Three-dimensional prospecting prediction method and system and storage medium

Abstract

The invention discloses a three-dimensional prospecting prediction method and system and a storage medium, and relates to the technical field of geological prospecting. The method comprises the following specific steps: collecting multi-source geological data in a target mining area, and establishing a geological database; performing data format standardization processing on the geological database to obtain preprocessed data; constructing a three-dimensional geologic model based on the preprocessed data; carrying out quantitative analysis on the three-dimensional geologic model, and extracting metallogenic favorable information; carrying out numerical simulation on the metallogenic process of the target mining area by utilizing a three-dimensional metallogenic process numerical simulation method, and extracting numerical simulation variable information; the metallogenic favorable information and the numerical simulation variable information are fused, and a three-dimensional comprehensive prospecting prediction model is constructed; and predicting a prospecting target area according to the three-dimensional comprehensive prospecting prediction model to obtain a prospecting prediction result. According to the method, a three-dimensional modeling and multi-source data fusion method is utilized, a new direction is provided for the field of prospecting prediction research, and the method has very wide application prospects.

Description

Technical Field

[0001] The present invention relates to the field of geological prospecting technology, and in particular to a three-dimensional prospecting prediction method, system and storage medium. Background Art

[0002] In recent years, with the increasing development of mineral deposits, the amount of mineral resources has been decreasing, while people's demand for mineral resources has been increasing. At the same time, the outcrop and near-surface mines that are easy to find have been decreasing. The reserves of a number of large and medium-sized mines have been gradually exhausted, and most of them have entered the ranks of crisis mines. In the existing technology, most of them use two-dimensional prospecting methods. However, the mineral deposit is not a plane, but a geological body with special significance existing in three-dimensional space. The lack of three-dimensional sense of two-dimensional maps will lead to a low accuracy rate of mineralization prediction. Therefore, for those skilled in the art, how to improve the accuracy of mineralization prediction is an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a three-dimensional prospecting prediction method, system and storage medium to solve the problems raised in the background technology.

[0004] To achieve the above object, the present invention provides the following scheme: a three-dimensional prospecting prediction method, the specific steps of which include the following:

[0005] Collect multi-source geological data in the target mining area and establish a geological database;

[0006] Performing data format standardization processing on the geological database to obtain preprocessed data;

[0007] constructing a three-dimensional geological model based on the preprocessed data;

[0008] Conducting quantitative analysis on the three-dimensional geological model to extract favorable mineralization information;

[0009] Using a three-dimensional mineralization process numerical simulation method to numerically simulate the mineralization process of the target mineral area, and extracting numerical simulation variable information;

[0010] The favorable mineralization information is integrated with the numerical simulation variable information to construct a three-dimensional comprehensive prospecting prediction model;

[0011] The prospecting target area is predicted according to the three-dimensional comprehensive prospecting prediction model to obtain the prospecting prediction result.

[0012] Preferably, the steps of performing data format standardization processing on the geological database are: first, performing data cleaning on the multi-source geological data in the geological database to remove duplicate, missing and erroneous data; secondly, performing layer standardization and coordinate system conversion on the cleaned data to make them in the same three-dimensional coordinate system; finally, performing data format standardization processing to obtain the preprocessed data.

[0013] Preferably, the multi-source geological data includes mine geological drilling data, exploration line profile data, geological plan data, gravity and magnetic data and AMT profile data.

[0014] Preferably, the three-dimensional geological model is gridded, and the model grid unit size is defined as 100m×100m×50m.

[0015] Preferably, the step of extracting the favorable mineralization information is:

[0016] Using the prospecting information method to calculate the information of each prospecting mark in the geological structure of the target mining area, the three-dimensional geological model is used to determine the information of each geological block;

[0017] Determine the weight of the information content of each geological block for mineralization based on the advantage ratio;

[0018] Based on the weight value, the comprehensive evaluation value of each model grid unit is obtained to obtain the favorable mineralization information.

[0019] Preferably, the three-dimensional comprehensive mineral prospecting prediction model is a deep fully connected neural network model based on the self-attention mechanism.

[0020] Preferably, it also includes using geostatistical methods to perform spatial interpolation on the three-dimensional geological model, interpolating the grades of all unknown blocks through known sample grades, thereby calculating the resource volume of each block, and finally statistically analyzing the resource volumes of all blocks in the target mining area to obtain the total resource volume of the ore body.

[0021] On the other hand, a three-dimensional prospecting prediction system is provided, including a data acquisition module, a preprocessing module, a three-dimensional model building module, an analysis module, a numerical simulation module, a prediction model building module, and a prediction module; wherein,

[0022] The data acquisition module is used to collect multi-source geological data in the target mining area and establish a geological database;

[0023] The preprocessing module is used to perform data format standardization processing on the geological database to obtain preprocessed data;

[0024] The three-dimensional model building module is used to build a three-dimensional geological model based on the preprocessed data;

[0025] The analysis module is used to perform quantitative analysis on the three-dimensional geological model and extract favorable mineralization information;

[0026] The numerical simulation module is used to perform numerical simulation on the mineralization process of the target mineralization area using a three-dimensional mineralization process numerical simulation method, and extract numerical simulation variable information;

[0027] The prediction model building module is used to fuse the favorable mineralization information with the numerical simulation variable information to build a three-dimensional comprehensive prospecting prediction model;

[0028] The prediction module is used to predict the prospecting target area according to the three-dimensional comprehensive prospecting prediction model to obtain the prospecting prediction result.

[0029] Finally, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the three-dimensional prospecting prediction method are implemented.

[0030] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0031] 1. By constructing a three-dimensional geological model of the target ore body, three-dimensional visualization technology is realized. The use of three-dimensional modeling + multi-source data fusion methods provides a new direction for the field of mineral prospecting and prediction research, and has a very broad application prospect.

[0032] 2. Theory-driven dynamic numerical simulation and data-driven machine learning are the two most important technical means for complex system prediction. In the present invention, these two methods are combined for mineral prospecting prediction, which improves the accuracy of mineralization prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 is a flow chart of the method of the present invention;

[0035] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The purpose of the present invention is to provide a three-dimensional prospecting prediction method. Figure 1 As shown, the specific steps include the following:

[0038] S1. Collect multi-source geological data in the target mining area and establish a geological database;

[0039] S2, performing data format standardization processing on the geological database to obtain preprocessed data;

[0040] S3, constructing a three-dimensional geological model based on the preprocessed data;

[0041] S4. Quantitatively analyze the three-dimensional geological model to extract favorable mineralization information;

[0042] S5. Use a three-dimensional mineralization process numerical simulation method to numerically simulate the mineralization process of the target mineral area and extract numerical simulation variable information;

[0043] S6, integrating the favorable mineralization information with the numerical simulation variable information to construct a three-dimensional comprehensive prospecting prediction model;

[0044] S7. Predict the prospecting target area according to the three-dimensional comprehensive prospecting prediction model to obtain the prospecting prediction result.

[0045] Furthermore, in step S1, the multi-source geological data includes mine geological drilling data, exploration line profile data, geological plan data, gravity and magnetic data, and AMT profile data.

[0046] Furthermore, in step S2, the steps of standardizing the data format of the geological database are as follows:

[0047] S21, firstly, data cleaning is performed on the multi-source geological data in the geological database to remove duplicate, missing and erroneous data;

[0048] S22, secondly, performing layer standardization and coordinate system conversion on the data after data cleaning so that the data are in the same three-dimensional coordinate system;

[0049] S23. Finally, the data format is standardized to obtain preprocessed data.

[0050] Three-dimensional geological body modeling is a technology that uses appropriate data structures, modern spatial information theory and computer technology to combine tools such as spatial information management, geological interpretation, spatial analysis and prediction, geostatistics, entity content analysis and graphic visualization in a three-dimensional environment to study geological information such as the geometric structure of geological bodies and their internal physical properties. The constructed three-dimensional geological model reflects the morphology of the ore body under the current exploration level in an intuitive and three-dimensional manner.

[0051] Furthermore, the three-dimensional geological model was gridded, and the model grid unit size was defined as 100m×100m×50m.

[0052] Further, the steps of extracting favorable mineralization information in step S4 are:

[0053] S41, using the prospecting information method to calculate the information amount of each prospecting mark in the geological structure of the target mining area for the three-dimensional geological model, and determine the information amount of each geological block;

[0054] S42, determining the weight value of the information amount of each geological block for mineralization according to the advantage ratio;

[0055] S43. Obtain a comprehensive evaluation value of each model grid unit based on the weight value to obtain favorable mineralization information.

[0056] It should be noted that the prospecting information method is a mineral resource prediction method based on factor analysis or cluster analysis. Its main idea is to obtain mineral resource information hidden behind the data through analysis and modeling of various geological, geochemical, geophysical and other factors, and to evaluate the possibility of mineral resource distribution based on the richness of information.

[0057] Furthermore, in step S5, a three-dimensional mineralization process numerical simulation is performed to provide new prediction information for the three-dimensional mineralization prediction method, obtain numerical simulation variable information, and integrate it with other prediction information in step S4 to achieve the delineation of deep prospecting target areas. In recent years, three-dimensional mineralization prediction theory and methods have been widely used in prospecting work in covered areas at home and abroad and have achieved good prospecting results; and the numerical simulation of the mineralization process is a computational analysis method that simulates the mineralization process using finite element or finite difference methods based on the intersection of multiple disciplines such as ore deposits, physics, chemistry, and computer technology, which can achieve quantitative expression of mineralization and quantitative analysis of control factors such as ore deposit scale, ore body morphology, and grade distribution and their action process.

[0058] In the three-dimensional numerical simulation of the mineralization process, the geological structure information, the physical parameters of the ore and the fluid parameters are combined to carry out multi-physics field numerical simulation calculations of the five-field coupling of force, heat, fluid, mass and chemistry in the mineralization geological process, and multiple numerical simulation variable information is obtained, including stress field parameters, temperature field parameters, fluid field parameters, mass transfer field parameters and chemical field parameters.

[0059] Furthermore, the favorable mineralization information is integrated with the numerical simulation variable information to construct a three-dimensional comprehensive prospecting prediction model, where the three-dimensional comprehensive prospecting prediction model is a deep fully connected neural network model based on the self-attention mechanism. After the three-dimensional comprehensive prospecting prediction model is constructed, the output prospecting prediction results are evaluated, and their reliability and uncertainty are analyzed. The accuracy of the prediction results is verified through field surveys and sampling analysis.

[0060] Furthermore, it also includes the use of geostatistical methods to perform spatial interpolation on the three-dimensional geological model, interpolating the grades of all unknown blocks through known sample grades, so as to calculate the resource volume of each block, and finally statistically analyzing the resource volume of all blocks in the target mining area to obtain the total resource volume information of the ore body.

[0061] On the other hand, Figure 2 As shown, a three-dimensional prospecting prediction system is provided, including a data acquisition module, a preprocessing module, a three-dimensional model building module, an analysis module, a numerical simulation module, a prediction model building module, and a prediction module; wherein,

[0062] Data acquisition module, used to collect multi-source geological data in the target mining area and establish a geological database;

[0063] A preprocessing module is used to perform data format standardization processing on the geological database to obtain preprocessed data;

[0064] A three-dimensional model building module, used to build a three-dimensional geological model based on preprocessed data;

[0065] Analysis module, used to conduct quantitative analysis of the three-dimensional geological model and extract favorable mineralization information;

[0066] Numerical simulation module, used to numerically simulate the mineralization process of the target mineral area using the three-dimensional mineralization process numerical simulation method and extract numerical simulation variable information;

[0067] A prediction model building module is used to integrate favorable mineralization information with the numerical simulation variable information to build a three-dimensional comprehensive prospecting prediction model;

[0068] The prediction module is used to predict the prospecting target area according to the three-dimensional comprehensive prospecting prediction model to obtain the prospecting prediction results.

[0069] Finally, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of a three-dimensional prospecting prediction method are implemented.

[0070] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A three-dimensional prospecting prediction method, characterized in that: The specific steps include the following: Collect multi-source geological data in the target mining area and establish a geological database; Performing data format standardization processing on the geological database to obtain preprocessed data; constructing a three-dimensional geological model based on the preprocessed data; Conducting quantitative analysis on the three-dimensional geological model to extract favorable mineralization information; Using a three-dimensional mineralization process numerical simulation method to numerically simulate the mineralization process of the target mineral area, and extract numerical simulation variable information; The favorable mineralization information is integrated with the numerical simulation variable information to construct a three-dimensional comprehensive prospecting prediction model; The prospecting target area is predicted according to the three-dimensional comprehensive prospecting prediction model to obtain the prospecting prediction result.

2. A three-dimensional prospecting prediction method according to claim 1, characterized in that: The steps of performing data format standardization processing on the geological database are as follows: first, performing data cleaning on the multi-source geological data in the geological database to remove duplicate, missing and erroneous data; second, performing layer standardization and coordinate system conversion on the cleaned data to make them in the same three-dimensional coordinate system; and finally, performing data format standardization processing to obtain the preprocessed data.

3. A three-dimensional prospecting prediction method according to claim 1, characterized in that: The multi-source geological data includes mine geological drilling data, exploration line profile data, geological plan data, gravity and magnetic data and AMT profile data.

4. A three-dimensional prospecting prediction method according to claim 1, characterized in that: The three-dimensional geological model is gridded, and the model grid unit size is defined as 100m×100m×50m.

5. A three-dimensional prospecting prediction method according to claim 4, characterized in that: The steps of extracting the favorable mineralization information are: Using the prospecting information method to calculate the information of each prospecting mark in the geological structure of the target mining area, the three-dimensional geological model is used to determine the information of each geological block; Determine the weight of the information content of each geological block for mineralization based on the advantage ratio; Based on the weight value, the comprehensive evaluation value of each model grid unit is obtained to obtain the favorable mineralization information.

6. A three-dimensional prospecting prediction method according to claim 1, characterized in that: The three-dimensional comprehensive mineral prospecting prediction model is a deep fully connected neural network model based on the self-attention mechanism.

7. A three-dimensional prospecting prediction method according to claim 1, characterized in that: It also includes spatial interpolation of the three-dimensional geological model using geostatistics, interpolating the grades of all unknown blocks using known sample grades, thereby calculating the resource volume of each block, and finally statistically analyzing the resource volumes of all blocks in the target mining area to obtain the total resource volume of the ore body.

8. A three-dimensional prospecting prediction system, characterized in that: It includes data acquisition module, preprocessing module, three-dimensional model building module, analysis module, numerical simulation module, prediction model building module and prediction module; among them, The data acquisition module is used to collect multi-source geological data in the target mining area and establish a geological database; The preprocessing module is used to perform data format standardization processing on the geological database to obtain preprocessed data; The three-dimensional model building module is used to build a three-dimensional geological model based on the preprocessed data; The analysis module is used to perform quantitative analysis on the three-dimensional geological model and extract favorable mineralization information; The numerical simulation module is used to perform numerical simulation on the mineralization process of the target mineralization area using a three-dimensional mineralization process numerical simulation method, and extract numerical simulation variable information; The prediction model building module is used to fuse the favorable mineralization information with the numerical simulation variable information to build a three-dimensional comprehensive prospecting prediction model; The prediction module is used to predict the prospecting target area according to the three-dimensional comprehensive prospecting prediction model to obtain the prospecting prediction result.

9. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of a three-dimensional prospecting prediction method as described in any one of claims 1 to 7.

Images