A method and system for predicting mineral prospecting targets based on geological three-dimensional modeling

Abstract

The present invention discloses a method and system for predicting mineral exploration targets based on geological three-dimensional modeling, which relates to the field of mineral resource exploration technology, including: obtaining geological, geophysical, geochemical and remote sensing data of the target area and preprocessing them to generate a modeling data set for geological modeling; constructing a lithology classification model by combining a three-dimensional geological model with deep learning, extracting shallow lithology characteristics to predict the deep lithology of the target area; screening mineralization factors based on the predicted results of the deep lithology of the target area, deep geophysical data and the three-dimensional geological model, and generating a mineralization prediction factor set; establishing a mineral exploration prediction model based on a graph convolutional network, importing the mineralization prediction factor set to obtain the mineralization distribution prediction results, and performing three-dimensional mineral exploration target area delineation. The present invention predicts deep lithology and strata through multi-source geological data and geological three-dimensional modeling, and uses a graph convolutional neural network for target area delineation, thereby improving the efficiency and accuracy of mineral exploration target area prediction and reducing exploration costs.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral resource exploration, and more specifically, to a method and system for predicting mineral prospecting targets based on geological three-dimensional modeling. Background Art

[0002] Target prediction is a critical step in mineral exploration. It aims to identify potential mineral-rich areas using multi-source data, including geological, geophysical, and geochemical data. Accurate target prediction can significantly reduce exploration costs and improve prospecting efficiency, significantly impacting the development and utilization of mineral resources. Traditional methods for prospecting target prediction rely primarily on the experience and manual analysis of geologists, including geological mapping, geophysical exploration, and geochemical exploration. While effective to a certain extent, these methods suffer from limitations such as high subjectivity, low efficiency, and limited accuracy.

[0003] With advances in computer technology and data science, modern prospecting target prediction technology is increasingly becoming data-driven and intelligent, primarily encompassing geographic information systems (GIS), machine learning and deep learning, big data, and cloud computing. Furthermore, with the surge in demand for mineral resources and the deepening of exploration efforts, prospecting has shifted from searching for shallow ore bodies to searching for deep, concealed ore bodies. The use of three-dimensional cube models for resource prediction and evaluation of concealed ore bodies has become a hot topic in mineral exploration. Therefore, combining artificial intelligence (AI) technology with three-dimensional cube models for high-precision prediction of concealed ore resources is a pressing issue. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes a prospecting target area prediction method and system based on geological three-dimensional modeling. Deep lithologic strata are predicted through multi-source data and geological three-dimensional modeling, and target areas are delineated using a graph convolutional neural network combined with preferred mineralization prediction factors, providing efficient and accurate technical support for mineral resource exploration.

[0005] A first aspect of the present invention provides a method for predicting prospecting target areas based on geological three-dimensional modeling, comprising the following steps:

[0006] Acquiring geological, geophysical, geochemical, and remote sensing data of the target area, preprocessing the acquired data to generate a modeling data set, and performing geological modeling of the target area based on the modeling data set to generate a three-dimensional geological model;

[0007] A lithology classification model is constructed by combining the three-dimensional geological model with deep learning to extract shallow lithology characteristics of the target area, and the shallow lithology characteristics are used to predict the deep lithology of the target area;

[0008] Screening metallogenic factors based on the predicted results of deep lithology in the target area, deep geophysical data and 3D geological models, and constructing the optimal metallogenic factor combination to generate a metallogenic prediction factor set;

[0009] A prospecting prediction model is established and trained based on a graph convolutional network, the mineralization prediction factor set is imported into the prospecting prediction model to obtain the mineralization distribution prediction result, and three-dimensional prospecting target area is delineated.

[0010] In this solution, geological, geophysical, geochemical and remote sensing data are preprocessed to generate a modeling dataset. Based on the modeling dataset, geological modeling of the target area is carried out. Specifically:

[0011] Based on the geographic information of the target area, historical geological survey data and historical exploration engineering data are obtained in the area, geological, geophysical, geochemical and remote sensing data are screened, and the screened data are standardized, denoised and normalized;

[0012] Generate a modeling data set from the preprocessed data, extract fault data based on the modeling data set, construct a three-dimensional geological entity model corresponding to the lithologic strata of the target area based on the fault data, extend and trim the constructed three-dimensional geological entity model using stratum boundaries, and determine difference range constraints for model interpolation;

[0013] querying the maximum and minimum coordinates of the three-dimensional geological entity model to determine the block size, using the block size to grid the three-dimensional geological entity model, obtaining the three-dimensional geological block model and creating attributes of the three-dimensional geological block model based on data in the modeling data set;

[0014] A three-dimensional geological model corresponding to the lithologic structure of the shallow strata in the target area is generated based on the constructed three-dimensional geological entity model and the three-dimensional geological block model.

[0015] In this solution, a lithology classification model is constructed by combining the three-dimensional geological model with deep learning to extract the shallow lithology characteristics of the target area. The shallow lithology characteristics are then used to predict the deep lithology of the target area. Specifically:

[0016] Slicing the three-dimensional geological model in two dimensions to obtain a three-dimensional geological model cross-section with geophysical data attribute labels, and establishing a training set and a validation set based on the three-dimensional geological model cross-section with geophysical data attribute labels and shallow lithology;

[0017] Constructing a lithologic classification model, using the training set for model training, introducing dilated convolution with different dilation coefficients to convolve the three-dimensional geological model profile to obtain feature maps of different scales, matching and encoding the feature maps of different scales with stratum lithologic labels, and obtaining shallow lithologic characteristics under different geophysical data attribute labels;

[0018] Each shallow lithologic feature matrix is processed by multi-head attention. In each attention head, mask estimation is introduced to obtain attention weights, and the shallow lithologic feature matrix is weighted using the obtained attention weights.

[0019] Multi-scale context aggregation is performed on the weighted shallow lithologic features. Through the split-transform-merge strategy, the weighted shallow lithologic features are transformed using the split standard convolution combined with different dilation coefficients to capture contextual information at different scales. The contextual information at different scales is then merged through concatenation and standard convolution.

[0020] Importing the fused context information into the fully connected layer to predict the corresponding stratum lithology label, and using the validation set to verify the predicted stratum lithology label to obtain a trained lithology classification model;

[0021] The three-dimensional geological model profile corresponding to each deep geophysical data of the target area is imported into the trained lithology classification model to obtain the distribution of deep lithology in the target area.

[0022] In this plan, mineralization factors are screened based on the predicted results of deep lithology in the target area, deep geophysical data and three-dimensional geological models, specifically:

[0023] Obtain the type of mineral deposits in the target area for prospecting, and use big data retrieval to obtain completed geological, geophysical, geochemical and prospecting work case data based on the mineral deposit type. Use deep lithology, deep geophysical data and three-dimensional geological models of the target area to obtain similar case data based on similarity calculation;

[0024] Using the Pearson correlation coefficient, the ore-controlling geological conditions that meet the preset correlation standard are screened from the obtained similar case data. The metallogenic factors in the case data are obtained based on the screened ore-controlling geological conditions. The information contribution of each metallogenic factor to the prospecting prediction is calculated, and the metallogenic factors are preliminarily screened based on the information.

[0025] The SVM model is trained by the initially screened metallogenic factors to perform classification prediction tasks, and several kernel functions are replaced during the training process to obtain the mean square error of the classification prediction tasks of different metallogenic factors under multiple kernel functions, and the importance scores of different metallogenic factors are generated according to the mean square error;

[0026] The metallogenic factors are sorted using the importance scores, a preset number of metallogenic factors are selected according to the sorting results, and redundant metallogenic factors are eliminated through collinearity detection.

[0027] In this scheme, the optimal metallogenic factor combination is constructed to generate a metallogenic prediction factor set, specifically:

[0028] Obtain the metallogenic factors corresponding to the ore-controlling geological conditions, randomly generate metallogenic factor combinations to construct the initial population, use the improved dung beetle optimization algorithm to optimize the metallogenic factor combinations, and introduce chaotic mapping into the initial population to optimize the initial dung beetle positions;

[0029] An objective function is constructed based on the classification accuracy and characteristic dimension of the mineralization factor combination, the objective function is positively associated with a fitness function, and the positions of dung beetle individuals in different behavioral states are updated according to the fitness function;

[0030] A reverse learning strategy and an adaptive nonlinear step-size control strategy are added to the position update process of dung beetle individuals in different behavioral states. The reverse learning strategy obtains the reverse position of each dung beetle individual and combines the chaotic population and the reverse population to solve the position information of the dung beetle individual. The adaptive nonlinear step-size control strategy adaptively controls the search step size according to the number of iterations to finely control the position update of the dung beetle individual.

[0031] The random coefficient is combined with the reverse learning strategy and the adaptive nonlinear step-size control strategy. When the random coefficient is less than a preset threshold, the adaptive nonlinear step-size control strategy is used to update the position. Otherwise, the reverse learning strategy is used to update the position.

[0032] After iterative optimization, the optimal solution output by the improved dung beetle optimization algorithm is obtained, and the optimal metallogenic factor combination corresponding to each ore-controlling geological condition is determined according to the optimal solution as the metallogenic prediction factor set.

[0033] In this solution, a prospecting prediction model is established and trained based on a graph convolutional network, and the mineralization prediction factor set is imported into the prospecting prediction model to obtain the mineralization distribution prediction results, specifically:

[0034] Extract characteristic variable values from completed geological, geophysical, geochemical and prospecting work data based on the set of metallogenic prediction factors, obtain the relationship between the characteristic variable values of different metallogenic prediction factors and the metallogenic distribution, construct a graph representation of the metallogenic distribution and different metallogenic prediction factors, and extract the adjacency matrix;

[0035] At the same time, based on the example data and the intersection of the three-dimensional geological model of ore body distribution and the three-dimensional geological models of different metallogenic factors, the characteristic variable value range of the ore body distribution corresponding to different metallogenic prediction factors is obtained, and the probability distribution function of different metallogenic prediction factors is obtained;

[0036] Using a graph convolutional network to establish a prospecting prediction model to learn the graph representation, updating node information according to the adjacency matrix and the state update weight matrix, and obtaining an updated node feature vector;

[0037] Obtaining characteristic variable values of the target area according to the metallogenic prediction factor set, obtaining probability distribution values corresponding to the characteristic variable values of the target area through probability distribution functions of different metallogenic prediction factors, and processing the adjacency matrix using the probability distribution values to obtain a dynamic adjacency matrix;

[0038] The node information is updated according to the dynamic adjacency matrix and the state update weight matrix to obtain a final node feature vector, which is then imported into a fully connected layer to obtain a mineralization distribution prediction result.

[0039] In this plan, the corresponding controlling geological conditions and mineralization laws are obtained through the types of mineral deposits in the target area, and the three-dimensional prospecting target area is delineated according to the mineralization distribution prediction results. The delineated three-dimensional prospecting target area is corrected using the controlling geological conditions and mineralization laws corresponding to the mineral deposit type, and a three-dimensional visual expression is performed.

[0040] The second aspect of the present invention provides a prospecting target area prediction system based on geological three-dimensional modeling, which includes a modeling data acquisition unit, a three-dimensional geological modeling unit, a deep lithology classification unit, a prospecting prediction unit and a deep prospecting target area delineation unit;

[0041] The modeling data acquisition unit is responsible for acquiring geological, geophysical, geochemical and remote sensing data of the target area and performing preprocessing to generate a modeling data set;

[0042] The three-dimensional geological modeling unit is responsible for modeling the shallow geological entities and attributes of the target area according to the modeling data set to obtain a three-dimensional geological model;

[0043] The deep lithology classification unit is responsible for constructing a lithology classification model based on a deep learning algorithm and a three-dimensional geological model, extracting shallow lithology characteristics of the target area, and predicting the deep lithology of the target area;

[0044] The prospecting prediction unit is responsible for screening metallogenic factors based on the predicted results of deep lithology in the target area, deep geophysical data and three-dimensional geological models, and constructing a metallogenic prediction factor set, establishing a prospecting prediction model and training it, and importing the metallogenic prediction factor set into the prospecting prediction model to obtain a metallogenic distribution prediction result;

[0045] The deep prospecting target area delineation unit is responsible for delineating the three-dimensional prospecting target area based on the mineralization distribution prediction results to realize the visualization of the prospecting target area.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention integrates multi-source data such as geology, geophysics, geochemistry, and remote sensing to construct a three-dimensional geological model, intuitively displaying the underground geological structure and ore body distribution, predicting deep lithologic strata through multi-source data and geological three-dimensional modeling, and using a graph convolutional neural network combined with preferred mineralization prediction factors to delineate target areas, thereby reducing the traditional manual prospecting's reliance on experience, realizing the automation and intelligence of prospecting target area prediction, significantly improving the efficiency and accuracy of prospecting target area prediction, and reducing exploration costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or exemplary descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to these drawings without paying any creative work.

[0049] Figure 1 A flow chart of a method for predicting prospecting target areas based on geological three-dimensional modeling is shown;

[0050] Figure 2 A flow chart for constructing a lithologic classification model to predict deep lithologic characteristics of a target area is shown;

[0051] Figure 3 A flow chart showing the use of prospecting prediction models to obtain mineralization distribution prediction results;

[0052] Figure 4 The block diagram of the prospecting target area prediction system based on geological three-dimensional modeling is shown. DETAILED DESCRIPTION

[0053] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0055] Figure 1 A flow chart of a method for predicting mineral exploration targets based on geological three-dimensional modeling is shown.

[0056] like Figure 1 As shown, the first embodiment of the present invention provides a method for predicting prospecting target areas based on geological three-dimensional modeling, including:

[0057] S102, acquiring geological, geophysical, geochemical, and remote sensing data of a target area, preprocessing the acquired data to generate a modeling data set, and performing geological modeling of the target area based on the modeling data set to generate a three-dimensional geological model;

[0058] S104, constructing a lithology classification model by combining the three-dimensional geological model with deep learning, extracting shallow lithology characteristics of the target area, and using the shallow lithology characteristics to predict deep lithology of the target area;

[0059] S106, screening metallogenic factors based on the predicted results of deep lithology of the target area, deep geophysical data and three-dimensional geological model, and constructing the best metallogenic factor combination to generate a metallogenic prediction factor set;

[0060] S108, establishing and training a prospecting prediction model based on a graph convolutional network, importing the mineralization prediction factor set into the prospecting prediction model to obtain a mineralization distribution prediction result, and performing three-dimensional prospecting target area delineation.

[0061] It should be noted that, based on the geographic information of the target area, historical geological survey data and historical exploration engineering data in the region are obtained, including regional geological survey, gravity measurement, geomagnetic measurement, gravity and magnetic profiles, magnetotelluric sounding, phase induced polarization measurement and drilling data; geological, geophysical, geochemical and remote sensing data are screened, and the screened data are standardized, denoised and normalized; a modeling data set is generated through the preprocessed data, fault data is extracted according to the modeling data set, fault data is extracted from MapGIS maps such as geological mineral maps, remote sensing structural interpretation maps, and electrical geological interpretation profiles, MapGIS two-dimensional line files are converted into GOCAD three-dimensional line string files, and the contour lines of the three-dimensional line string files are spliced to form triangular patch files to construct a three-dimensional geological entity model corresponding to the lithologic strata of the target area. The constructed three-dimensional geological entity model is extended and trimmed using the stratum boundary, and the difference range constraint is determined for model interpolation; the maximum and minimum coordinates of the three-dimensional geological entity model are queried to determine the block size, and the three-dimensional geological entity model is gridded using the block size to obtain the three-dimensional geological block model and create the attributes of the three-dimensional geological block model based on the data in the modeling data set; and a three-dimensional geological model corresponding to the shallow stratum lithologic structure of the target area is generated based on the constructed three-dimensional geological entity model and the three-dimensional geological block model.

[0062] Figure 2 A flow chart for constructing a lithologic classification model to predict deep lithologic characteristics of a target area is shown.

[0063] According to an embodiment of the present invention, a lithology classification model is constructed by combining the three-dimensional geological model with deep learning to extract shallow lithology characteristics of the target area. The shallow lithology characteristics are then used to predict the deep lithology of the target area. Specifically,

[0064] S202, performing two-dimensional slicing on the three-dimensional geological model to obtain a three-dimensional geological model cross-section with geophysical data attribute labels, and establishing a training set and a validation set based on the three-dimensional geological model cross-section with geophysical data attribute labels and shallow lithology;

[0065] S204: Constructing a lithologic classification model, using the training set to perform model training, introducing dilation convolution with different dilation coefficients to convolve the 3D geological model profile to obtain feature maps of different scales, matching and encoding the feature maps of different scales with stratum lithologic labels, and obtaining shallow lithologic characteristics under different geophysical data attribute labels;

[0066] S206, processing each shallow lithologic feature matrix through multi-head attention, introducing mask estimation in each attention head to obtain attention weights, and using the obtained attention weights to weight the shallow lithologic feature matrix;

[0067] S208, performing multi-scale context aggregation on the weighted shallow lithologic features. Using a split-transform-merge strategy, the weighted shallow lithologic features are transformed using the split standard convolution combined with different dilation coefficients to capture contextual information at different scales. The contextual information at different scales is then merged through concatenation and standard convolution.

[0068] S210, importing the fused context information into the fully connected layer to predict the corresponding stratum lithology label, using the validation set to verify the predicted stratum lithology label, and obtaining a trained lithology classification model;

[0069] S212, importing the three-dimensional geological model profile corresponding to each deep geophysical data of the target area into the trained lithology classification model to obtain the distribution of deep lithology in the target area.

[0070] It should be noted that the lithologic classification model was built based on the DeeplabV3+ network architecture, replacing the original backbone network Xception with the pre-trained lightweight MobileNetV2. In the encoder, dilated convolutions were introduced with different dilation coefficients to convolve the 3D geological model profiles to obtain feature maps of different scales, extracting and aggregating features from different perspectives. In the decoding part, the encoder output was first upsampled, and each shallow lithologic feature matrix was processed using multi-head attention. Mask estimation was added to the self-attention mechanism to calculate the attention weights. , , represents the number of feature items, represents the matrix dimension, Represents the mask value, represents the query vector, represents the key vector, Represents a value vector; and fuses shallow lithologic features extracted from the backbone network. In multi-scale feature fusion, the standard convolution kernel is split into several sub-kernels, each with fewer output channels. Each sub-kernel transforms shallow lithologic features differently using different expansion coefficients, capturing contextual information at different scales. The contextual information from different receptive fields is ultimately merged through concatenation and standard convolution operations, effectively capturing multi-scale contextual information. Because the mineral composition of different lithologies leads to differences in magnetic susceptibility and apparent resistivity, and because different mineral compositions also result in different formation densities for different lithologies, leading to differences in regional gravity anomaly effects for those lithologies, the fully connected layer of the lithologic classification model is used to construct a mapping between geophysical data and lithologies, enabling lithologic prediction.

[0071] It should be noted that the type of mineral deposit for prospecting in the target area is obtained, and big data retrieval is used to obtain completed geological, geophysical, geochemical and prospecting work example data based on the mineral deposit type. The deep lithology, deep geophysical data and three-dimensional geological model of the target area are used to obtain similar example data based on similarity calculation; the Pearson correlation coefficient is used to screen the mineral-controlling geological conditions that meet the preset correlation standards from the obtained similar example data. The preferred mineral-controlling geological conditions include stratigraphic conditions, structural conditions, geophysical conditions, geochemical conditions, remote sensing anomaly conditions, etc. The mineralization factors in the example data are obtained according to the screened mineral-controlling geological conditions. The preferred mineralization factors include apparent resistivity distribution characteristics, gravity distribution characteristics, fault distance field, geochemical anomaly distribution, remote sensing anomaly, geomagnetic anomaly distribution, etc. The amount of information contributed by each mineralization factor to prospecting prediction is calculated, and the mineralization factors are preliminarily screened by the information amount; the information amount model can effectively reflect the relevance of the selected mineralization factors and their classification intervals to prospecting prediction. When the information value is greater than 0, it indicates that prospecting prediction is promoted within the classification interval of the mineralization factor; when the information value is less than 0, it indicates that prospecting prediction is suppressed within the classification interval of the mineralization factor. The SVM model is trained by the initially screened mineralization factors to perform classification prediction tasks. The SVM uses a kernel function to project the data in the existing dimension into a high-dimensional feature space, and performs the classification task through the distance of the hyperplane of the sample. Several kernel functions are replaced during the training process. Commonly used kernel functions include polynomial kernel functions and RBF kernel functions. The mean square error of the classification prediction task of different mineralization factors under multiple kernel functions is obtained, and the importance scores of different mineralization factors are generated according to the mean square error; the mineralization factors are sorted using the importance scores, and a preset number of mineralization factors are selected according to the sorting results, and redundant mineralization factors are eliminated through collinearity detection.

[0072] The dung beetle optimization algorithm is a heuristic optimization algorithm based on the behavior of dung beetles in nature, which simulates the process of dung beetles in searching, rolling and burying dung balls. By simulating the rolling, competition, reproduction and other behaviors of dung beetles, the search and optimization of the solution space are realized. The metallogenic factors corresponding to the ore-controlling geological conditions are obtained, and the metallogenic factor combinations are randomly generated to construct the initial population. The improved dung beetle optimization algorithm is used to optimize the metallogenic factor combinations. The Tent chaotic mapping function is used to introduce chaotic mapping in the initial population to optimize the initial dung beetle positions, so that the initial population distribution is more uniform; according to the SVM model, the mean square error is obtained through n-fold cross-training to generate the classification accuracy corresponding to the mineralization factor combination, and the characteristic dimension corresponding to the mineralization factor combination is obtained according to the sum of the dimensions of the mineralization factors. By maximizing the classification accuracy of the mineralization factor combination and the maximum The characteristic dimension of the combination of mineralization factors is minimized to construct an objective function, and the objective function is used to positively associate with the fitness function. The larger the objective function value is, the larger the fitness value is. The positions of dung beetle individuals in different behavioral states are updated according to the fitness function; in the position update process of dung beetle individuals in rolling, competing, and breeding behavioral states, a reverse learning strategy and an adaptive nonlinear step-size control strategy are added. The reverse learning strategy obtains the reverse position of each dung beetle individual, and the chaotic population and the reverse population are merged to solve the position information of the dung beetle individual, thereby further improving the diversity of the population. The dung beetle individuals in the reverse position Expressed as , Indicates the upper and lower limits of the individual dimensions of dung beetles, Represents the individual dung beetle after chaotic mapping. The adaptive nonlinear step size control strategy adaptively controls the search step size according to the number of iterations. As the number of iterations increases, using a smaller step size is conducive to fine-tuning the exploration of local details and controlling the position update of the dung beetle individual. The step size in the adaptive nonlinear step size control strategy is The calculation is expressed as: , represents the original fixed step size, represents the incomplete function, 、 Represents the current number of iterations and the maximum number of iterations. A random coefficient is combined with a reverse learning strategy and an adaptive nonlinear step-size control strategy. The preferred random coefficient threshold is set to 0.5. When the random coefficient is less than the preset threshold, the adaptive nonlinear step-size control strategy is used to update the position. Otherwise, the reverse learning strategy is used to update the position. The global optimal position and fitness value are recorded to determine whether the maximum number of iterations has been exceeded. If so, the optimization ends. After iterative optimization, the optimal solution output by the improved dung beetle optimization algorithm is obtained. Based on the optimal solution, the optimal metallogenic factor combination corresponding to each ore-controlling geological condition is determined as the metallogenic prediction factor set.

[0073] Figure 3A flow chart showing the use of prospecting prediction models to obtain mineralization distribution prediction results.

[0074] According to an embodiment of the present invention, a prospecting prediction model is established and trained based on a graph convolutional network, and the mineralization prediction factor set is imported into the prospecting prediction model to obtain a mineralization distribution prediction result, specifically:

[0075] S302, extracting characteristic variable values from completed geological, geophysical, geochemical, and prospecting work example data based on the metallogenic prediction factor set, obtaining the relationship between the characteristic variable values of different metallogenic prediction factors and the metallogenic distribution, constructing a graph representation of the metallogenic distribution and different metallogenic prediction factors, and extracting an adjacency matrix;

[0076] S304, simultaneously obtaining characteristic variable value ranges of different metallogenic prediction factors corresponding to the ore body distribution based on the example data and the intersection of the three-dimensional geological model of the ore body distribution and the three-dimensional geological models of different metallogenic factors, and obtaining probability distribution functions of the different metallogenic prediction factors;

[0077] S306, using a graph convolutional network to establish a prospecting prediction model to learn the graph representation, updating node information according to the adjacency matrix and the state update weight matrix, and obtaining an updated node feature vector;

[0078] S308, obtaining characteristic variable values of the target area according to the metallogenic prediction factor set, obtaining probability distribution values corresponding to the characteristic variable values of the target area through probability distribution functions of different metallogenic prediction factors, and processing the adjacency matrix using the probability distribution values to obtain a dynamic adjacency matrix;

[0079] S310, updating the node information according to the dynamic adjacency matrix and the state update weight matrix, obtaining a final node feature vector, and importing the final node feature vector into a fully connected layer to obtain a mineralization distribution prediction result.

[0080] It should be noted that the relationship between the characteristic variable values of different metallogenic prediction factors and the metallogenic distribution is obtained by analyzing the example data. The metallogenic prediction factors and the metallogenic distribution are used as nodes, and the obtained relationships are used as edge structures to construct a graph representation of the metallogenic distribution and different metallogenic prediction factors. The graph representation is learned using a graph convolutional network, and the correlation information between different metallogenic prediction factors and the metallogenic distribution is obtained based on the relationship matrix and graph convolution. According to the three-dimensional geological model interpolated by different data of the example data, the three-dimensional geological model of the ore body distribution and the three-dimensional geological models of different metallogenic factors are intersected, and the intersection area of the ore body distribution is assigned a value 1 operation. The assigned area is obtained from the three-dimensional geological model of different metallogenic factors, and the corresponding characteristic variable value range is read. The probability distribution function of the different metallogenic prediction factors is obtained according to the value distribution law of the characteristic variable value range. The characteristic variable value of the target area is obtained according to the lithological distribution and geological, geophysical, geochemical and remote sensing data of the deep strata in the target area. The probability distribution function of the different metallogenic prediction factors is used to obtain the probability distribution value corresponding to the characteristic variable value of the target area. The probability distribution value is processed on the adjacency matrix using the probability distribution value to obtain a dynamic adjacency matrix, so that the prospecting task in the target area has an exclusive adjacency matrix, the ability of the prospecting prediction model to represent the correlation between different metallogenic prediction factors and metallogenic distribution is improved, the correlation information of the correlation between the metallogenic distribution of different metallogenic prediction factors is adaptively updated, and a dynamic adjacency matrix is set to reduce the overfitting risk of the model. The corresponding controlling geological conditions and mineralization laws are obtained through the type of mineral deposits in the target area. The boundaries of the prospecting target area are determined according to the results of mineralization distribution prediction, and the three-dimensional prospecting target area is delineated. With full reference to the relevant results of surface geological exploration, the controlling geological conditions and mineralization laws corresponding to the mineral deposit type are used to correct the delineated three-dimensional prospecting target area to obtain the deep prospecting target area in the target area and perform three-dimensional visualization.

[0081] Figure 4 The block diagram of the prospecting target area prediction system based on geological three-dimensional modeling is shown.

[0082] The second embodiment of the present invention provides a prospecting target area prediction system 4 based on geological three-dimensional modeling, which includes a modeling data acquisition unit 401, a three-dimensional geological modeling unit 402, a deep lithology classification unit 403, a prospecting prediction unit 404 and a deep prospecting target area delineation unit 405;

[0083] The modeling data acquisition unit is responsible for acquiring geological, geophysical, geochemical and remote sensing data of the target area and performing preprocessing to generate a modeling data set;

[0084] The three-dimensional geological modeling unit is responsible for modeling the shallow geological entities and attributes of the target area according to the modeling data set to obtain a three-dimensional geological model;

[0085] The deep lithology classification unit is responsible for constructing a lithology classification model based on a deep learning algorithm and a three-dimensional geological model, extracting shallow lithology characteristics of the target area, and predicting the deep lithology of the target area;

[0086] The prospecting prediction unit is responsible for screening metallogenic factors based on the predicted results of deep lithology in the target area, deep geophysical data and three-dimensional geological models, and constructing a metallogenic prediction factor set, establishing a prospecting prediction model and training it, and importing the metallogenic prediction factor set into the prospecting prediction model to obtain a metallogenic distribution prediction result;

[0087] The deep prospecting target area delineation unit is responsible for delineating the three-dimensional prospecting target area based on the mineralization distribution prediction results to realize the visualization of the prospecting target area.

[0088] The third embodiment of the present invention provides a computer-readable storage medium, which includes a prospecting target area prediction method program based on geological three-dimensional modeling. When the prospecting target area prediction method program based on geological three-dimensional modeling is executed by a processor, it implements the steps of the prospecting target area prediction method based on geological three-dimensional modeling.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0090] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0091] Alternatively, if the integrated units described above are implemented as software functional units and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0092] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for predicting prospecting target areas based on geological three-dimensional modeling, characterized in that: The following steps are involved: Acquiring geological, geophysical, geochemical, and remote sensing data of the target area, preprocessing the acquired data to generate a modeling data set, and performing geological modeling of the target area based on the modeling data set to generate a three-dimensional geological model; A lithology classification model is constructed by combining the three-dimensional geological model with deep learning to extract shallow lithology characteristics of the target area, and the shallow lithology characteristics are used to predict the deep lithology of the target area; Screening metallogenic factors based on the predicted results of deep lithology in the target area, deep geophysical data and 3D geological models, and constructing the optimal metallogenic factor combination to generate a metallogenic prediction factor set; Establishing and training a prospecting prediction model based on a graph convolutional network, importing the mineralization prediction factor set into the prospecting prediction model to obtain a mineralization distribution prediction result, and performing three-dimensional prospecting target area delineation; Construct the optimal metallogenic factor combination to generate the metallogenic prediction factor set, specifically: Obtain the metallogenic factors corresponding to the ore-controlling geological conditions, randomly generate metallogenic factor combinations to construct the initial population, use the improved dung beetle optimization algorithm to optimize the metallogenic factor combinations, and introduce chaotic mapping into the initial population to optimize the initial dung beetle positions; An objective function is constructed based on the classification accuracy and characteristic dimension of the mineralization factor combination, the objective function is positively associated with a fitness function, and the positions of dung beetle individuals in different behavioral states are updated according to the fitness function; A reverse learning strategy and an adaptive nonlinear step-size control strategy are added to the position update process of dung beetle individuals in different behavioral states. The reverse learning strategy obtains the reverse position of each dung beetle individual and combines the chaotic population and the reverse population to solve the position information of the dung beetle individual. The adaptive nonlinear step-size control strategy adaptively controls the search step size according to the number of iterations to finely control the position update of the dung beetle individual. The random coefficient is combined with the reverse learning strategy and the adaptive nonlinear step-size control strategy. When the random coefficient is less than a preset threshold, the adaptive nonlinear step-size control strategy is used to update the position. Otherwise, the reverse learning strategy is used to update the position. After iterative optimization, the optimal solution output by the improved dung beetle optimization algorithm is obtained, and the optimal metallogenic factor combination corresponding to each ore-controlling geological condition is determined according to the optimal solution as the metallogenic prediction factor set; A prospecting prediction model is established and trained based on a graph convolutional network, and the mineralization prediction factor set is imported into the prospecting prediction model to obtain the mineralization distribution prediction result, specifically: Extract characteristic variable values from completed geological, geophysical, geochemical and prospecting work data based on the set of metallogenic prediction factors, obtain the relationship between the characteristic variable values of different metallogenic prediction factors and the metallogenic distribution, construct a graph representation of the metallogenic distribution and different metallogenic prediction factors, and extract the adjacency matrix; At the same time, based on the example data and the intersection of the three-dimensional geological model of ore body distribution and the three-dimensional geological models of different metallogenic factors, the characteristic variable value range of the ore body distribution corresponding to different metallogenic prediction factors is obtained, and the probability distribution function of different metallogenic prediction factors is obtained; Using a graph convolutional network to establish a prospecting prediction model to learn the graph representation, updating node information according to the adjacency matrix and the state update weight matrix, and obtaining an updated node feature vector; Obtaining characteristic variable values of the target area according to the metallogenic prediction factor set, obtaining probability distribution values corresponding to the characteristic variable values of the target area through probability distribution functions of different metallogenic prediction factors, and processing the adjacency matrix using the probability distribution values to obtain a dynamic adjacency matrix; The node information is updated according to the dynamic adjacency matrix and the state update weight matrix to obtain a final node feature vector, which is then imported into a fully connected layer to obtain a mineralization distribution prediction result.

2. The method for predicting prospecting target areas based on geological three-dimensional modeling according to claim 1, characterized in that: The acquired geological, geophysical, geochemical and remote sensing data are pre-processed to generate a modeling dataset, and geological modeling of the target area is performed based on the modeling dataset, specifically: Based on the geographic information of the target area, historical geological survey data and historical exploration engineering data are obtained in the area, geological, geophysical, geochemical and remote sensing data are screened, and the screened data are standardized, denoised and normalized; Generate a modeling data set from the preprocessed data, extract fault data based on the modeling data set, construct a three-dimensional geological entity model corresponding to the lithologic strata of the target area based on the fault data, extend and trim the constructed three-dimensional geological entity model using stratum boundaries, and determine difference range constraints for model interpolation; querying the maximum and minimum coordinates of the three-dimensional geological entity model to determine the block size, using the block size to grid the three-dimensional geological entity model, obtaining the three-dimensional geological block model and creating attributes of the three-dimensional geological block model based on data in the modeling data set; A three-dimensional geological model corresponding to the lithologic structure of the shallow strata in the target area is generated based on the constructed three-dimensional geological entity model and the three-dimensional geological block model.

3. The method for predicting prospecting target areas based on geological three-dimensional modeling according to claim 1, characterized in that: The lithology classification model is constructed by combining the three-dimensional geological model with deep learning to extract the shallow lithology characteristics of the target area. The shallow lithology characteristics are then used to predict the deep lithology of the target area. Specifically, Slicing the three-dimensional geological model in two dimensions to obtain a three-dimensional geological model cross-section with geophysical data attribute labels, and establishing a training set and a validation set based on the three-dimensional geological model cross-section with geophysical data attribute labels and shallow lithology; Constructing a lithologic classification model, using the training set for model training, introducing dilated convolution with different dilation coefficients to convolve the three-dimensional geological model profile to obtain feature maps of different scales, matching and encoding the feature maps of different scales with stratum lithologic labels, and obtaining shallow lithologic characteristics under different geophysical data attribute labels; Each shallow lithologic feature matrix is processed by multi-head attention. In each attention head, mask estimation is introduced to obtain attention weights, and the shallow lithologic feature matrix is weighted using the obtained attention weights. Multi-scale context aggregation is performed on the weighted shallow lithologic features. Through the split-transform-merge strategy, the weighted shallow lithologic features are transformed using the split standard convolution combined with different dilation coefficients to capture contextual information at different scales. The contextual information at different scales is then merged through concatenation and standard convolution. Importing the fused context information into the fully connected layer to predict the corresponding stratum lithology label, and using the validation set to verify the predicted stratum lithology label to obtain a trained lithology classification model; The three-dimensional geological model profile corresponding to each deep geophysical data of the target area is imported into the trained lithology classification model to obtain the distribution of deep lithology in the target area.

4. The method for predicting prospecting target areas based on geological three-dimensional modeling according to claim 1, characterized in that: Based on the predicted results of deep lithology in the target area, deep geophysical data and three-dimensional geological models, the mineralization factors are screened, specifically: Obtain the type of mineral deposits in the target area for prospecting, and use big data retrieval to obtain completed geological, geophysical, geochemical and prospecting work case data based on the mineral deposit type. Use deep lithology, deep geophysical data and three-dimensional geological models of the target area to obtain similar case data based on similarity calculation; Using the Pearson correlation coefficient, the ore-controlling geological conditions that meet the preset correlation standard are screened from the obtained similar case data. The metallogenic factors in the case data are obtained based on the screened ore-controlling geological conditions. The information contribution of each metallogenic factor to the prospecting prediction is calculated, and the metallogenic factors are preliminarily screened based on the information. The SVM model is trained by the initially screened metallogenic factors to perform classification prediction tasks, and several kernel functions are replaced during the training process to obtain the mean square error of the classification prediction tasks of different metallogenic factors under multiple kernel functions, and the importance scores of different metallogenic factors are generated according to the mean square error; The metallogenic factors are sorted using the importance scores, a preset number of metallogenic factors are selected according to the sorting results, and redundant metallogenic factors are eliminated through collinearity detection.

5. The method for predicting mineral prospecting targets based on geological three-dimensional modeling according to claim 1, characterized in that: The corresponding controlling geological conditions and mineralization laws are obtained through the mineral deposit types in the target area, and the three-dimensional prospecting target area is delineated according to the mineralization distribution prediction results. The delineated three-dimensional prospecting target area is corrected using the controlling geological conditions and mineralization laws corresponding to the mineral deposit type, and three-dimensional visualization is performed.

6. A prospecting target area prediction system based on geological three-dimensional modeling, characterized in that: A method for predicting a prospecting target area based on geological three-dimensional modeling according to any one of claims 1 to 5 is implemented, wherein the system comprises a modeling data acquisition unit, a three-dimensional geological modeling unit, a deep lithology classification unit, a prospecting prediction unit, and a deep prospecting target area delineation unit; The modeling data acquisition unit is responsible for acquiring geological, geophysical, geochemical and remote sensing data of the target area and performing preprocessing to generate a modeling data set; The three-dimensional geological modeling unit is responsible for modeling the shallow geological entities and attributes of the target area according to the modeling data set to obtain a three-dimensional geological model; The deep lithology classification unit is responsible for constructing a lithology classification model based on a deep learning algorithm and a three-dimensional geological model, extracting shallow lithology characteristics of the target area, and predicting the deep lithology of the target area; The prospecting prediction unit is responsible for screening metallogenic factors based on the predicted results of deep lithology in the target area, deep geophysical data and three-dimensional geological models, and constructing a metallogenic prediction factor set, establishing a prospecting prediction model and training it, and importing the metallogenic prediction factor set into the prospecting prediction model to obtain a metallogenic distribution prediction result; The deep prospecting target area delineation unit is responsible for delineating the three-dimensional prospecting target area based on the mineralization distribution prediction results to realize the visualization of the prospecting target area.

Images