, such as Figure 2As shown, a method for geological interpretation using muon absorption imaging is provided. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps 201 to 204.

[0025] Step 201: Obtain muon absorption imaging data, geological data, and geophysical data for the study area.

[0026] In a specific application example, step 201 includes steps 11 to 13.

[0027] Step 11: Obtain raw data of muon absorption imaging, geological data, and geophysical data for the study area.

[0028] Raw muon absorption imaging data includes muon flux data (unit: muons / (m²)). 2 Density inversion cross-sectional data (unit: g / cm³) 3 The data dimensions must include metadata such as spatial coordinates (X,Y,Z), detection time, and counting efficiency.

[0029] The original geological data includes borehole data of the survey area and surrounding areas (including borehole depth, lithology logging, and core density test values) and geological mapping data (including stratigraphic division and structural occurrence).

[0030] The original geophysical data includes geophysical data (including gravity, magnetic, and electrical profiles) and regional geological survey reports (including rock mass distribution and mineralization patterns).

[0031] Step 12: Establish a unified spatial coordinate system and perform spatial registration on the raw muon absorption imaging data, the raw geological data, and the raw geophysical data to obtain preliminary muon absorption imaging data, geological data, and geophysical data.

[0032] The unified spatial coordinate system adopted is the 2000 National Geodetic Coordinate System or the WGS84 coordinate system. The raw data of muzi absorption imaging, geological data, and geophysical exploration are spatially registered using ArcGIS or MAPGIS software to form a linked database of "muzi data-geological data-geophysical data," with data matching errors controlled within ±0.5m.

[0033] Step 13: The preliminary muon absorption imaging data is subjected to noise removal and geological density inversion in sequence to obtain muon absorption imaging data.

[0034] Specifically, data purification and correction were performed to address noise and environmental interference in the muon imaging system. Outliers were removed using the 3σ criterion. Isolated data points in the muon flux data that deviated from the mean by three times the standard deviation were marked and replaced with the neighborhood mean. The formula is as follows: ;in, For the first i Line number j The original muon flux data of the column, The mean of the data. The standard deviation of the data. n The number of neighboring data points. For the corrected first i Line number j Muon flux data of the column.

[0035] Based on the muon absorption law, the density of a geological body is inverted from the corrected flux data using the following formula: The density inversion formula is obtained by deformation: ;in, Density of the geological body This represents the muon flux after absorption by underground geological bodies. The atmospheric muon reference flux (obtained through open sky measurements). t The thickness of the geological body along the path of muon propagation. The cross section for the interaction between muons and matter (0.17 cm). 2 / g, adjusted according to muon energy).

[0036] The muon absorption imaging data includes muon flux data, density inversion profile data, and geological body density data. The geological data includes borehole data and geological mapping data. The geophysical data includes geophysical data and regional geological survey reports.

[0037] Step 202: Based on the muon absorption imaging data, feature extraction is performed using visual feature extraction methods and machine learning algorithms to obtain gradient features, continuity features, morphological features, and clustering features.

[0038] In a specific application example, visual feature extraction and machine learning-based intelligent extraction are used to uncover core features related to geological targets in density cross-sections, providing quantitative basis for subsequent interpretation. For visual features, based on the visual interpretation experience of professional geologists, three types of core visual features are extracted from the density cross-sections, and image processing techniques are used to quantify these features.

[0039] Step 202 includes steps 21 to 24.

[0040] Step 21: Based on the muon absorption imaging data, calculate the density gradient using the Sobel operator, identify abrupt density transition bands, and obtain gradient features. The formula for calculating the density gradient is as follows: ;in, G x The gradient is in the x-direction. G y The gradient is in the y-direction. G ( x , y ) represents the density gradient. When G ( x , y ≥0.3g / cm 3 It was determined to be a steep transition zone, corresponding to a fault or lithological interface.

[0041] Step 22: Based on the muon absorption imaging data, the continuous extension length of the density variation zone is detected using Hough transform to obtain the continuity characteristics. A continuous extension length ≥ 5m and a stable strike (azimuth change ≤ 15°) are defined as effective lithological interface characteristics.

[0042] Step 23: Based on the muon absorption imaging data, a contour extraction algorithm (such as the Canny operator) is used to extract the morphological parameters of the density anomaly to obtain its morphological features. The morphological parameters include area, perimeter, and roundness. Anomalies with a roundness ≥ 0.6 and a closed shape correspond to ore-controlling rock bodies.

[0043] Step 24: Based on the muon absorption imaging data, K-means clustering algorithm and principal component analysis (PCA) algorithm are used to determine the clustering features.

[0044] Specifically, based on the numerical characteristics of density cross-sectional data, the K-means clustering algorithm is used to achieve automated data classification and core feature extraction, such as... Figure 3 As shown, the steps are as follows: (1) Perform neighborhood analysis on the density inversion section in the muon absorption imaging data to construct a multidimensional feature vector for each pixel.

[0045] Specifically, a 5×5 neighborhood analysis is performed on the density inversion cross-section to construct an 8-dimensional feature vector F=[ρ1, μ] for each pixel. ρ , σ ρ G, C, S, ρ min , ρ max This lays the foundation for data analysis; where ρ1 is the center pixel density, μ ρ σ is the mean density of the neighborhood. ρ Let G be the standard deviation of the neighborhood density, C be the gradient value, S be the roundness, and ρ be the area of ​​the neighborhood anomaly.max ρ is the maximum neighborhood density. min This represents the minimum neighborhood density.

[0046] (2) Perform principal component analysis on the multidimensional feature vector, calculate the feature covariance matrix, solve for the eigenvalues ​​and corresponding eigenvectors of the feature covariance matrix, and select the first N principal components as core features to reduce the dimensionality of the multidimensional feature vector, thereby obtaining the dimensionality-reduced feature vector. Wherein, N is the preset number of principal components.

[0047] Specifically, to simplify the eigenvectors and highlight the core information, principal component analysis is performed on the 8-dimensional eigenvectors to calculate the eigencovariance matrix. : ;in, A The total number of samples, For the first a The feature vector of each sample The mean of the feature vectors of all samples; For vectors The transpose of the matrix is ​​used to solve for the eigenvalues ​​and corresponding eigenvectors of the covariance matrix. The first three principal components (cumulative contribution rate ≥ 90%) are selected as core features to achieve feature dimensionality reduction.

[0048] (3) Based on the reduced feature vector of each pixel, the K-means clustering algorithm is used to perform clustering to obtain clustering features.

[0049] K-means clustering is based on dimensionality-reduced feature vectors. It iteratively calculates and minimizes the sum of squares for error (SSE) within each cluster to divide the data into k initial clusters. Compared to directly using 8-dimensional feature vectors, applying dimensionality-reduced feature vectors avoids the "curse of dimensionality" of high-dimensional data, reduces computation time, and minimizes the interference of redundant information on the clustering results, making the boundaries of the initial clusters clearer.

[0050] The classification principle of the K-means clustering algorithm is based on finding the initial cluster centers and the distance from each sample. c a The paradigm distance is calculated. The specific algorithm is as follows: First, randomly select k points as the initial cluster centers, denoted as . Secondly, calculate each sample c a The distance to each cluster center is determined and the cluster is assigned to the nearest cluster. : ;in, This represents the current iteration step. For the first There are several clusters. Then, for each cluster, the cluster centers (i.e., the mean vector) are recalculated using samples from that cluster: Finally, repeat the above steps T times. If the clustering result remains unchanged, then the iteration process ends.

[0051] Furthermore, the elbow method was used to determine the optimal k value, and the SSE-k curve was plotted. The k value corresponding to the curve "inflection point" (generally k=3~5, corresponding to different lithology or tectonic units) was selected. The clustering results were verified in combination with known borehole lithology data, and the cluster centers were adjusted to achieve a classification accuracy of ≥85%.

[0052] Step 203: Based on the gradient characteristics, continuity characteristics, morphological characteristics, and clustering characteristics, interpret the favorable faults, lithological interfaces, and ore-controlling rock masses to determine the spatial morphology and attribute parameters of the geology within the study area.

[0053] The gradient feature includes the density gradient of each pixel. The continuity feature includes the continuous extension length of the density variation band. The clustering feature includes multiple clusters.

[0054] In a specific application example, step 203 includes steps 31 to 33.

[0055] Step 31: Identify anomalous regions that meet the first preset condition based on the gradient features and clustering features, and determine the horizontal position, dip angle, and distribution morphology of fracture anomalies within the anomalous regions. Combined with regional mineralization patterns, determine mineralization-favorable fractures. The first preset condition is a density gradient greater than or equal to 0.3 g / (cm³). 3 ·m), and there are mutation boundaries between different clusters.

[0056] Specifically, using the lateral variation characteristics in the density cross-section as the core criterion, and integrating gradient anomaly and tectonic attitude analysis, the interpretation process is as follows: (1) Anomaly identification: Screening for anomaly regions that meet the following conditions: ① Density gradient G(x,y)≥0.3g / (cm 3 ·m) (abrupt transition zone); ② The clustering results show "discontinuity" (abrupt boundary between different clusters); ③ The corresponding low-resistivity tongue-shaped anomaly in the electrical resistivity data.

[0057] (2) Parameter determination: 1) Horizontal position: Take the coordinates of the central axis of the fracture anomaly and obtain the direction through linear fitting, with an error ≤1m.

[0058] 2) Dip and dip angle: Based on the fracture position offset at different depths, the dip angle α is calculated as tanα = ΔZ / ΔX. This is corrected by combining the fault plane orientation revealed by borehole drilling. The dip angle error is ≤5°. Where ΔZ is the depth difference and ΔX is the horizontal offset.

[0059] 3) Distribution morphology: Connect the fracture traces at each depth section to construct a three-dimensional fracture model and clarify its extension direction and pinch-out location in the concealed strata.

[0060] (3) Favorability evaluation: Based on the regional metallogenic regularity, if the fault strike is consistent with the known ore body strike and cuts the ore-bearing strata, it is determined to be a favorable fault for metallogenesis.

[0061] Step 32: Identify feature bands that satisfy the second preset condition based on the gradient characteristics, continuity characteristics, and clustering characteristics to determine the lithological interface. The second preset condition is a density gradient greater than or equal to 0.3 / (cm²). 3 ·m) and less than or equal to 0.8 g / (cm) 3 ·m), and the continuous extension length is greater than or equal to 20m, and the standard deviation within the cluster is less than the set standard deviation threshold.

[0062] Specifically, the interpretation is carried out using continuously extending zones of dense variation as the core marker, combined with regional geological continuity characteristics: (1) Interface recognition: Identify feature bands that meet the following conditions: ① Density gradient 0.3 / (cm) 3 ·m)≤G(x,y)≤0.8g / (cm 3 • m); ② The continuous extension length detected by Hough transform is ≥ 20 m; ③ The characteristics within the same geological unit in the clustering results are similar (within-cluster standard deviation ≤ 0.2 g / cm³). 3 ).

[0063] (2) Attribute division: 1) Lithology correspondence: Based on the density test values ​​of borehole cores, establish the correspondence between "density range and lithology".

[0064] 2) Regional extrapolation: Utilizing the ductility of lithological interfaces, the verified interface features of neighboring areas are extrapolated to the survey area, and the interpretation results are determined through cross-validation (interface attitude consistency of different depth sections ≥90%).

[0065] 3) Morphological classification: Based on the attitude of the interface, it is divided into horizontal (dip angle ≤ 10°), inclined (10° < dip angle < 80°), and nearly vertical (dip angle ≥ 80°), corresponding to different sedimentary or tectonic environments.

[0066] Step 33: Identify anomalous bodies that meet the third preset condition based on the morphological characteristics and clustering characteristics to determine the ore-controlling rock mass. The third preset condition is that the morphological characteristics are vein-like or mound-like, extending from deep to shallow, with a closed top interface or directly exposed to the surface, and the clusters are independent clusters with a density value greater than or equal to 0.2 g / cm³ compared to the surrounding rock. 3 .

[0067] Specifically, focusing on intrusive rock masses related to mineralization, identification is based on a comprehensive analysis of morphological characteristics and density properties: (1) Rock mass identification: Screen anomalies that meet the following characteristics: ① Vein-like morphology (length-to-width ratio ≥ 5:1) or mound-like morphology (roundness ≥ 0.7), extending from deep to shallow; ② Closed top interface or directly exposed on the surface (consistent with the rock mass outcrop point in the geological mapping); ③ Independent clusters in the clustering results, with a density value ≥ 0.2 g / cm³ different from the surrounding rock. 3 .

[0068] (2) Lithological differentiation: 1) Density calibration: Based on regional geological data, determine the density range of the ore-controlling rock mass (e.g., granodiorite 2.65 g / cm³). 3 -2.75g / cm 3 diabase 2.8 g / cm³ 3 -3.0g / cm 3 ).

[0069] 2) Multi-method verification: For anomalous bodies with unclear density characteristics, a comprehensive inference is made by combining gravity data (high gravity anomalies correspond to high-density rock bodies) and magnetic data (magnetic rock bodies correspond to magnetic anomalies) to exclude non-ore-controlling rock bodies (such as sedimentary conglomerate).

[0070] 3) Evaluation of mineralization correlation: If the rock mass intersects with the favorable fault for mineralization and there are signs of mineralization and alteration in the surrounding area (such as pyrite mineralization found in the borehole), it is determined to be a mineralization-controlling rock mass.

[0071] Step 204: Based on the geological data and the geophysical data, verify the reliability of the interpretation results of favorable faults, lithological interfaces and ore-controlling rock masses that form mineral deposits, and reinterpret the feature extraction process after adjusting it according to the reliability verification results.

[0072] This application enhances the reliability of the interpretation results through cross-validation of multiple sources, forming a closed-loop process of "Muse interpretation - data verification - result correction".

[0073] (1) Borehole verification: Select 3 to 5 representative boreholes in the survey area, compare the lithological interface and fracture location of the borehole core logging with the interpretation of the muzi, and calculate the degree of agreement (the degree of agreement error ≤ 2m is qualified). If it is not qualified, adjust the feature extraction parameters (such as gradient threshold) and reinterpret.

[0074] (2) Geological data verification: Compare the interpreted fault strike and rock mass distribution with the regional geological map and structural outline map to ensure consistency with the regional structural framework (strike deviation ≤ 10°).

[0075] (3) Verification of geophysical data: Compare the interpretation results of the Muzi with the electrical and gravity profiles. The fractures should correspond to low resistivity and low density anomalies, and the ore-controlling rock mass should correspond to anomalies that match the physical properties. The verification pass rate is ≥85% as the final interpretation result.

[0076] This application further outputs the interpretation results in the form of visual maps and text reports, providing direct support for mineral exploration. The results include: (1) Map results: ① Muzi density inversion cross section map (marking fractures, lithological interfaces, rock mass location and parameters); ② Three-dimensional model map of core geological targets (showing fracture distribution, rock mass morphology and lithological distribution); ③ Comparison map of "Miaozi interpretation-drilling verification" (marking verification points and errors).

[0077] (2) Data results: ① Interpretation of parameter tables (including quantitative data such as fracture strike, dip angle, rock mass density, and lithological interface depth); ② Clustering and PCA analysis reports (including eigenvectors, principal component contribution rates, and classification accuracy).

[0078] (3) Written results: Geological interpretation report, which explains the interpretation method, the reliability of the results and the prediction of favorable mineralization areas (clarifying the core basis of fault-controlled mineralization and rock mass mineralization).

[0079] In summary, this application, through a full-chain design of "multi-source data fusion, quantitative feature extraction, intelligent and accurate interpretation, and multi-source closed-loop verification," precisely addresses the shortcomings of traditional deep geological exploration technologies, forming four core advantages. Each advantage is realized based on specific technical points, as detailed below: (1) It has high detection accuracy and can accurately locate and characterize the parameters of hidden geological targets.

[0080] This advantage stems from three key technologies: "precise integration of multi-source data, quantitative feature extraction, and personalized interpretation parameter calibration," ensuring accuracy across the entire process from data foundation and feature recognition to target interpretation.

[0081] Multi-source data standardization and integration technology: A national geodetic coordinate system benchmark of 2000 was established, and precise correlation of muon data, borehole data, and geophysical data was achieved through ArcGIS spatial registration. The data matching error was controlled within ±0.5m (far superior to the matching error of more than 1m in traditional geophysical exploration). High-quality data integration provides accurate spatial reference for subsequent interpretation, avoiding interpretation deviations caused by data misalignment.

[0082] Quantization feature extraction system: On the one hand, visual interpretation experience is transformed into quantization parameters (such as density gradient threshold of 0.3~0.8 g / (cm³)) through Sobel operator, Hough transform, etc. 3•m), lithological interface continuity length ≥20m), avoiding the subjective errors of traditional visual interpretation; on the other hand, through the construction of 8-dimensional feature vectors and K-means+PCA intelligent algorithm, the objective classification of geological features is realized, with a clustering accuracy of ≥85%, providing accurate quantitative basis for target identification.

[0083] Personalized interpretation parameter calibration: Precise parameter criteria are established for favorable faults, lithological interfaces, and ore-controlling rock masses. For example, the fault strike is achieved with an error of ≤1m through linear fitting, and the dip angle is calculated by tanα=ΔZ / ΔX and corrected by borehole, with an error of ≤5°. The lithological interface is accurately divided through the correspondence between "density range and lithology" and cross-validation (consistency ≥90%) to ensure the accuracy of the target parameter characterization.

[0084] (2) High decoding efficiency, greatly reducing manual dependence and enabling batch processing.

[0085] This advantage stems from two key technologies: "intelligent algorithm fusion and standardized process design." By replacing the traditional manual interpretation mode with automated processing, efficiency is significantly improved.

[0086] K-means+PCA Intelligent Feature Extraction Algorithm: This algorithm introduces machine learning algorithms to automate feature extraction and data classification. By constructing 8-dimensional feature vectors and performing PCA dimensionality reduction (with the first 3 principal components having a cumulative contribution rate ≥90%), high-dimensional density cross-sectional data is transformed into low-dimensional core features. Then, K-means clustering is used to achieve batch grouping of data, replacing the traditional manual interpretation method of geologists on a cross-section basis, improving processing efficiency by more than 50%.

[0087] The entire process is standardized: It clearly defines the standardized steps of "data preparation - feature extraction - core interpretation - verification output," with each step having clear operating procedures and parameter thresholds (such as the 3σ criterion for noise removal and parameters for density inversion). This standardized design avoids the "personalized" experience differences inherent in traditional interpretation, enabling standardized batch processing of different survey areas and data, significantly reducing manual intervention costs and improving overall interpretation efficiency.

[0088] (3) The results are highly reliable, with traceable errors and verifiable results.

[0089] This advantage stems from two key technologies: "full-process data correction and multi-source cross-validation closed loop," which constructs a complete chain of "error control - result verification - parameter correction," ensuring the credibility of the results.

[0090] The end-to-end data correction model employs a two-stage preprocessing stage: noise removal and density inversion. Outliers are removed using the 3σ criterion, and accurate density inversion based on the muon absorption law is performed, enabling quantitative control of data errors. The density inversion accuracy is improved by 15%–20% compared to traditional methods, providing high-quality core data for subsequent interpretation and reducing errors at the source.

[0091] A multi-source cross-validation closed-loop system is established: a three-level validation mechanism is set up, consisting of "direct borehole validation - indirect geological data validation - collaborative geophysical data validation". This involves selecting 3-5 representative boreholes for comparative validation (depth error ≤ 2m is considered acceptable), comparing with regional geological mapping to ensure structural framework consistency (strike deviation ≤ 10°), and co-matching anomaly features with electrical resistivity and gravity data. A validation pass rate ≥ 85% is required to confirm the final results. This closed-loop validation effectively traces the source of errors (data errors or interpretation method errors) and corrects the results by adjusting feature extraction parameters, significantly improving the reliability of the results.

[0092] (4) It has wide applicability to deep areas and can overcome the detection limitations of traditional technologies.

[0093] This advantage stems from the technical design of "muse penetration characteristics + targeted interpretation scheme", which can effectively detect deep hidden areas that are difficult to cover by traditional technologies.

[0094] The natural penetrating advantage of muon imaging technology: Muons have extremely strong penetrating power and can penetrate strata from hundreds to thousands of meters deep. Compared with the limitations of traditional electrical resistivity methods in penetrating high-resistivity strata and the "point-like" coverage of borehole exploration, muons can achieve continuous detection of large-area deep regions and effectively capture the distribution morphology of targets such as deep mineralization faults and concealed ore-controlling rock masses.

[0095] Targeted interpretation scheme for deep targets: For deep geological targets (such as deep mineralized faults and concealed rock masses), the process is designed with a comprehensive criterion of "abrupt density change zone + cluster discontinuity + low resistivity anomaly". Combined with technologies such as three-dimensional fault model construction and rock mass morphology contour extraction (roundness ≥ 0.7, vein / mound morphology), it can accurately depict the three-dimensional distribution and attribute characteristics of deep targets, making up for the shortcomings of traditional technologies in detecting deep concealed targets.

[0096] In summary, the four core advantages are interconnected and mutually supportive, all stemming from the technical process's core design goals of "precision, automation, reliability, and versatility," ultimately achieving efficient and accurate detection of concealed geological targets and providing reliable technical support for deep mineral exploration.

[0097] Based on the same inventive concept, this application also provides a muon absorption imaging geological interpretation apparatus for implementing the muon absorption imaging geological interpretation method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations of one or more muon absorption imaging geological interpretation apparatus embodiments provided below can be found in the limitations of the muon absorption imaging geological interpretation method described above, and will not be repeated here.

[0098] In one exemplary embodiment, such as Figure 4 As shown, a muon absorption imaging geological interpretation device is provided, comprising: a data acquisition module 401, a feature extraction module 402, an interpretation module 403, and a verification module 404.

[0099] The data acquisition module 401 is used to acquire muon absorption imaging data, geological data and geophysical data of the study area.

[0100] The feature extraction module 402 is used to extract features based on the muon absorption imaging data using visual feature extraction methods and machine learning algorithms to obtain gradient features, continuity features, morphological features and clustering features.

[0101] The interpretation module 403 is used to interpret the favorable faults, lithological interfaces and ore-controlling rock masses of mineralization based on the gradient features, the continuity features, the morphological features and the clustering features, so as to determine the spatial morphology and attribute parameters of the geology in the study area.

[0102] The verification module 404 is used to verify the reliability of the interpretation results of favorable faults, lithological interfaces and ore-controlling rock masses based on the geological data and the geophysical data, and to re-interpret the feature extraction process after adjusting it according to the reliability verification results.

[0103] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores muon absorption imaging data, geological data, and geophysical data for the study area. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a muon absorption imaging geological interpretation method.

[0104] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0106] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0108] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0109] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0110] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, etc., and are not limited to these.

[0111] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0112] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for geological interpretation using muon absorption imaging, characterized in that, The muon absorption imaging geological interpretation method includes: Acquire muon absorption imaging data, geological data, and geophysical data for the study area; Based on the muon absorption imaging data, visual feature extraction methods and machine learning algorithms are used to extract features, resulting in gradient features, continuity features, morphological features, and clustering features. Based on the gradient characteristics, continuity characteristics, morphological characteristics, and clustering characteristics, the favorable faults for mineralization, lithological interfaces, and ore-controlling rock masses are interpreted to determine the spatial morphology and attribute parameters of the geology within the study area. Based on the geological data and geophysical data, the reliability of the interpretation results of favorable faults, lithological interfaces and ore-controlling rock masses was verified, and the feature extraction process was adjusted and reinterpreted based on the reliability verification results.

2. The muon absorption imaging geological interpretation method according to claim 1, characterized in that, Acquire muon absorption imaging data, geological data, and geophysical data for the study area, including: Acquire raw data of muon absorption imaging, geological data, and geophysical exploration data for the study area; A unified spatial coordinate system is established, and the raw data of muon absorption imaging, the raw geological data, and the raw geophysical data are spatially registered to obtain preliminary muon absorption imaging data, geological data, and geophysical data. The preliminary muon absorption imaging data are subjected to noise removal and geological density inversion in sequence to obtain muon absorption imaging data.

3. The muon absorption imaging geological interpretation method according to claim 1, characterized in that, The muon absorption imaging data includes muon flux data, density inversion section data, and geological body density data; the geological data includes borehole data and geological mapping data; and the geophysical data includes geophysical data and regional geological survey reports.

4. The muon absorption imaging geological interpretation method according to claim 1, characterized in that, Based on the muon absorption imaging data, visual feature extraction methods and machine learning algorithms are used to extract features, resulting in gradient features, continuity features, morphological features, and clustering features, including: Based on the muon absorption imaging data, the density gradient is calculated using the Sobel operator, and the density abrupt change zone is identified to obtain the gradient characteristics; Based on the muon absorption imaging data, the continuous extension length of the density change band is detected by Hough transform to obtain the continuity feature; Based on the muon absorption imaging data, a contour extraction algorithm is used to extract the morphological parameters of density anomalies to obtain morphological features; Based on the muon absorption imaging data, K-means clustering algorithm and principal component analysis algorithm were used to determine the clustering characteristics.

5. The muon absorption imaging geological interpretation method according to claim 4, characterized in that, Based on the muon absorption imaging data, K-means clustering and principal component analysis algorithms were used to determine the clustering features, including: Neighborhood analysis is performed on the density inversion cross-section in the muon absorption imaging data to construct a multidimensional feature vector for each pixel. Principal component analysis is performed on the multidimensional feature vector to calculate the feature covariance matrix, and the eigenvalues ​​and corresponding eigenvectors of the feature covariance matrix are solved. The first N principal components are selected as core features to reduce the dimensionality of the multidimensional feature vector, resulting in a dimensionality-reduced feature vector; where N is the preset number of principal components. Based on the dimensionality-reduced feature vector of each pixel, the K-means clustering algorithm is used to perform clustering to obtain cluster features.

6. The muon absorption imaging geological interpretation method according to claim 1, characterized in that, The gradient feature includes the density gradient of each pixel; the continuity feature includes the continuous extension length of the density change band; the clustering feature includes multiple clusters. Based on the gradient characteristics, continuity characteristics, morphological characteristics, and clustering characteristics, the favorable faults, lithological interfaces, and ore-controlling rock masses for mineralization are interpreted, including: Based on the gradient features and clustering features, abnormal regions satisfying the first preset condition are identified, and the horizontal position, dip angle, and distribution morphology of fracture anomalies within the abnormal regions are determined. Combined with regional mineralization patterns, favorable mineralization fractures are identified. The first preset condition is a density gradient greater than or equal to 0.3 g / (cm³). 3 ·m), and there are mutation boundaries between different clusters; Based on the gradient characteristics, continuity characteristics, and clustering characteristics, feature bands satisfying a second preset condition are identified to determine the lithological interface; the second preset condition is a density gradient greater than or equal to 0.3 / (cm²). 3 ·m) and less than or equal to 0.8 g / (cm) 3 ·m), and the continuous extension length is greater than or equal to 20m, and the standard deviation within the cluster is less than the set standard deviation threshold; Based on the morphological characteristics and clustering characteristics, anomalies meeting the third preset condition are identified to determine the ore-controlling rock mass; the third preset condition is that the morphological characteristics are vein-like or mound-like, extending from deep to shallow, with a closed top interface or directly exposed to the surface, and the clusters are independent clusters with a density value greater than or equal to 0.2 g / cm³ compared to the surrounding rock. 3 .

7. A muon absorption imaging geological interpretation device, characterized in that, The muon absorption imaging geological interpretation device performs the muon absorption imaging geological interpretation method according to any one of claims 1-6, and the muon absorption imaging geological interpretation device comprises: The data acquisition module is used to acquire muon absorption imaging data, geological data, and geophysical data of the study area; The feature extraction module is used to extract features from the muon absorption imaging data using visual feature extraction methods and machine learning algorithms to obtain gradient features, continuity features, morphological features and clustering features. The interpretation module is used to interpret the favorable faults, lithological interfaces and ore-controlling rock masses based on the gradient features, the continuity features, the morphological features and the clustering features, so as to determine the spatial morphology and attribute parameters of the geology in the study area. The verification module is used to verify the reliability of the interpretation results of favorable faults, lithological interfaces and ore-controlling rock masses based on the geological data and the geophysical data, and to reinterpret the feature extraction process after adjusting it according to the reliability verification results.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the muon absorption imaging geological interpretation method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the muon absorption imaging geological interpretation method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the muon absorption imaging geological interpretation method as described in any one of claims 1-6.

Images