A three-dimensional prediction method, equipment, medium and product for magmatic rare earth ore
By constructing a geological model for prospecting of rare earth ore and using genetic algorithms and random forest algorithms, the problem of low three-dimensional prediction accuracy of magmatic rare earth ore is solved, and higher prediction accuracy and identification of prospecting target areas are achieved.
Patent Information
- Application Number
- CN202410281813.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-13
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-03-13
AI Technical Summary
The prior art has low accuracy in the three-dimensional prediction of magma rare earth ore, especially in mining areas with scarce geological information, and it is difficult to find ore-prospecting targets.
By constructing a rare earth ore prospecting geological model, using drilling data to generate drilling models and combined sample files, based on genetic algorithms and random forest algorithms, a three-dimensional geological model and attribute model are constructed to determine the mineralization probability within the predicted area.
It improves the three-dimensional prediction accuracy of magmatic rare earth ore, can more effectively analyze the nonlinear relationship between ore prospecting elements, and improves the accuracy of ore search target areas in rare earth ore exploration.
Smart Images

Figure CN118070970B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of three-dimensional mineral resource prediction, and in particular to a three-dimensional prediction method, equipment, medium and product for magmatic rare earth ore. Background Art
[0002] Three-dimensional quantitative prediction technology is an important means to carry out deep mineral resource potential evaluation and prospecting work. At present, three-dimensional quantitative prediction technology has been widely used in the prediction of metal deposits such as gold, lead, zinc, iron, and copper, but this technology is less used in the exploration and prediction of rare earth mines, and even less in the exploration of magmatic rare earth mines related to carbonate-alkaline rocks.
[0003] In the prediction of potential rare earth resources, predecessors mostly used methods such as geochemistry, geophysics, expert experience, and drilling engineering. Traditional technologies were mostly influenced by expert experience and it was difficult to discover the potential nonlinear relationship between various prospecting factors. The accuracy was low and the analysis technology was basically based on a two-dimensional level, lacking three-dimensional spatial constraints and dynamic evaluation.
[0004] The existing three-dimensional prediction scheme is only a weight-of-evidence method. It is difficult to find prospecting targets outside known ore bodies in mining areas with relatively scarce geological information, and the accuracy of prospecting is still very low. Summary of the invention
[0005] The purpose of the present invention is to provide a three-dimensional prediction method, equipment, medium and product for magmatic rare earth ore to solve the problem of low prospecting accuracy.
[0006] To achieve the above object, the present invention provides the following solutions:
[0007] A three-dimensional prediction method for magmatic rare earth ore, comprising:
[0008] Constructing a rare earth ore prospecting geological model based on the geological data of the rare earth mining area; the geological data of the rare earth mining area includes a geological topographic map of the rare earth mining area, a geological survey report, a profile of the exploration line, a mid-section plan, geophysical data, geochemical data, remote sensing data and drilling data;
[0009] Generate a drilling model and a combined sample file according to the drilling data;
[0010] Determining two-dimensional profile data according to the drilling model;
[0011] Based on the rare earth ore prospecting geological model, the geological body boundary is drawn according to the two-dimensional profile data to determine the three-dimensional profile file;
[0012] Using a genetic algorithm, constructing a three-dimensional geological model according to the three-dimensional section file; the three-dimensional geological model includes a three-dimensional ore body model, a three-dimensional structural model and a three-dimensional rock body model;
[0013] constructing an attribute model according to the combined sample file;
[0014] The attribute model and the three-dimensional geological model are imported into the prediction empty block model, the mineralization probability within the prediction area is determined using the random forest algorithm, and the location of the rare earth ore is predicted based on the mineralization probability; the prediction empty block model is constructed based on the prediction area.
[0015] Optionally, based on the rare earth mineral prospecting geological model, drawing geological body boundaries according to the two-dimensional profile data and determining a three-dimensional profile file specifically includes:
[0016] Based on the drilling model, a survey line is drawn according to the two-dimensional profile data, and the profile data in the SHP format transformed according to the WL format survey line profile diagram is imported into the corresponding survey line position;
[0017] Draw geological body boundaries for the SHP format profile data at the location of the exploration line and determine the profile file; the geological body boundaries include ore bodies, rock bodies and structures;
[0018] The drilling data is updated into the profile file to determine a three-dimensional profile file; the three-dimensional profile file includes lithology, profile frame, drilling section projection line, wellhead coordinate projection point, stratum boundary, fault line and entity contour line.
[0019] Optionally, using a genetic algorithm to construct a three-dimensional geological model according to the three-dimensional section file specifically includes:
[0020] Encoding the parameter information in the three-dimensional profile file and using the parameter information as chromosomes in a genetic algorithm; the parameter information includes geometric features of the surface, coordinates of control points, and surface type;
[0021] Randomly generate a set of initial chromosomes; the initial chromosomes represent an initial surface structure;
[0022] Using a fitness function to evaluate the degree of fit between the surface represented by each chromosome and the actual geological data, and determining the parent generation according to the degree of fit;
[0023] In the process of surface generation, a chromosome is selected from the parent generation for crossover and a new chromosome is determined; the crossover includes exchanging control point coordinates and modifying the surface type;
[0024] Introducing randomness, in the process of surface generation, mutating the new chromosome to generate a mutated chromosome; the mutation includes shape adjustment and random change of control points;
[0025] The parent generation is replaced by the chromosomes after color change to form a new population, and the parent generation is reselected until a three-dimensional surface that best conforms to geological reality is generated; the three-dimensional surface is the three-dimensional geological model.
[0026] Optionally, constructing an attribute model according to the combined sample file specifically includes:
[0027] Import the combined sample file in cps format, set the row spacing, column spacing and layer spacing, use the ordinary kriging method to interpolate the rare earth ore grade in the drill hole, and construct the attribute model in GRD format.
[0028] Optionally, based on the attribute model, the three-dimensional geological model is imported into a prediction empty block model, and a random forest algorithm is used to determine the mineralization probability within the prediction area, specifically including:
[0029] Importing the three-dimensional geological model into the prediction empty block model, and assigning information of the three-dimensional geological model to each empty block;
[0030] Based on the predicted empty block model, all empty blocks are subjected to variable binarization processing, and attributes are attached to each empty block to generate an attribute table; the attributes include ore block body characteristics; the ore block body characteristics include ore body, rock mass, structure and rare earth ore grade;
[0031] Based on the attributes, the unknown blocks are classified using the random forest algorithm to generate the mineralization probability within the predicted area; the mineralization probability is displayed in different colors in three-dimensional space.
[0032] Optionally, based on the attributes, a random forest algorithm is used to classify unknown blocks to generate a mineralization probability within the prediction area, specifically including:
[0033] A bootstrap sampling method is used to randomly extract samples from the original data set with replacement to generate multiple different training data sets to train different decision trees; the samples are each row of data in the attribute table;
[0034] Based on the voting mechanism, the mineralization probability of each new sample within the prediction area is predicted according to different decision trees.
[0035] Optionally, the mineralization probability is:
[0036]
[0037] Where P(C) is the normalized mineralization probability; N is the number of decision trees in the random forest; P i (C) is the voting probability of the i-th decision tree for category C.
[0038] A computer device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-mentioned three-dimensional prediction method for magmatic rare earth ores.
[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned three-dimensional prediction method for magmatic rare earth ores.
[0040] A computer program product includes a computer program, wherein when the computer program / instructions are executed by a processor, the steps of the above-mentioned three-dimensional prediction method for magmatic rare earth ores are implemented.
[0041] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0042] Compared with the traditional two-dimensional prospecting prediction, the embodiment of the present invention adopts a three-dimensional quantitative prediction method, and applies machine learning technologies such as genetic algorithm and random forest algorithm on the basis of the former. Based on the constructed multiple models (specifically including rare earth mineral prospecting geological model, drilling model, three-dimensional geological model, attribute model and predicted empty block model), the nonlinear relationship between prospecting elements is analyzed, and the probability of mineralization within the prediction area is determined, thereby improving the accuracy of prospecting. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] 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 work.
[0044] Figure 1 A flow chart of the three-dimensional prediction method for magmatic rare earth ores provided by the present invention;
[0045] Figure 2 This is a schematic diagram of the drilling model;
[0046] Figure 3 It is a schematic diagram of the cross-section file;
[0047] Figure 4 This is a schematic diagram of the first three-dimensional rock model;
[0048] Figure 5 This is a schematic diagram of the second three-dimensional rock model;
[0049] Figure 6 It is a schematic diagram of the three-dimensional structural model;
[0050] Figure 7 It is a schematic diagram of the three-dimensional ore body model;
[0051] Figure 8 It is a schematic diagram of the attribute model;
[0052] Fig. 9 This is a schematic diagram of the model for predicting empty blocks;
[0053] Fig.10 It is a schematic diagram of comprehensive prediction results;
[0054] Fig.11 This is the overall framework diagram of the three-dimensional prediction method for magmatic rare earth ores provided by the present invention. DETAILED DESCRIPTION
[0055] 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.
[0056] Example 1
[0057] like Figure 1 As shown, the present invention provides a three-dimensional prediction method for magmatic rare earth ore, comprising:
[0058] Step 101: construct a rare earth ore prospecting geological model based on the geological data of the rare earth mining area; the rare earth mining area geological data includes a rare earth mining area geological topographic map, a geological survey report, a survey line profile, a mid-section plan, geophysical data, geochemical data, remote sensing data and drilling data.
[0059] Furthermore, we understand the regional metallogenic geological background, mineralization type, genetic type, and metallogenic period, combine ore deposits, mineralogy, and petrology, and construct a rare earth mineral prospecting geological model based on expert experience and actual mine production conditions. Table 1 is a schematic diagram of the rare earth mineral prospecting geological model, as shown in Table 1.
[0060] Table 1
[0061]
[0062]
[0063] Step 102: Generate a drilling model and a combined sample file based on the drilling data. Figure 2 shown.
[0064] Furthermore, based on the drilling data, a digital drilling database (including the drilling location table shown in Table 2, the drilling morphology table shown in Table 3, and the sampling information table shown in Table 4) was compiled, and the Access format drilling database was imported into the Minexplorer platform to generate a drilling model, which was used to generate a cps format combined sample file for subsequent construction of the attribute model.
[0065] Table 2
[0066]
[0067] Table 3
[0068]
[0069] Table 4
[0070]
[0071] Step 103: Determine two-dimensional profile data according to the drilling model.
[0072] Furthermore, the exploration line profile in WL format was imported into the MapGIS platform, and the original data with a scale of 1:500 was transformed into the whole map. The X and Y coordinates of the points, lines and surfaces were adjusted to 1 / 2 of the original, and the transformed file (SHP format) was output. The SHP format file (a total of 18 exploration line profiles were used in this work area) was input into the ArcGIS platform to read the two-dimensional coordinates of any two boreholes (a total of 32 groups) and sorted into a library. Table 5 is the two-dimensional and three-dimensional coordinate database table.
[0073] Table 5
[0074]
[0075]
[0076] Step 104: Based on the rare earth mineral prospecting geological model, the geological body boundary is drawn according to the two-dimensional profile data to determine the three-dimensional profile file.
[0077] Furthermore, in the Minexplorer platform, the generated SHP format profile data is processed as follows:
[0078] First, according to the drilling model, 18 exploration lines are drawn on the XY plane in sequence (the X and Y coordinates in Table 5 can be used to determine a straight line between two points); secondly, the generated SHP format profile data are imported into the corresponding exploration line positions in sequence; finally, the boundaries of geological bodies such as ore bodies, rock bodies, and structures are drawn on each SHP format profile data. After completing the above steps, save it as a profile file.
[0079] The profile definition module inputs a borehole data file (generated according to Table 2, Table 3, and Table 4). Table 6 is a structure table of the borehole data file, as shown in Table 6. The output result of this module is a profile file. Table 7 is a structure table of the profile file, as shown in Table 7, where lithology, profile border, borehole section projection line, wellhead coordinate projection point, stratum boundary, fault line, and entity contour line each have a type number. The profile file obtained by the profile definition does not contain information such as stratum boundary, fault line, and entity contour line. These data are obtained and stored in the profile file when the profile is edited.
[0080] Table 6
[0081]
[0082]
[0083] Table 7
[0084]
[0085]
[0086]
[0087] Profile editing includes editing entity contours (i.e. delineating ore bodies), editing stratigraphic lines and fault lines. Minexplorer will map the spatial data on the profile to a specific position on the screen based on the profile frame data in the profile file. A curve can be generated by clicking the mouse. The screen curve is converted into a curve on the profile through inverse mapping and finally saved.
[0088] Step 105: constructing a three-dimensional geological model according to the three-dimensional section file using a genetic algorithm; the three-dimensional geological model includes a three-dimensional ore body model, a three-dimensional structural model and a three-dimensional rock body model.
[0089] Furthermore, in the Minexplorer platform, open the final saved profile file, such as Figure 3 As shown, the geological boundaries on adjacent sections are connected. Through this step, a three-dimensional ore body model, a three-dimensional structural model, and a three-dimensional rock body model are generated in sequence (the boundaries of the geological bodies such as the ore body, rock body, and structure on each section have been drawn. In this step, it is only necessary to connect the boundaries of various geological bodies on adjacent sections one by one. The connection of two closed curves into a body is achieved through a genetic algorithm). Figure 4-Figure 7 , save as a gbd format solid model file.
[0090] Furthermore, the spatial surface is stored in a profile file. Table 8 is a profile file structure table. The structure of this file is shown in Table 8. A spatial surface is composed of multiple surface patches. Therefore, spatial surface patches must be generated before generating a spatial surface. Minexplorer uses a genetic algorithm to generate surface patches. Surfaces and surface patches are represented by irregular triangulated networks (TIN).
[0091] Table 8
[0092]
[0093]
[0094]
[0095] The genetic algorithm (GA) operates as follows when generating surfaces:
[0096] Step 1: Encoding. Encode the parameter information of the 3D profile file and represent the surface parameters (including the geometric features of the surface, the coordinates of the control points, the surface type, etc.) as chromosomes in the genetic algorithm.
[0097] Step 2: Initialize the population. Randomly generate a set of initial chromosomes, which represent the initial surface structure, including simple shapes or surfaces with certain characteristics.
[0098] Step 3: Fitness evaluation. The fitness function is used to evaluate the degree of fit between the surface represented by each chromosome and the actual geological data (strike, dip, inclination). The fitness function can be the smoothness of the surface, etc.
[0099] Step 4: Selection. Select a portion of excellent chromosomes as parents based on chromosome fitness to produce offspring.
[0100] Step 5: Crossover. Select chromosomes from the parent generation for crossover to produce new chromosomes. In surface generation, crossover can include exchanging control point coordinates, modifying surface types, etc.
[0101] Step 6: Mutation. Introduce a certain amount of randomness. During the surface generation process, the mutation can include slight shape adjustments, random changes in control points, etc.
[0102] Step 7: Replacement. According to a certain replacement strategy (selective replacement, retaining the one closer to the actual geological data), the parent generation is replaced with the newly generated chromosome to form a new population.
[0103] Step 8: Iteration. Repeat step 4 to step 7 until a three-dimensional surface that best fits the geological reality is generated.
[0104] Step 106: construct an attribute model according to the combined sample file.
[0105] Furthermore, the status and function of the attribute model are consistent with the three-dimensional geological model, but the type and model construction method are different. Import the above cps format combined sample file, set the row spacing, column spacing, and layer spacing to 20m, 20m, and 3m respectively, and use the ordinary kriging method to interpolate the rare earth ore grade in the drill hole, such as Figure 8 , output GRD format attribute model file.
[0106] Step 107: Import the attribute model and the three-dimensional geological model into the prediction empty block model, use the random forest algorithm to determine the mineralization probability within the prediction area, and predict the location of the rare earth ore based on the mineralization probability; the prediction empty block model is constructed based on the prediction area.
[0107] Furthermore, in the comprehensive prediction module, the operation principle in Minexplorer is as follows:
[0108] Step 1: Create a prediction empty block model based on the prediction area range (X, Y, Z range), which is also a three-dimensional model. Customize the module size, color, range, etc. Fig. 9 shown.
[0109] Step 2: Import all generated 3D models into the predicted empty block model in sequence, and each empty block will be assigned the information of each model.
[0110] Step 3: Binarize all empty blocks. Empty blocks with information are 1, and empty blocks without information are 0. At this time, each small cube is attached with attributes. Table 9 is the attribute table, as shown in Table 9.
[0111] Table 9
[0112]
[0113] Step 4: The random forest algorithm classifies the data of unknown blocks, i.e., ore bodies, which are 0, according to the data with ore block characteristics (rock mass, structure, and attribute model as features) in Table 9, i.e., ore bodies, which are 1. The classification is decided by voting based on the features.
[0114] Principle of random forest operation: First, a self-service sampling method is used to randomly extract samples with replacement from the original data set (each row of data in Table 9 is a sample) to generate multiple different training data sets. Each data set is obtained through sampling with replacement to ensure that the training set of each decision tree is slightly different; second, at each node division, the random forest only considers a part of the features for division, in order to increase the difference between trees and prevent overfitting; finally, the probability of mineralization is carried out through a voting mechanism. Each decision tree will make a prediction for a new sample, and the final prediction result is the voting result of all trees. The probability calculation can be obtained by counting the number of votes for each category and normalizing it. The formula is as follows:
[0115]
[0116] Where P(C) is the normalized mineralization probability; N is the number of decision trees in the random forest; P i (C) is the voting probability of the i-th decision tree for category C.
[0117] Step 5: The final mineralization probability can be displayed in three-dimensional space using different colors, such as Fig.10 shown.
[0118] The present invention is based on the Minexplorer platform for research and development. The idea of 3D geological modeling is consistent with the platform. First, various geological data of the study area are collected and sorted into a library, and then imported into the platform to construct each 3D geological body. Combined with the regional geological background of the study area, a prospecting geological model is constructed, favorable mineralization elements are quantitatively extracted, and the potential relationship of various prospecting elements is analyzed using the random forest algorithm. Finally, the mineralization probability is output, and the prospecting target area is delineated in combination with the 3D geological model. The overall framework is as follows Fig.11 shown.
[0119] Example 2
[0120] A computer device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the three-dimensional prediction method for magmatic rare earth ores in Example 1.
[0121] Example 3
[0122] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the three-dimensional prediction method for magmatic rare earth ores in Example 1.
[0123] Example 4
[0124] A computer program product includes a computer program, which, when executed by a processor, implements the steps of the three-dimensional prediction method for magmatic rare earth ores in Example 1.
[0125] Example 5
[0126] A computer device, which may be a database. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Wherein, the processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store pending transactions. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the three-dimensional prediction method of magmatic rare earth ore in Example 1 is implemented.
[0127] It should be noted that the object information (including but not limited to object device information, object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.
[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.
[0129] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0130] 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 prediction method for magmatic rare earth ore, characterized in that: include: Constructing a rare earth ore prospecting geological model based on the geological data of the rare earth mining area; the geological data of the rare earth mining area includes a geological topographic map of the rare earth mining area, a geological survey report, a profile of the exploration line, a mid-section plan, geophysical data, geochemical data, remote sensing data and drilling data; Generate a drilling model and a combined sample file according to the drilling data; Determining two-dimensional profile data according to the drilling model; Based on the rare earth ore prospecting geological model, the geological body boundary is drawn according to the two-dimensional profile data to determine the three-dimensional profile file; Using a genetic algorithm, a three-dimensional geological model is constructed according to the three-dimensional section file, specifically including: Encoding the parameter information in the three-dimensional profile file and using the parameter information as chromosomes in a genetic algorithm; the parameter information includes geometric features of the surface, coordinates of control points, and surface type; Randomly generate a set of initial chromosomes; the initial chromosomes represent an initial surface structure; Using a fitness function to evaluate the degree of fit between the surface represented by each chromosome and the actual geological data, and determining the parent generation according to the degree of fit; In the process of surface generation, a chromosome is selected from the parent generation for crossover and a new chromosome is determined; the crossover includes exchanging control point coordinates and modifying the surface type; Introducing randomness, in the process of surface generation, mutating the new chromosome to generate a mutated chromosome; the mutation includes shape adjustment and random change of control points; The parent generation is replaced by the chromosomes after color change to form a new population, and the parent generation is reselected until a three-dimensional surface that best conforms to the geological reality is generated; the three-dimensional surface is a three-dimensional geological model; the three-dimensional geological model includes a three-dimensional ore body model, a three-dimensional structural model and a three-dimensional rock body model; constructing an attribute model according to the combined sample file; The attribute model and the three-dimensional geological model are imported into the prediction empty block model, and the random forest algorithm is used to determine the mineralization probability within the prediction area, specifically including: Importing the three-dimensional geological model into the prediction empty block model, and assigning information of the three-dimensional geological model to each empty block; Based on the predicted empty block model, all empty blocks are subjected to variable binarization processing, and attributes are attached to each empty block to generate an attribute table; the attributes include ore block body characteristics; the ore block body characteristics include ore body, rock mass, structure and rare earth ore grade; Based on the attributes, the random forest algorithm is used to classify unknown blocks to generate the mineralization probability within the prediction area; the mineralization probability is displayed in three-dimensional space with different colors; and the location of rare earth ore is predicted based on the mineralization probability; the predicted empty block model is constructed based on the prediction area.
2. The three-dimensional prediction method for magmatic rare earth ore according to claim 1, characterized in that: Based on the rare earth ore prospecting geological model, the geological body boundary is drawn according to the two-dimensional profile data, and the three-dimensional profile file is determined, which specifically includes: Based on the drilling model, a survey line is drawn according to the two-dimensional profile data, and the profile data in the SHP format transformed according to the WL format survey line profile diagram is imported into the corresponding survey line position; Draw geological body boundaries for the SHP format profile data at the location of the exploration line and determine the profile file; the geological body boundaries include ore bodies, rock bodies and structures; The drilling data is updated into the profile file to determine a three-dimensional profile file; the three-dimensional profile file includes lithology, profile frame, drilling section projection line, wellhead coordinate projection point, stratum boundary, fault line and entity contour line.
3. The three-dimensional prediction method for magmatic rare earth ore according to claim 1, characterized in that: Constructing an attribute model according to the combined sample file specifically includes: Import the combined sample file in cps format, set the row spacing, column spacing and layer spacing, use the ordinary kriging method to interpolate the rare earth ore grade in the drill hole, and construct the attribute model in GRD format.
4. The three-dimensional prediction method for magmatic rare earth ore according to claim 1, characterized in that: Based on the above attributes, the random forest algorithm is used to classify unknown blocks and generate the mineralization probability within the predicted area, including: A bootstrap sampling method is used to randomly extract samples from the original data set with replacement to generate multiple different training data sets to train different decision trees; the samples are each row of data in the attribute table; Based on the voting mechanism, the mineralization probability of each new sample within the prediction area is predicted according to different decision trees.
5. The three-dimensional prediction method for magmatic rare earth ore according to claim 4, characterized in that: The mineralization probability is: Where P(C) is the normalized mineralization probability; N is the number of decision trees in the random forest; P i (C) is the voting probability of the i-th decision tree for category C.
6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the three-dimensional prediction method for magmatic rare earth ores as described in any one of claims 1-5.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the three-dimensional prediction method for magmatic rare earth ores described in any one of claims 1 to 5 are implemented.
8. A computer program product, comprising a computer program, characterized in that When the computer program / instructions are executed by a processor, the steps of the three-dimensional prediction method for magmatic rare earth ores described in any one of claims 1 to 5 are implemented.
Citation Information
Patent Citations
Geological exploring ore body three-dimensional modeling system
CN103729880A
Three-dimensional visual positioning prediction method for deep resources of metal ore deposit
CN115081685A
