A 3D Geological Modeling Optimization Method Based on GIS

Abstract

The present invention discloses a method for optimizing 3D geological modeling based on GIS. The method includes data integration and processing, information clustering and extraction, borehole plane visualization, borehole model construction, geological body model construction, and 3D geological modeling optimization. The present invention relates to the technical field of 3D geological modeling. Specifically, it refers to a method for optimizing 3D geological modeling based on GIS. The present invention adopts an overall idea of 3D geological modeling that combines information clustering and extraction, spatial interpolation optimization, and geological body model construction optimization. Through information clustering and extraction, the multi-source and multi-scale extraction capabilities of information in the data source are optimized. And through spatial interpolation optimization and geological body model construction optimization, the accuracy and performance of borehole data modeling and geological body data modeling are respectively improved. Overall, the 3D modeling performance based on GIS is optimized, and the usability and generality of the method are improved. A multi-coupled cascade hybrid density network that combines random algorithms and geostatistical calculations is used for geological body model construction.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional geological modeling, and specifically refers to an optimization method for three-dimensional geological modeling based on GIS. Background Art

[0002] The optimization method for three-dimensional geological modeling based on GIS combines the geographic information system (GIS) and three-dimensional modeling technology, aiming to construct an accurate and reliable three-dimensional geological model. By collecting geological exploration data, remote sensing images, drilling data, etc., and using the powerful spatial data analysis and processing function of GIS, a three-dimensional visualization model of geological bodies is generated. This method improves the modeling accuracy and efficiency through optimization algorithms, can accurately reflect the spatial distribution and structural characteristics of geological bodies, and provides support for mineral resource exploration, groundwater management, disaster prediction, etc. It not only improves the accuracy and automation of modeling, but also supports real-time monitoring and decision-making analysis through dynamic update and interactive analysis, and is widely used in geological research and engineering practice.

[0003] However, in the existing three-dimensional geological modeling methods, there are technical problems in that the existing three-dimensional model construction methods often have difficulties in comprehensively and accurately reflecting the complexity and diversity of geological bodies in the processes of geological information extraction, spatial interpolation, and geological body modeling; in the existing methods for extracting modeling borehole and formation information, there is a problem that the traditional formation information extraction uses the standard K-means clustering algorithm to intelligently extract information, but when facing multi-source and multi-scale data sources, due to the complexity of formation information, it is very easy to be interfered by the data sources, resulting in large errors and fluctuations in the extracted information, and it is difficult to provide high-quality data for subsequent various modeling requirements; in the existing process of spatial interpolation and visualization of borehole models, there is a technical problem that when the spatial interpolation method is applied to borehole model interpolation, since the borehole model is a pre-step for modeling the geological body model, the borehole model also has high requirements for accuracy as a pre-step, so the traditional spatial interpolation method also needs to be improved in this regard; in the existing optimization methods for constructing geological body models, there is a problem that the traditional method uses the classic Kriging interpolation method for direct interpolation statistical analysis and then interpolation ideas, and the existing automation ideas mostly focus on the generation of original data sources, or use generative adversarial networks to generate samples in terms of parameters. However, due to the fact that the multi-source and multi-scale geological modeling task itself is a complex multi-variable modeling task, the existing methods have deficiencies in dealing with complex spatial data distributions, uncertainties, and the mutual correlations between different strata and geological parameters. Summary of the Invention

[0004] In view of the above situation, to overcome the defects of the prior art, the present invention provides an optimization method for 3D geological modeling based on GIS. This solution creatively adopts an overall idea of 3D geological modeling that combines information clustering extraction, spatial interpolation optimization, and geological body model construction optimization. Through information clustering extraction, it optimizes the multi-source and multi-scale extraction capabilities of information in the data source, and through spatial interpolation optimization and geological body model construction optimization, it respectively improves the accuracy and performance of borehole data modeling and geological body data modeling. Overall, it optimizes the 3D modeling performance based on GIS and improves the usability and versatility of the method. This solution creatively adopts a clustering method improved by dynamic nearest neighbor labeling for information clustering extraction. By combining an adaptive weighted and optimized clustering algorithm, it improves the quantity and quality of information extracted from modeling boreholes and strata information, providing good data support for subsequent method improvement. This solution creatively adopts an adaptive weighted Gaussian spatial interpolation method for spatial interpolation optimization and borehole plane visualization. By continuing the weighted analysis of distance attributes and local density attributes in clustering information extraction and optimizing the consistency of the data processing process, it improves the accuracy of spatial interpolation of the borehole model and also provides a good model and parameter basis for subsequent geological body modeling. This solution creatively adopts a multi-coupled cascaded hybrid density network that combines random algorithms and geostatistical calculations for geological body model construction. By combining geostatistics as reference data samples and using cascaded coupling training of the hybrid density network, it can perform high-precision probability distribution modeling on geological parameters (such as porosity, lithology distribution, formation thickness, etc.), capture complex distribution patterns such as multi-modal distributions or long-tailed characteristics. At the same time, through the cascaded structure, the data distributions of different strata or regions are decoupled layer by layer, gradually approaching the true distribution. Each layer of the module further models the output of the previous layer, enabling better capture of the multi-scale and multi-variable characteristics in complex geological environments. Overall, it meets the geological modeling requirements of multi-stage and multi-parameter complex modeling of multi-scale and multi-source data, providing good practical experience for the implementation path of 3D geological modeling.

[0005] The technical solution adopted by the present invention is as follows: An optimization method for 3D geological modeling based on GIS provided by the present invention, the method comprising the following steps:

[0006] Step S1: Data integration and processing;

[0007] Step S2: Information clustering extraction;

[0008] Step S3: Borehole plane visualization;

[0009] Step S4: Borehole model construction;

[0010] Step S5: Geological body model construction;

[0011] Step S6: 3D geological modeling optimization.

[0012] Further, in step S1, the data integration process is used to collect, integrate, and preprocess the original dataset required for 3D geological modeling optimization. Specifically, from the geographic information system, through data collection, the original data of the surface matrix survey points is obtained, and through data integration and preprocessing, the original dataset for geological modeling is obtained;

[0013] The original data of the surface matrix survey points specifically includes borehole engineering data, basic borehole information data, borehole stratification data, and standard stratigraphic data;

[0014] The data integration and preprocessing specifically includes data outlier detection, data missing value detection, and data integrity detection, and through formatting standardization of the borehole depth and lithology description data, data integration and preprocessing are carried out;

[0015] The original dataset for geological modeling specifically includes integrated borehole engineering data, integrated basic borehole information data, integrated borehole stratification data, and integrated standard formation data.

[0016] Further, in step S2, the information clustering extraction is used to extract hierarchical information from the borehole information in the original dataset. Specifically, based on the original dataset for geological modeling, an improved clustering method with dynamic nearest neighbor labeling is used for information clustering extraction to obtain geological stratification information data, which specifically includes the following steps:

[0017] Step S21: Data cleaning and optimization, specifically, for the original dataset for geological modeling, the local outlier factor algorithm is used to identify outliers and perform data cleaning and optimization to obtain cleaned and optimized data;

[0018] Step S22: Clustering distance weighted optimization, specifically, by calculating the clustering weighted distance, based on the sample distance calculated in the cleaned and optimized data, weighted distance optimization is carried out to obtain the weighted distance weight;

[0019] Step S23: Local density enhancement, specifically, by calculating local density information to calculate the dynamic K nearest neighbor value, an adaptive K nearest neighbor value is obtained. The calculation formula is:

[0020] ;

[0021] In the formula, K dy is the adaptive K nearest neighbor value, which is used as the clustering parameter for clustering information extraction. min(·) is the function to find the minimum value. K max is the maximum K nearest neighbor value. density(·) is the local density calculation function. x i is the i-th input data sample, which is used to represent the data in the original dataset for geological modeling, is the adaptive adjustment coefficient;

[0022] Step S24: Dynamic neighbor label enhancement, specifically, through the clustering distance weighting optimization and the local density enhancement, perform majority voting dynamic neighbor label enhancement to obtain dynamic nearest neighbor improved label data. The calculation formula is:

[0023] ;

[0024] In the formula, lable(·) is the dynamic nearest neighbor labeling improvement function, x i is the i-th input data sample, used to represent the data in the original geological modeling dataset. argmax is the function to find the maximum value, L is the label index, is the total number of neighbor nodes after adaptive optimization. Among them, x j is the j-th neighbor node sample, j is the neighbor node sample index, K dy is the adaptive K-nearest neighbor value, used as the clustering parameter for clustering information extraction. Wdist(·) is the weighted distance weight calculation function, is the indicator function, used to judge whether the label L j corresponding to the neighbor node sample x j is equal to the label index L;

[0025] Step S25: Multi-level label optimization, specifically, adopt the multi-level K-means clustering method to extract hierarchical clustering information, and based on the dynamic nearest neighbor improved label data, perform iterative label enhancement to obtain multi-level optimized label data;

[0026] Step S26: Information clustering extraction, specifically, through the dynamic neighbor label enhancement and the multi-level label optimization, perform information clustering extraction of the clustering method with dynamic nearest neighbor labeling improvement to obtain geological stratification information data.

[0027] Furthermore, in step S3, the borehole plane visualization is used to optimize spatial interpolation in combination with borehole information and perform visualization settings. Specifically, based on the geological stratification information data, adopt the adaptive weighted Gaussian spatial interpolation method to perform spatial interpolation optimization and borehole plane visualization to obtain borehole plane visualization data, which specifically includes the following steps:

[0028] Step S31: Borehole data standardization, specifically, perform Z-score standardization processing on the geological stratification information data to obtain standardized borehole data;

[0029] Step S32: Adaptive weighted operator calculation, specifically, based on the standardized borehole data, calculate the distance similarity in the borehole data to obtain the adaptive weighted factor. The calculation formula is:

[0030] ;

[0031] Wherein, W(·) is an adaptive weighting factor calculation function, and X a is the first borehole data point, used to represent the data point in the standardized borehole data, and X b is the second borehole data point, used to represent the neighborhood data point of the first borehole data point, exp(·) is the natural base function, and d(·) is a similarity calculation function, used to represent the distance similarity calculation function and attributes, and specifically calculates the Euclidean distance, is the data point density parameter, used as an adaptive weighting parameter;

[0032] Step S33: Adaptive Gaussian interpolation calculation, specifically by combining the adaptive weighting factor and setting an adaptive weighted Gaussian function to perform spatial interpolation calculation to obtain adaptive interpolation data, and the calculation formula is:

[0033] ;

[0034] Wherein, Z(·) is a geological attribute value calculation function, used to represent the adaptive interpolation data corresponding to the interpolation point, P is the interpolation point index, is the total number of interpolation points, and X b is the second borehole data point, used to represent the neighborhood data point of the first borehole data point, and W(P, X b ) is the adaptive weighting factor corresponding to the interpolation point P and the second borehole data point X b , and Z(X b ) is the geological attribute value of the second borehole data point X b ;

[0035] Step S34: Spatial interpolation optimization, specifically by performing smoothing optimization on the adaptive interpolation data through Gaussian filtering, and by combining the self-adaptive weighting operator and introducing a composite adaptive weighting operator to obtain smoothed and optimized interpolation data, and the calculation formula is:

[0036] ;

[0037] Wherein, Z s (·) is a Gaussian filtering smoothing calculation function, P is the interpolation point index, is the total number of interpolation points, X b is the second borehole data point, is the self-adaptive weighting factor introducing the composite adaptive weighting operator, Z(X b ) is the geological attribute value of the second borehole data point X b , and W(P, X b) is the adaptive weighting factor corresponding to the interpolation point P and the second borehole data point X b , is the composite weighted local density adjustment parameter, and density(·) is the local density calculation function;

[0038] Step S35: Borehole plane visualization, specifically, based on the smoothed and optimized interpolation data, perform spatial interpolation to obtain a spatial interpolation reference result, and combine and visualize the spatial interpolation reference result and the geological stratification information data to obtain geological layer visualization plane data;

[0039] Step S36: Interactive visual optimization, specifically, adopt WebGIS technology to perform interactive borehole information visualization, represent borehole information through a point layer, and represent the depth, formation, and spatial position through attribute list information to obtain borehole plane visualization data.

[0040] Furthermore, in step S4, the borehole model construction is used to initialize the construction of the borehole model and perform geological simulation in combination with borehole information. Specifically, based on the borehole plane visualization data, set the parameters of the borehole model and initialize the generation of the borehole model to obtain the initial borehole model data, which specifically includes the following steps:

[0041] Step S41: Initialization of borehole model parameters, specifically, based on the initial borehole model data, set the initialization parameter set for borehole model construction;

[0042] The initialization parameter set for borehole model construction specifically includes the model name, borehole radius, and texture unit size parameters;

[0043] Step S42: Standard formation editing, specifically, through setting the initialization parameter set for borehole model construction, perform initial editing of the borehole model, and obtain formation information data through customizing formation information;

[0044] The formation information data specifically includes formation coding, rock and soil name, formation sequence, and formation legend style;

[0045] Step S43: Generation of borehole model, specifically, based on the formation information data, divide the initialization parameter set for borehole model construction into different formation units, generate a three-dimensional model for each formation unit to obtain an initial set of three-dimensional model shapes of the formation, and through optimizing and simulating based on the texture unit size and formation legend style in the initialization parameter set for borehole model construction and the formation information data, generate and obtain the initial borehole model data.

[0046] Furthermore, in step S5, the geological body model construction is used to comprehensively construct the geological body model in combination with the initialized borehole model. Specifically, based on the geological stratification information data, the borehole plane visualization data, and the initial borehole model data, a multi-coupled cascade hybrid density network combining a random algorithm and geostatistical calculations is used to construct the geological body model, obtaining geological body modeling data, which specifically includes the following steps:

[0047] Step S51: Initialize the geological body model parameters. Specifically, based on the geological stratification information data, the borehole plane visualization data, and the initial borehole model data, set the geological body model parameters to obtain a set of geological body model parameters;

[0048] The set of geological body model parameters specifically includes the geological body model name, horizontal grid spacing, sample influence radius, formation change coefficient, and geological body texture unit size;

[0049] Step S52: Edit the geological body strata. Specifically, by setting the set of geological body model parameters, perform initial editing of the geological body strata model, and obtain geological body strata information data by customizing the strata information;

[0050] The geological body strata information data specifically includes the geological body strata code, geological body rock and soil name, geological body strata sequence, and geological body legend style;

[0051] Step S53: Geostatistical analysis. Specifically, adopt the combined Kriging interpolation method, and based on the geological body strata information data and the set of geological body model parameters, perform geostatistical analysis to obtain the reference values of the statistical attributes of the geological body interpolation points;

[0052] Step S54: Construct a random simulation algorithm. Specifically, based on the reference values of the statistical attributes of the geological body interpolation points, use the Monte Carlo method to generate spatial statistical features, and through the calculation of the expected value and variance, obtain the statistical feature data of the random simulation geological body interpolation points;

[0053] Step S55: Construct a multi-coupled cascade density hybrid network. Specifically, train multiple standard hybrid density networks and perform cascade combination to construct the multi-coupled cascade density hybrid network, perform multivariate joint analysis, and obtain the output of the geological body spatial parameters;

[0054] The multi-coupled cascade density hybrid network specifically includes an input layer, a feature extraction layer, a mixing layer, and an output layer;

[0055] The calculation formula for the construction process of the multi-coupled cascade density hybrid network is:

[0056] ;

[0057] In the formula, Model GC is a multi-coupled cascade density mixing network, which is used to represent the model for generating the spatial parameters of geological body modeling and calculate the output of the spatial parameters of the geological body. as a whole is used to represent the sum of the outputs of the first c-layer density mixing networks, where is the total number of coupled layers of the density mixing network, is the coupling index of the density mixing network, which is used to represent the input source of the c-th layer of the mixed density network. c is the layer index of the mixed density network. is the output of the output layer of the -th layer of the density mixing network, which is used to represent the output of the spatial parameters of the geological body and is used as the input data of the mixed density network of the (c + 1)-th layer. CN c+1 is the calculation output of the feature extraction layer of the (c + 1)-th layer of the mixed density network, specifically used to represent the output of the standard convolutional layer features using the non-linear activation function. Mixture c+1 is the calculation output of the mixing layer of the (c + 1)-th layer of the mixed density network, specifically used to represent the calculation output using the standard mixture density model. output c+1 is the output of the output layer of the (c + 1)-th layer of the mixed density network;

[0058] Step S56: Generation of spatial parameters for geological body modeling. Specifically, based on the statistical feature data of the interpolation points of the randomly simulated geological body, through the multi-coupled cascade density mixing network, model training for generating the spatial parameters of geological body modeling is carried out to obtain the model Model GC for generating the spatial parameters of the geological body, and the model Model GC for generating the spatial parameters of the geological body is used to generate the geological attribute parameter set;

[0059] Step S57: Construction of the geological body model. Specifically, based on the geological attribute parameter set, combined with the image rendering technology, the scene of the geological body model is constructed to obtain the geological body modeling data;

[0060] Furthermore, in step S6, the three-dimensional geological modeling optimization is used to store and manage the three-dimensional model of the geological body and perform comprehensive optimization. Specifically, based on the geological body modeling data, management optimization of the geological body model is carried out, and by grouping and storing the borehole model data and the geological body model data, a model directory and a management system are established to perform three-dimensional geological modeling optimization to obtain a three-dimensional geological modeling optimization database.

[0061] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0062] (1) In view of the technical problem that in the existing 3D geological modeling methods, the existing 3D model construction methods mostly have difficulties in comprehensively and accurately reflecting the complexity and diversity of geological bodies during the extraction of geological information, the spatial interpolation process, and the geological body modeling process, this solution creatively adopts the overall idea of 3D geological modeling that combines information clustering extraction, spatial interpolation optimization, and geological body model construction optimization. Through information clustering extraction, the multi-source and multi-scale extraction capabilities of information in the data source are optimized, and through spatial interpolation optimization and geological body model construction optimization, the accuracy and performance of borehole data modeling and geological body data modeling are respectively improved, and overall, the 3D modeling performance based on GIS is optimized, and the usability and versatility of the method are improved;

[0063] (2) In view of the technical problem that in the existing methods for extracting modeling borehole and formation information, the traditional formation information extraction uses the standard K-means clustering algorithm to intelligently extract information. However, when facing multi-source and multi-scale data sources, due to the complexity of formation information, it is very easy to be interfered by the data source, resulting in large errors and fluctuations in the extracted information, and it is difficult to provide high-quality data for subsequent various modeling requirements. This solution creatively adopts the clustering method improved by dynamic nearest neighbor labeling for information clustering extraction. By combining the adaptive weighted and optimized clustering algorithm, the quantity and quality of the information extracted from the modeling borehole and formation information are improved, so as to provide good data support for subsequent method improvement;

[0064] (3) In view of the technical problem that in the existing spatial interpolation and visualization process of the borehole model, when the spatial interpolation method is applied to the interpolation of the borehole model, since the borehole model is a pre-step for modeling the geological body model, the borehole model also has high requirements for accuracy as a pre-step. Therefore, the traditional spatial interpolation method also needs to be improved in this regard. This solution creatively adopts the adaptive weighted Gaussian spatial interpolation method for spatial interpolation optimization and borehole plane visualization. By continuing the weighted analysis of the distance attribute and local density attribute in the clustering information extraction, and through the consistency optimization of the data processing flow, the accuracy of the spatial interpolation of the borehole model is improved, and a good model and parameter basis for subsequent geological body modeling are also provided;

[0065] (4) In the existing geological body model construction and optimization methods, the traditional method uses the classical Kriging interpolation method for direct interpolation statistical analysis and then interpolation. The existing automated ideas mostly focus on the generation of the original data source or use the generative adversarial network to generate samples in terms of parameters. However, due to the fact that the multi-source and multi-scale geological modeling task itself is a complex multi-variable modeling task, the existing methods have deficiencies in dealing with complex spatial data distribution, uncertainty, and the mutual correlation between different strata and geological parameters. This solution creatively adopts a multi-coupled cascade hybrid density network that combines random algorithms and geostatistical calculations to construct a geological body model. By combining geostatistics as reference data samples and using the cascade coupling training of the hybrid density network, it is possible to perform high-precision probability distribution modeling on geological parameters (such as porosity, lithology distribution, formation thickness, etc.), capture complex distribution patterns such as multi-modal distribution or long-tailed characteristics. At the same time, through the cascade structure, the data distribution of different strata or regions is decoupled layer by layer, gradually approaching the real distribution. Each layer of the module further models the output of the previous layer, enabling the multi-scale and multi-variable characteristics in a complex geological environment to be better captured, and overall meeting the geological modeling requirements of multi-stage and multi-parameter complex modeling of multi-scale and multi-source data, providing good practical experience for the implementation path of 3D geological modeling. Description of the Drawings

[0066] Figure 1 It is a schematic flow chart of a 3D geological modeling optimization method based on GIS provided by the present invention;

[0067] Figure 2 It is a schematic flow chart of information clustering and extraction in step S2;

[0068] Figure 3 It is a schematic flow chart of borehole plane visualization in step S3;

[0069] Figure 4 It is a schematic flow chart of borehole model construction in step S4;

[0070] Figure 5 It is a schematic flow chart of geological body model construction in step S5.

[0071] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. Detailed Embodiments

[0072] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0073] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0074] Embodiment 1, refer to Figure 1 , a three-dimensional geological modeling optimization method based on GIS provided by the present invention, the method comprises the following steps:

[0075] Step S1: Data integration and processing;

[0076] Step S2: Information clustering and extraction;

[0077] Step S3: Borehole plane visualization;

[0078] Step S4: Borehole model construction;

[0079] Step S5: Geological body model construction;

[0080] Step S6: Three-dimensional geological modeling optimization.

[0081] By performing the above operations, aiming at the technical problem that in the existing three-dimensional geological modeling methods, the existing three-dimensional model construction methods mostly have difficulties in comprehensively and accurately reflecting the complexity and diversity of geological bodies in the processes of geological information extraction, spatial interpolation, and geological body modeling, this solution creatively adopts the overall idea of three-dimensional geological modeling combining information clustering and extraction, spatial interpolation optimization, and geological body model construction optimization. Through information clustering and extraction, the multi-source and multi-scale extraction capabilities of information in the data source are optimized, and through spatial interpolation optimization and geological body model construction optimization, the accuracy and performance of borehole data modeling and geological body data modeling are respectively improved, and the three-dimensional modeling performance based on GIS is optimized as a whole, and the usability and versatility of the method are improved.

[0082] Embodiment 2, refer to Figure 1, in step S1, the data integration process is used to collect, integrate, and preprocess the original dataset required for 3D geological modeling optimization. Specifically, from the geographic information system, through data collection, the original data of the surface matrix survey points is obtained, and through data integration and preprocessing, the original dataset for geological modeling is obtained;

[0083] The original data of the surface matrix survey points specifically includes borehole engineering data, basic borehole information data, borehole stratification data, and standard stratigraphic data;

[0084] The data integration and preprocessing specifically includes data outlier detection, data missing value detection, and data integrity detection, and through format standardization of borehole depth and lithology description data, data integration and preprocessing are carried out;

[0085] The original dataset for geological modeling specifically includes integrated borehole engineering data, integrated basic borehole information data, integrated borehole stratification data, and integrated standard bottom layer data;

[0086] The integrated borehole engineering data specifically includes project name, project code, and coordinate system data;

[0087] The integrated basic borehole information data specifically includes hole code, hole elevation, hole depth, and geographic coordinate data;

[0088] The integrated borehole stratification data specifically includes hole code, formation code, bottom layer depth data, top layer depth data, layer thickness data, rock and soil name, and project code;

[0089] The integrated standard bottom layer data specifically includes formation code, rock and soil name, formation sequence, formation color, and project code.

[0090] Example 3, refer to Figure 1 and Figure 2 , based on the above example, in step S2, the information clustering extraction is used to extract hierarchical information from the borehole information in the original dataset. Specifically, based on the original dataset for geological modeling, an improved clustering method with dynamic nearest neighbor labeling is used for information clustering extraction to obtain geological stratification information data, which specifically includes the following steps:

[0091] Step S21: Data cleaning and optimization. Specifically, for the original dataset for geological modeling, the local outlier factor algorithm is used to identify outliers and perform data cleaning and optimization to obtain cleaned and optimized data. The calculation formula is:

[0092] ;

[0093] In the formula, LOF(·) is the local outlier factor algorithm function, sum(·) is the summation function, xi is the i-th input data sample, used to represent the data in the original geological modeling dataset. i is the data sample index, dist(·) is the sample distance calculation function, specifically referring to the Euclidean distance, x j is the j-th neighbor node sample, j is the neighbor node sample index, reachability(·) is the reachable distance calculation function, used to represent the reachability between the input data sample and the neighbor node sample, N(x i ,k) is the total number of K neighbor nodes of the input data sample x i , and K is the K-nearest neighbor value, used to represent the number of neighbor nodes of the input data sample and as a clustering parameter;

[0094] Step S22: Clustering distance weighted optimization, specifically by calculating the clustering weighted distance, and performing weighted distance optimization based on the sample distance calculated in the cleaned and optimized data to obtain the weighted distance weight. The calculation formula is:

[0095] ;

[0096] In the formula, Wdist(·) is the weighted distance weight calculation function, dist(·) is the sample distance calculation function, specifically referring to the Euclidean distance, x j is the j-th neighbor node sample, j is the neighbor node sample index, is the regularization constant;

[0097] Step S23: Local density enhancement, specifically by calculating the local density information to perform dynamic K-nearest neighbor value calculation to obtain the adaptive K-nearest neighbor value. The calculation formula is:

[0098] ;

[0099] In the formula, K dy is the adaptive K-nearest neighbor value, used as the clustering parameter for clustering information extraction, min(·) is the function to obtain the minimum value, K max is the maximum K-nearest neighbor value, density(·) is the local density calculation function, x i is the i-th input data sample, used to represent the data in the original geological modeling dataset, is the adaptive adjustment coefficient;

[0100] Step S24: Dynamic neighbor label enhancement, specifically by performing majority voting dynamic neighbor label enhancement through the clustering distance weighted optimization and the local density enhancement to obtain the dynamic nearest neighbor improved label data. The calculation formula is:

[0101] ;

[0102] Where, lable(·) is the dynamic nearest neighbor labeling improvement function, and x i is the i-th input data sample, which is used to represent the data in the original geological modeling dataset. argmax is the function to find the maximum value, L is the label index, is the total number of neighbor nodes after adaptive optimization. Among them, x j is the j-th neighbor node sample, j is the neighbor node sample index, and K dy is the adaptive K-nearest neighbor value, which is used as the clustering parameter for clustering information extraction. Wdist(·) is the weighted distance weight calculation function, is the indicator function, which is used to judge whether the label L j corresponding to the neighbor node sample x j is equal to the label index L;

[0103] Step S25: Multi-level label optimization, specifically using the multi-level K-means clustering method to extract hierarchical clustering information, and iteratively enhancing the labels based on the dynamic nearest neighbor improved label data to obtain multi-level optimized label data;

[0104] Step S26: Information clustering extraction, specifically through the dynamic neighbor label enhancement and the multi-level label optimization, performing information clustering extraction of the clustering method with dynamic nearest neighbor labeling improvement to obtain geological stratification information data.

[0105] By performing the above operations, in the existing modeling borehole and formation information extraction methods, there is a problem that the traditional formation information extraction uses the standard K-means clustering algorithm to intelligently extract information. However, when facing multi-source and multi-scale data sources, due to the complexity of the formation information, it is very easy to be interfered by the data sources, resulting in large errors and fluctuations in the extracted information, and it is difficult to provide high-quality data for subsequent various modeling requirements. The present solution creatively uses the clustering method with dynamic nearest neighbor labeling improvement to perform information clustering extraction. By combining the adaptive weighted and optimized clustering algorithm, the quantity and quality of the information extracted from the modeling borehole and formation are improved, and good data support can be provided for subsequent method improvement.

[0106] Example 4, refer to Figure 1 and Figure 3 , based on the above example, in step S3, the borehole plane visualization is used to optimize the spatial interpolation in combination with the borehole information and perform visualization settings. Specifically, according to the geological stratification information data, the adaptive weighted Gaussian spatial interpolation method is used to perform spatial interpolation optimization and borehole plane visualization to obtain borehole plane visualization data, which specifically includes the following steps:

[0107] Step S31: Standardize the drilling data. Specifically, perform Z-score standardization on the geological stratification information data to obtain standardized drilling data;

[0108] Step S32: Calculate the adaptive weighting operator. Specifically, based on the standardized drilling data, calculate the distance similarity in the drilling data to obtain an adaptive weighting factor. The calculation formula is:

[0109] ;

[0110] In the formula, W(·) is the adaptive weighting factor calculation function, X a is the first drilling data point, used to represent the data point in the standardized drilling data, X b is the second drilling data point, used to represent the neighborhood data point of the first drilling data point, exp(·) is the natural exponential function, d(·) is the similarity calculation function, used to represent the distance similarity calculation function and attributes, and specifically calculates the Euclidean distance. is the data point density parameter, used as the adaptive weighting parameter;

[0111] Step S33: Perform adaptive Gaussian interpolation calculation. Specifically, by combining the adaptive weighting factor and setting an adaptive weighted Gaussian function, perform spatial interpolation calculation to obtain adaptive interpolation data. The calculation formula is:

[0112] ;

[0113] In the formula, Z(·) is the geological attribute value calculation function, used to represent the adaptive interpolation data corresponding to the interpolation point, P is the interpolation point index, is the total number of interpolation points, X b is the second drilling data point, used to represent the neighborhood data point of the first drilling data point, W(P,X b ) is the adaptive weighting factor corresponding to the interpolation point P and the second drilling data point X b , Z(X b ) is the geological attribute value of the second drilling data point X b ;

[0114] Step S34: Optimize the spatial interpolation. Specifically, perform smoothing optimization on the adaptive interpolation data through Gaussian filtering. By combining the self-adaptive weighting operator and introducing a composite adaptive weighting operator, obtain the smoothed and optimized interpolation data. The calculation formula is:

[0115] ;

[0116] In the formula, Z s (·) is the Gaussian filtering smoothing calculation function, P is the interpolation point index, is the total number of interpolation points, X b is the second borehole data point, is the self - adaptive weighting factor introducing the composite adaptive weighting operator, Z(X b ) is the geological attribute value of the second borehole data point X b of, W(P, X b ) is the adaptive weighting factor corresponding to the interpolation point P and the second borehole data point X b ; is the composite weighted local density adjustment parameter, density(·) is the local density calculation function;

[0117] Step S35: Borehole plane visualization, specifically, based on the smoothed and optimized interpolation data, perform spatial interpolation to obtain a spatial interpolation reference result, and combine and visualize the spatial interpolation reference result and the geological stratification information data to obtain geological layer visualization plane data;

[0118] The geological layer visualization plane data specifically includes geological layer information and spatial distribution information;

[0119] Step S36: Interactive visual optimization, specifically, adopt WebGIS technology to perform interactive borehole information visualization, represent borehole information through a point layer, and represent depth, formation, and spatial position through attribute list information to obtain borehole plane visualization data.

[0120] By performing the above operations, aiming at the technical problem that in the existing spatial interpolation and visualization process of the borehole model, when the spatial interpolation method is applied to the borehole model interpolation, since the borehole model is a pre - step for modeling the geological body model, the borehole model also has high requirements for accuracy as a pre - step, and thus the traditional spatial interpolation method also needs to be improved in this regard. This solution creatively adopts the adaptive weighted Gaussian spatial interpolation method to optimize spatial interpolation and borehole plane visualization. By continuing the weighted analysis of distance attributes and local density attributes through clustering information extraction, and through the consistency optimization of the data processing flow, the accuracy of the spatial interpolation of the borehole model is improved, and a good model and parameter basis for subsequent geological body modeling is also provided.

[0121] Example Five, refer to Figure 1 and Figure 4 , based on the above example, in step S4, the construction of the borehole model is used to initialize the construction of the borehole model and perform geological simulation in combination with borehole information. Specifically, based on the borehole plane visualization data, set the parameters of the borehole model and generate the initialization of the borehole model to obtain the initial borehole model data, which specifically includes the following steps:

[0122] Step S41: Initialize the parameters of the drilling model. Specifically, according to the initial drilling model data, set the initialization parameter set for constructing the drilling model.

[0123] The initialization parameter set for constructing the drilling model specifically includes the model name, drilling radius, and texture unit size parameter.

[0124] Step S42: Edit the standard formation. Specifically, by setting the initialization parameter set for constructing the drilling model, perform the initial editing of the drilling model, and obtain the formation information data by customizing the formation information.

[0125] The formation information data specifically includes formation code, geotechnical name, formation sequence, and formation legend style.

[0126] Step S43: Generate the drilling model. Specifically, according to the formation information data, divide the initialization parameter set for constructing the drilling model into different formation units, generate a three-dimensional model for each formation unit to obtain the initial shape set of the formation three-dimensional model, and perform model optimization simulation according to the texture unit size and formation legend style in the initialization parameter set for constructing the drilling model and the formation information data, and generate the initial drilling model data.

[0127] Example 5, refer to Figure 1 and Figure 5 , this example is based on the above example. In step S5, the construction of the geological body model is used to comprehensively construct the geological body model in combination with the initialized drilling model. Specifically, according to the geological stratification information data, the drilling plane visualization data, and the initial drilling model data, a multi-coupled cascaded hybrid density network combining a random algorithm and geostatistical calculation is used to construct the geological body model to obtain the geological body modeling data, which specifically includes the following steps:

[0128] Step S51: Initialize the parameters of the geological body model. Specifically, according to the geological stratification information data, the drilling plane visualization data, and the initial drilling model data, set the parameters of the geological body model to obtain the parameter set of the geological body model.

[0129] The parameter set of the geological body model specifically includes the geological body model name, horizontal grid spacing, sample influence radius, formation change coefficient, and geological body texture unit size.

[0130] The geological body model name is used to represent the identifier of the geological body model.

[0131] The horizontal grid spacing is used to control the grid division accuracy of the model and serves as the horizontal size of each grid unit.

[0132] The sample influence radius is used to define the range of influence of geological variables in space;

[0133] The formation change coefficient is used to describe the steepness of the formation change. The closer the value is to 1, the flatter the formation is, and the closer the value is to 0, the more dramatic the formation change is.

[0134] The geological body texture unit size is used to define the size of the texture unit within the geological body and the detail level of the geological body;

[0135] Step S52: geological body stratum editing, specifically, performing initial editing of the geological body stratum model by setting the geological body model parameter set, and obtaining geological body stratum information data by customizing stratum information;

[0136] The geological body stratigraphic information data specifically includes the geological body stratigraphic code, geological body rock and soil name, geological body stratigraphic sequence and geological body legend style;

[0137] The geological body stratum code is used to represent the unique code of each geological body stratum;

[0138] The geological body rock and soil name is used to indicate the rock and soil type in each geological body stratum;

[0139] The geological body stratigraphic sequence is used to indicate the order of geological body stratigraphic layers;

[0140] The geological body legend style is used to represent the display style of the geological body strata in the three-dimensional model;

[0141] Step S53: geostatistical analysis, specifically, using the Kriging interpolation method, based on the geological body stratigraphic information data and the geological body model parameter set, to perform geostatistical analysis to obtain the statistical attribute reference value of the geological body interpolation point, the calculation formula is:

[0142] ;

[0143] Where y(·) is a semi-differential calculation function, which is used to represent the degree of variation of geological variables with distance, h is the geostatistical distance variable, and n(h) is the total number of all data points within the geostatistical distance h. is the index of data points within the geostatistical distance h, It is a geological variable value calculation function, which is specifically used to represent the Kriging interpolation attribute value. It is The original geological data corresponding to the data points are used to represent the geological body stratigraphic information data and the geological parameters in the geological body model parameter set. is the reference value of the statistical attributes of the geological body interpolation points, are the data points to be interpolated by Kriging, is the Kriging interpolation weight corresponding to the th data point;

[0144] Step S54: Construction of the stochastic simulation algorithm, specifically, based on the reference values of the statistical attributes of the interpolation points of the geological body, the Monte Carlo method is used to generate spatial statistical features, and through the calculation of the expected value and the housing difference, the statistical feature data of the stochastic simulation geological body interpolation points are obtained;

[0145] Step S55: Construction of the multi-coupled cascade density mixture network, specifically, training multiple standard mixture density networks and performing cascade combination to construct the multi-coupled cascade density mixture network, and performing multivariate joint analysis to obtain the output of the geological body spatial parameters;

[0146] The multi-coupled cascade density mixture network specifically includes an input layer, a feature extraction layer, a mixture layer, and an output layer;

[0147] The calculation formula for the construction process of the multi-coupled cascade density mixture network is:

[0148] ;

[0149] In the formula, Model GC is the multi-coupled cascade density mixture network, which is used to represent the model for generating the spatial parameters of the geological body modeling and calculate the output of the geological body spatial parameters, as a whole is used to represent the sum of the outputs of the first c layers of the density mixture network, where is the total number of coupling layers of the density mixture network, is the coupling index of the density mixture network, which is used to represent the input source of the cth layer of the mixture density network. c is the layer index of the mixture density network, is the output of the output layer of the th layer of the density mixture network, which is used to represent the output of the geological body spatial parameters and is used as the input data of the (c + 1)th layer of the mixture density network. CN c+1 is the calculated output of the feature extraction layer of the (c + 1)th layer of the mixture density network, specifically used to represent the output of the standard convolutional layer features using the non-linear activation function. Mixture c+1 is the calculated output of the mixture layer of the (c + 1)th layer of the mixture density network, specifically used to represent the calculated output using the standard mixture density model. output c+1 is the output of the output layer of the (c + 1)th layer of the mixture density network;

[0150] Step S56: Generation of spatial parameters for geological body modeling. Specifically, based on the statistical feature data of the interpolated points of the randomly simulated geological body, through the multi-coupled cascaded density mixture network, training is performed on the generation model of the spatial parameters for geological body modeling to obtain the generation model Model of the spatial parameters for geological body modeling GC , and use the generation model Model of the spatial parameters for geological body modeling GC to generate the spatial parameters for geological body modeling, and obtain a set of geological attribute parameters;

[0151] Step S57: Construction of a geological body model. Specifically, based on the set of geological attribute parameters, combined with image rendering technology, a scene of the geological body model is constructed to obtain geological body modeling data;

[0152] The image rendering technology is specifically implemented by using the API interface provided by the WebGL (Web Graphics Library) graphics rendering technology.

[0153] By performing the above operations, in the existing optimization methods for geological body model construction, there is an idea in the traditional method of using the classical Kriging interpolation method for direct interpolation statistical analysis and then interpolation. And the existing automated ideas mostly focus on the generation of the original data source, or use the generative adversarial network to generate samples in terms of parameters. However, due to the fact that the multi-source and multi-scale geological modeling task itself is a complex multi-variable modeling task, the existing methods have deficiencies in dealing with complex spatial data distributions, uncertainties, and the mutual correlations between different strata and geological parameters. This solution creatively uses a multi-coupled cascaded hybrid density network that combines random algorithms and geostatistical calculations to construct a geological body model. By combining geostatistics as reference data samples and using the cascaded coupling training of the hybrid density network, it is possible to perform high-precision probability distribution modeling on geological parameters (such as porosity, lithology distribution, formation thickness, etc.), capture complex distribution patterns such as multi-modal distributions or long-tail characteristics. At the same time, through the cascaded structure, the data distributions of different strata or regions are decoupled layer by layer, gradually approaching the real distribution. Each layer of the module further models the output of the previous layer, enabling the multi-scale and multi-variable characteristics in a complex geological environment to be better captured, and overall meeting the geological modeling requirements of multi-stage and multi-parameter complex modeling of multi-scale and multi-source data, providing good practical experience for the implementation path of 3D geological modeling.

[0154] Example Six, refer to Figure 1 and Figure 5, based on the above embodiment, in step S6, the 3D geological modeling optimization is used to store and manage the 3D model of the geological body and conduct comprehensive optimization. Specifically, according to the geological body modeling data, the management optimization of the geological body model is carried out, and by grouping and storing the borehole model data and the geological body model data, a model directory and a management system are established to conduct 3D geological modeling optimization, and a 3D geological modeling optimization database is obtained.

[0155] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0156] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention.

[0157] The above describes the present invention and its implementation manners. Such description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. All in all, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments without creative efforts without departing from the purpose of the present invention, they shall fall within the protection scope of the present invention.

Claims

1. A three-dimensional geological modeling optimization method based on GIS, characterized in that: The method includes the following steps: Step S1: Data integration and processing to obtain the original dataset for geological modeling; Step S2: Information clustering and extraction. Specifically, based on the original dataset for geological modeling, a clustering method improved by dynamic nearest neighbor labeling is used for information clustering and extraction to obtain geological stratification information data; Step S3: Borehole plane visualization. Specifically, based on the geological stratification information data, an adaptive weighted Gaussian spatial interpolation method is used for spatial interpolation optimization and borehole plane visualization to obtain borehole plane visualization data, including the following steps: Step S31: Borehole data standardization; Step S32: Adaptive weighted operator calculation; Step S33: Adaptive Gaussian interpolation calculation; Step S34: Spatial interpolation optimization; Step S35: Borehole plane visualization; Step S36: Interactive visual optimization; Step S4: Borehole model construction. Specifically, based on the borehole plane visualization data, borehole model parameter settings are carried out, and initial borehole model generation is performed to obtain initial borehole model data; Step S5: Geological body model construction, which is used to comprehensively construct the geological body model in combination with the initialized borehole model. Specifically, based on the geological stratification information data, the borehole plane visualization data, and the initial borehole model data, a multi-coupled cascade hybrid density network combining a random algorithm and geostatistical calculation is used for geological body model construction to obtain geological body modeling data, including the following steps: Step S51: Geological body model parameter initialization; Step S52: Geological body stratigraphic editing; Step S53: Geostatistical analysis; Step S54: Random simulation algorithm construction; Step S55: Multi-coupled cascade density hybrid network construction; Step S56: Generation of geological body modeling spatial parameters; Step S57: Geological body model construction; Step S6: Three-dimensional geological modeling optimization to obtain a three-dimensional geological modeling optimization database.

2. The three-dimensional geological modeling optimization method based on GIS according to claim 1, wherein: In step S1, for the data integration and processing, original data of surface matrix survey points are obtained from a geographic information system through data collection, and the original dataset for geological modeling is obtained through data integration and preprocessing; The original data of the surface matrix survey points specifically includes borehole engineering data, borehole basic information data, borehole stratification data, and standard stratigraphic data; The data integration and preprocessing specifically include data outlier detection, data missing value detection, and data integrity detection, and data integration and preprocessing are carried out by standardizing the formats of borehole depth and lithology description data; The original dataset for geological modeling specifically includes integrated borehole engineering data, integrated borehole basic information data, integrated borehole stratification data, and integrated standard underlying data.

3. A three-dimensional geological modeling optimization method based on GIS according to claim 2, characterized in that: In step S2, the information clustering and extraction is used to extract stratification information from the borehole information in the original dataset. Specifically, based on the original dataset for geological modeling, a clustering method improved by dynamic nearest neighbor labeling is used for information clustering and extraction to obtain geological stratification information data, specifically including the following steps: Step S21: Data cleaning and optimization. Specifically, for the original geological modeling dataset, the Local Outlier Factor algorithm is used to identify outliers and perform data cleaning and optimization to obtain cleaned and optimized data. Step S22: Clustering distance weighted optimization. Specifically, by calculating the clustering weighted distance and based on the sample distances calculated in the cleaned and optimized data, weighted distance optimization is performed to obtain the weighted distance weights. Step S23: Local density enhancement. Specifically, by calculating the local density information, dynamic K-nearest neighbor value calculation is performed to obtain the adaptive K-nearest neighbor value. The calculation formula is: K dy = min(K max , density(x i )·α); Where, K dy is the adaptive K-nearest neighbor value, which is used as the clustering parameter for clustering information extraction, min(·) is the function for obtaining the minimum value, and K max is the maximum K-nearest neighbor value, density(·) is the local density calculation function, and x i is the i-th input data sample, which is used to represent the data in the original geological modeling dataset, and α is the adaptive adjustment coefficient; Step S24: Dynamic neighbor label enhancement. Specifically, through the clustering distance weighted optimization and the local density enhancement, majority voting dynamic neighbor label enhancement is performed to obtain the dynamic nearest neighbor improved label data. The calculation formula is: where \(lable(\cdot)\) is the improved function of dynamic nearest neighbor labeling, \(x\) i is the \(i\)-th input data sample, used to represent the data in the original geological modeling dataset, \(argmax\) is the function to find the maximum value, \(L\) is the label index, \(N(x\) j , \(K\) dy ) is the total number of neighbor nodes after adaptive optimization, where \(x\) j is the \(j\)-th neighbor node sample, \(j\) is the neighbor node sample index, \(K\) dy is the value of adaptive \(K\) nearest neighbors, used as the clustering parameter for clustering information extraction, \(Wdist(\cdot)\) is the weighted distance weight calculation function, \(I(L\) j = \(L)\) is the indicator function, used to judge whether the label \(L\) j corresponding to the neighbor node sample \(x\) j is equal to the label index \(L\); Step S25: Multi-level label optimization. Specifically, the multi-level K-means clustering method is used to extract hierarchical clustering information, and based on the dynamic nearest neighbor improved label data, iterative label enhancement is performed to obtain the multi-level optimized label data. Step S26: Information clustering extraction. Specifically, through the dynamic neighbor label enhancement and the multi-level label optimization, information clustering extraction of the clustering method with dynamic nearest neighbor labeling improvement is performed to obtain the geological stratification information data.

4. A 3D geological modeling optimization method based on GIS according to claim 3, characterized in that: In step S3, the borehole plane visualization is used to optimize the spatial interpolation in combination with the borehole information and perform visualization settings. Specifically, based on the geological stratification information data, the adaptive weighted Gaussian spatial interpolation method is used to perform spatial interpolation optimization and borehole plane visualization to obtain the borehole plane visualization data. The specific steps are as follows: Step S31: Borehole data standardization. Specifically, Z-score standardization processing is performed on the geological stratification information data to obtain the standardized borehole data. Step S32: Adaptive weighted operator calculation. Specifically, based on the standardized borehole data, by calculating the distance similarity in the borehole data, the adaptive weighted factor is obtained. The calculation formula is: where W(·) is an adaptive weighting factor calculation function, and X a is the first borehole data point, used to represent the data point in the standardized borehole data, X b is the second borehole data point, used to represent the neighborhood data point of the first borehole data point, exp(·) is the natural base function, d(·) is a similarity calculation function, used to represent the distance similarity calculation function and attributes, specifically calculating the Euclidean distance, and σ is the data point density parameter, used as an adaptive weighting parameter; Step S33: Adaptive Gaussian interpolation calculation. Specifically, by combining the adaptive weighted factor and setting the adaptive weighted Gaussian function, spatial interpolation calculation is performed to obtain the adaptive interpolation data. The calculation formula is: In the formula, Z(·) is a geological attribute value calculation function, used to represent the adaptive interpolation data corresponding to the interpolation point, P is the interpolation point index, N′(P) is the total number of interpolation points, and X b is the second borehole data point, used to represent the neighborhood data point of the first borehole data point, and W(P, X b ) is the adaptive weighting factor corresponding to the interpolation point P and the second borehole data point X b , and Z(X b ) is the geological attribute value of the second borehole data point X b ; Step S34: Spatial interpolation optimization. Specifically, the adaptive interpolation data is smoothed and optimized by Gaussian filtering. By combining the adaptive weighted operator and introducing the composite adaptive weighted operator, the smoothed and optimized interpolation data is obtained. The calculation formula is: Where Z s (·) is the Gaussian filtering smoothing calculation function, P is the interpolation point index, N′(P) is the total number of interpolation points, X b is the second borehole data point, W′(P, X b ) is the adaptive weighting factor introducing the composite adaptive weighting operator, Z(X b ) is the geological attribute value of the second borehole data point X b , W(P, X b ) is the adaptive weighting factor corresponding to the interpolation point P and the second borehole data point X b , α′ is the composite weighted local density adjustment parameter, density(·) is the local density calculation function; Step S35: Borehole plane visualization. Specifically, based on the smoothed and optimized interpolation data, spatial interpolation is performed to obtain the spatial interpolation reference result, and the spatial interpolation reference result and the geological stratification information data are combined for visualization to obtain the geological layer visualization plane data. Step S36: Interactive visual optimization. Specifically, the WebGIS technology is used to perform interactive borehole information visualization. The borehole information is represented through the point layer, and the depth, formation, and spatial position are visually represented through the attribute list information to obtain the borehole plane visualization data.

5. A three-dimensional geological modeling optimization method based on GIS according to claim 4, characterized in that: In step S4, the borehole model construction is used to initialize the construction of the borehole model and conduct geological simulation in combination with borehole information. Specifically, based on the visualized borehole plane data, the parameters of the borehole model are set, and the initialization of the borehole model is generated to obtain the initial borehole model data. The specific steps are as follows: Step S41: Initialize the parameters of the borehole model. Specifically, based on the initial borehole model data, the initialization parameter set for the borehole model construction is set; The initialization parameter set for the borehole model construction specifically includes the model name, borehole radius, and texture unit size parameters; Step S42: Edit the standard formation. Specifically, by setting the initialization parameter set for the borehole model construction, the initial editing of the borehole model is carried out, and the formation information data is obtained by customizing the formation information; The formation information data specifically includes formation coding, rock and soil name, formation sequence, and formation legend style; Step S43: Generate the borehole model. Specifically, based on the formation information data, the initialization parameter set for the borehole model construction is divided into different formation units, and a three-dimensional model is generated for each formation unit to obtain the initial shape set of the formation three-dimensional model. And through the texture unit size and formation legend style in the initialization parameter set for the borehole model construction and the formation information data, model optimization simulation is carried out to generate the initial borehole model data.

6. A method for optimizing 3D geological modeling based on GIS according to claim 5, characterized in that: In step S5, the geological body model construction is used to comprehensively construct the geological body model in combination with the initialized borehole model. Specifically, based on the geological stratification information data, the visualized borehole plane data, and the initial borehole model data, a multi-coupled cascade hybrid density network combining random algorithms and geostatistical calculations is used to construct the geological body model to obtain the geological body modeling data. The specific steps are as follows: Step S51: Initialize the parameters of the geological body model. Specifically, based on the geological stratification information data, the visualized borehole plane data, and the initial borehole model data, the parameters of the geological body model are set to obtain the parameter set of the geological body model; The parameter set of the geological body model specifically includes the geological body model name, horizontal grid spacing, sample influence radius, formation change coefficient, and geological body texture unit size; Step S52: Edit the geological body formation. Specifically, by setting the parameter set of the geological body model, the initial editing of the geological body formation model is carried out, and the geological body formation information data is obtained by customizing the formation information; The geological body formation information data specifically includes geological body formation coding, geological body rock and soil name, geological body formation sequence, and geological body legend style; Step S53: Geostatistical analysis. Specifically, by combining the Kriging interpolation method, based on the geological body formation information data and the parameter set of the geological body model, geostatistical analysis is carried out to obtain the reference values of the statistical attributes of the geological body interpolation points; Step S54: Construct a random simulation algorithm. Specifically, based on the reference values of the statistical attributes of the geological body interpolation points, the Monte Carlo method is used to generate spatial statistical characteristics, and through the calculation of the expected value and variance, the statistical characteristic data of the random simulation geological body interpolation points is obtained; Step S55: Construction of a multi-coupled cascaded density mixture network, specifically by training multiple standard mixture density networks and performing cascaded combination to construct the multi-coupled cascaded density mixture network, and conducting multivariate joint analysis to obtain the output of geological body spatial parameters; The multi-coupled cascaded density mixture network specifically includes an input layer, a feature extraction layer, a mixture layer, and an output layer; The calculation formula for the construction process of the multi-coupled cascaded density mixture network is: In the formula, Model GC is a multi-coupled cascade density mixing network, which is used to represent the model for generating the spatial parameters of geological body modeling and calculate the output of geological body spatial parameters. Overall, it is used to represent the sum of the outputs of the first c-layer density mixing networks. Among them, K′ is the total number of coupled layers of the density mixing network, k′ is the coupling index of the density mixing network, which is used to represent the input source of the c-th layer of the mixed density network, c is the layer index of the mixed density network, and output k′ is the output of the output layer of the k′-th layer density mixing network, which is used to represent the output of geological body spatial parameters and is used as the input data of the c + 1-th layer of the mixed density network. CN c+1 is the calculated output of the feature extraction layer of the c + 1-th layer of the mixed density network, specifically used to represent the output of the standard convolutional layer features using the non-linear activation function. Mixture c+1 is the calculated output of the mixing layer of the c + 1-th layer of the mixed density network, specifically used to represent the calculated output using the standard mixture density model. output c+1 is the output of the output layer of the c + 1-th layer of the mixed density network; Step S56: Generation of spatial parameters for geological body modeling. Specifically, based on the statistical feature data of the interpolated points of the stochastic simulated geological body, the multi-coupled cascade density mixture network is used to train the generation model of spatial parameters for geological body modeling, and the generation model of spatial parameters for geological body modeling, Model, is obtained. GC And the generation model of spatial parameters for geological body modeling, Model GC is used to generate the spatial parameters for geological body modeling, and a set of geological attribute parameters is obtained. Step S57: Construction of a geological body model, specifically constructing a geological body model scene based on the geological attribute parameter set and combining image rendering technology to obtain geological body modeling data.

7. A three-dimensional geological modeling optimization method based on GIS according to claim 6, characterized in that: In step S6, the 3D geological modeling optimization is used to store and manage the 3D geological body model and conduct comprehensive optimization. Specifically, based on the geological body modeling data, the management optimization of the geological body model is carried out, and by grouping and storing the borehole model data and the geological body model data, a model directory and a management system are established to conduct 3D geological modeling optimization and obtain a 3D geological modeling optimization database.

Images