Pot area deep brine mineralization analysis and evaluation method

Abstract

The invention relates to the technical field of metallogenic prediction and evaluation, in particular to a basin area deep brine metallogenic analysis and evaluation method, which comprises the following steps of: obtaining prospecting element characteristic information of a basin area to construct a multi-source database; constructing a three-dimensional geologic model based on the multi-source database; obtaining three-dimensional geologic models corresponding to the plurality of historical basin areas and extracting corresponding brine characteristic information; training a brine mineralization prediction model based on the brine characteristic information; obtaining a three-dimensional geologic model corresponding to the target basin area and extracting brine feature information corresponding to the target basin area to obtain target brine feature information; inputting the target brine feature information into a brine mineralization prediction model to generate a brine mineralization prediction result; the accurate three-dimensional geologic model can be constructed, brine mineralization prediction can be performed, the efficiency and accuracy of geological exploration are improved, and intelligent management and efficient prediction of brine resources are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of metallogenic prediction and evaluation, and particularly to a method for analyzing and evaluating deep brine metallogenesis in basin areas. Background Technique

[0002] In geological exploration and resource development, basins, as important sedimentary tectonic units, contain rich mineral resources, especially brine resources. Brine resources are of great significance to industries such as chemical engineering and energy. However, the brine metallogenic mechanism in basin areas is complex and is affected by various geological structures, geophysical, and geochemical factors.

[0003] Traditional brine resource evaluation methods often rely on limited data sources, and the description of complex geological features is not accurate enough, lacking the ability to comprehensively consider multiple data sources, thus affecting the efficiency and accuracy of predicting and evaluating the brine metallogenic potential in basin areas.

[0004] Therefore, we propose a method for analyzing and evaluating deep brine metallogenesis in basin areas to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for analyzing and evaluating deep brine metallogenesis in basin areas to solve the problems raised in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A method for analyzing and evaluating deep brine metallogenesis in basin areas, the method includes the following steps:

[0007] Obtain the prospecting element feature information of the basin area to construct a multi-source database, wherein the prospecting element feature information includes geological structure feature information, geophysical feature information, and geochemical feature information; the multi-source database includes the prospecting element feature information and the monitoring terminals corresponding to each prospecting element feature information respectively;

[0008] Construct a three-dimensional geological model based on the multi-source database, wherein the multi-source database is divided into a historical database and a target database;

[0009] Obtain the three-dimensional geological models corresponding to multiple historical basin areas respectively and extract the corresponding brine feature information, wherein the brine feature information includes brine level distribution and longitudinal burial depth feature information and metallogenic mechanism feature information; train a brine metallogenesis prediction model based on the brine feature information;

[0010] Obtain the three-dimensional geological model corresponding to the target basin area and extract the brine feature information corresponding to the target basin area to obtain target brine feature information; input the target brine feature information into the brine metallogenesis prediction model to generate a brine metallogenesis prediction result;

[0011] Compare and evaluate the prediction results of brine mineralization with standard brine deposits, and divide the target basin area into ore-forming potential areas of different grades based on the evaluation results.

[0012] Preferably, the step of obtaining the ore prospecting element characteristic information of the basin area to construct a multi-source database, wherein the ore prospecting element characteristic information includes geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information, includes:

[0013] Collect the geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information of the basin area; upload the geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information to the database uniformly and store them classified; register monitoring terminals corresponding to the geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information respectively; form a multi-source database based on the ore prospecting element characteristic information and the monitoring terminals corresponding to each ore prospecting element characteristic information.

[0014] Preferably, the step of constructing a three-dimensional geological model of deep brine in the basin area based on the multi-source database includes:

[0015] Obtain multiple historical databases corresponding to the three-dimensional geological models of multiple geological evolution stages corresponding to multiple historical basin areas respectively; collect the ore prospecting element characteristic information of the target basin area to construct a target database; screen out the historical database with the highest similarity to the target database from multiple historical databases to obtain a preselected database, and obtain the corresponding three-dimensional geological model of the preselected database to obtain an initial geological model; determine the difference characteristic information based on the target database and the preselected database, wherein the difference characteristic information includes explicit difference information and implicit difference information; adjust the initial geological model based on the difference characteristic information to obtain the three-dimensional geological model corresponding to the target database.

[0016] Preferably, the step of determining the difference characteristic information based on the target database and the preselected database, wherein the difference characteristic information includes explicit difference information and implicit difference information, includes:

[0017] Obtain the topographic information of the target basin area, lay multiple feature points with associated relationships on the target basin area according to the topographic information, and extract the feature information corresponding to the multiple feature points with associated relationships to form the geological structure characteristic information in the target database;

[0018] Lay filling points corresponding to the initial geological model to form a filling frame; obtain the same data in the geological structure characteristic information and the preselected database, and fill the feature points corresponding to the geological structure characteristic information into the filling frame of the initial geological model according to the same data to form an initial three-dimensional model;

[0019] Take the geological structure feature information in the target database corresponding to the unfilled filling points on the filling rack as explicit distinguishing information; compare the target database with the preselected database, and extract other distinguishing information that is not explicit distinguishing information as implicit distinguishing information;

[0020] Based on the explicit distinguishing information and the implicit distinguishing information, form distinguishing feature information, and mark the filling points corresponding to the distinguishing feature information in the initial geological model to obtain marked filling points.

[0021] Preferably, the steps of obtaining the terrain information of the target basin area, setting multiple feature points with associated relationships according to the terrain information, and extracting the feature information corresponding to the multiple feature points with associated relationships to form the geological structure feature information in the target database include:

[0022] Obtain the terrain information of the target basin area, and obtain the feature lines and corner points of the terrain information;

[0023] Lay multiple feature points corresponding to the corner points and feature lines within the target basin area, where the feature line is a line segment with an obvious trend or morphological change in the terrain information, and the corner point is a point where the feature lines intersect or the morphology changes significantly;

[0024] Extract the corner points corresponding to each terrain information and the feature points corresponding to the feature lines, and connect them in sequence according to the terrain information to obtain multiple feature points with associated relationships;

[0025] Extract the feature information corresponding to the multiple feature points with associated relationships to form the geological structure feature information in the target database.

[0026] Preferably, the steps of adjusting the geological model template based on the distinguishing feature information to obtain the three-dimensional geological model corresponding to the target database include:

[0027] Obtain each filling point of the initial geological model, and register a monitoring end corresponding to the filling point; establish a connection link between the monitoring end corresponding to the filling point and the monitoring end of the geological structure feature information in the target database, and set a trigger condition and a transmission switch for the connection link, where the trigger condition is that there is explicit distinguishing information for the filling point corresponding to the connection link;

[0028] When the connection link corresponding to the marked filling point reaches the trigger condition, start the transmission switch of the corresponding connection link, transmit the geological structure feature information in the target database to the corresponding marked filling point via the connection link, replace the geological structure feature information of the preselected database corresponding to the filling point, and perform a preliminary adjustment on the initial three-dimensional model based on the replaced geological structure feature information;

[0029] Obtain implicit difference information, and perform secondary adjustment on the initially adjusted initial three-dimensional model based on the implicit difference information to obtain the three-dimensional geological model corresponding to the target database.

[0030] Preferably, the steps of obtaining the three-dimensional geological models corresponding to multiple historical basin regions respectively and extracting the corresponding brine characteristic information, wherein the brine characteristic information includes brine level distribution, longitudinal burial depth characteristic information, and ore-forming mechanism characteristic information; and training the brine ore-forming prediction model based on the brine characteristic information include:

[0031] Obtain the three-dimensional geological models corresponding to multiple historical basin regions respectively, and perform spatial coincidence processing on the three-dimensional geological models corresponding to multiple historical basin regions respectively to generate a coincidence region and non-coincidence regions; identify and separate the brine characteristic information of the coincidence region and multiple non-coincidence regions; perform comprehensive processing on the separated brine characteristic information, remove the brine characteristic information of the coincidence region, retain the data of the non-coincidence regions, form an optimized data set, and use the optimized data set to train the ore-forming prediction model.

[0032] Preferably, the steps of comparing and evaluating the brine ore-forming prediction result with the standard brine deposit and dividing the target basin region into different grades of ore-forming potential regions based on the evaluation result include:

[0033] Obtain the standard brine deposit information, determine the brine ore-forming information of the target basin region based on the brine ore-forming prediction result, and compare the brine deposit information with the brine ore-forming information to determine the difference information; determine the division criteria for dividing the ore-forming potential regions based on the difference information; divide the target basin region into different grades of ore-forming potential regions based on the division criteria.

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] 1. By collecting the geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information of the basin region, and uniformly uploading them to the database for classification storage, a multi-source database is constructed. This method can effectively integrate multiple data sources and provide comprehensive data support for subsequent three-dimensional geological modeling and brine ore-forming prediction;

[0036] 2. Based on the multi-source database of ore prospecting elements, by comparing the historical database with the target database, the difference characteristic information is identified, and the initial geological model is adjusted to obtain the three-dimensional geological model corresponding to the target database, which can more accurately describe the geological characteristics of the basin region and improve the accuracy and reliability of the three-dimensional geological model;

[0037] 3. By extracting the brine characteristic information of multiple historical basin areas and training a brine mineralization prediction model based on this characteristic information, it is possible to comprehensively consider the influence of multiple data sources on brine mineralization. By optimizing the data set, removing the brine characteristic information in the overlapping areas and retaining the data in the non-overlapping areas, the accuracy and generalization ability of the prediction model are further improved.

[0038] 4. By automatically collecting, integrating and analyzing multi-source data information in the basin area, constructing an accurate three-dimensional geological model and conducting brine mineralization prediction, the efficiency and accuracy of geological exploration are improved, and the intelligent management and efficient prediction of brine resources are realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] 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. Obviously, the described embodiments are only some embodiments of the present invention, rather than all 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.

[0042] Embodiment

[0043] Please refer to Figure 1 , the present invention provides a technical solution for a method for analyzing and evaluating deep brine mineralization in a basin area: a method for analyzing and evaluating deep brine mineralization in a basin area, including the following steps:

[0044] S1: Obtain the prospecting element characteristic information of the basin area to construct a multi-source database. Among them, the prospecting element characteristic information includes geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information; the multi-source database includes the prospecting element characteristic information and the monitoring terminals corresponding to each prospecting element characteristic information respectively;

[0045] Steps for obtaining prospecting element feature information of the basin area to construct a multi-source database, where the prospecting element feature information includes geological structure feature information, geophysical feature information, and geochemical feature information are as follows: collecting geological structure feature information, geophysical feature information, and geochemical feature information of the basin area; uniformly uploading the geological structure feature information, geophysical feature information, and geochemical feature information to the database and storing them classified; registering monitoring terminals corresponding to the geological structure feature information, geophysical feature information, and geochemical feature information respectively; forming a multi-source database based on the prospecting element feature information and the monitoring terminals corresponding to each prospecting element feature information;

[0046] It should be noted that the specific contents of the geological structure feature information, geophysical feature information, and geochemical feature information in the collection basin area are as follows: The geological structure feature information mainly includes the geographical location, topography, stratigraphic structure, and structural features of the basin. Geological information such as the stratigraphic structure and structural features of the basin can be obtained through field investigations and geological section measurements. Large-scale topographical information of the basin, including elevation, slope, and aspect, can be obtained using technologies such as satellite remote sensing and unmanned aerial vehicle remote sensing. Combining the geological structure features of the western part and the periphery of the Qaidam Basin, through field geological surveys and structural analyses, the spatio-temporal evolution process of the Cenozoic anticline structures within the basin, the development characteristics of sedimentary strata and paleocurrents, and the tectonic background of the basin periphery are analyzed in detail. The geophysical feature information mainly reflects the geophysical field characteristics of the basin, such as the gravity field, magnetic field, and conductivity. Information such as the geological structure and lithological distribution of the basin can be inferred by measuring the gravity anomaly distribution within the basin. The distribution of magnetic rock bodies and structural features in the basin can be revealed by measuring the magnetic anomaly distribution within the basin. The distribution of groundwater and rocks in the basin can be detected using the changes in electrical parameters such as resistivity and conductivity. By using tectonothermal chronology testing techniques and combining reflection seismic and magnetotelluric sounding profile data, the key geological elements for deep brine mineralization are accurately identified. The geochemical feature information mainly reflects the element distribution and anomaly characteristics within the basin. Soil geochemical surveys can be carried out: soil samples within the basin are collected and their element contents and distribution characteristics are analyzed. Rock geochemical analysis: Rock samples within the basin are collected and analyzed for element contents, isotope ratios, etc. Water body geochemical monitoring: Groundwater, surface water, etc. within the basin are sampled and analyzed to understand their chemical compositions and sources. Through source rock and deep brine geochemical testing techniques, the contents and isotope ratios of key ore-forming elements such as potassium, lithium, and boron are analyzed to determine the genetic relationship between deep brines and Cenozoic volcanic rocks in the Hoh Xil area in the southern part of the Qaidam Basin. A multi-source database is constructed based on the geological structure feature information, geophysical feature information, and geochemical feature information for storage and management. According to the type and scale of the data, a suitable database management system (DBMS) is selected. According to the characteristics of the data and business requirements, a suitable data model is designed to organize and manage the data. The data model can include a vector data model (used to represent geometric objects such as points, lines, and polygons) and a raster data model (used to represent continuously covered geographical areas such as images and remote sensing data), and data from different sources are integrated and standardized to ensure the accuracy, consistency, and comparability of the data;

[0047] S2: Construct a 3D geological model based on the multi-source database for prospecting elements, where the multi-source database is divided into a historical database and a target database;

[0048] Construct a 3D geological model of the deep basin structure and brine reservoir based on the multi-source database of prospecting elements; construct an ore-forming model (reveal the ore-forming model of the Paleogene-Neogene anticlinal fold-type deep brine, and clarify the roles of anticlinal structures, fault systems, and sedimentary strata in brine mineralization. Propose the key controlling factors for brine mineralization (such as tectonic traps, hydrothermal activities, evaporation and concentration, etc.)).

[0049] The steps for constructing a 3D geological model of regional deep brine in the basin based on the multi-source database include: obtaining multi-source databases corresponding to the 3D geological models of multiple geological evolution stages corresponding to multiple historical basin regions to obtain multiple historical databases; collecting the prospecting element characteristic information of the target basin region to construct a multi-source database to obtain a target database; screening out the historical database with the highest similarity to the target database from multiple historical databases to obtain a preselected database, and obtaining the 3D geological model corresponding to the preselected database to obtain an initial geological model; determining the distinguishing feature information based on the target database and the preselected database, where the distinguishing feature information includes explicit distinguishing information and implicit distinguishing information; adjusting the initial geological model based on the distinguishing feature information to obtain the 3D geological model corresponding to the target database;

[0050] The steps for determining the distinguishing feature information based on the target database and the preselected database, where the distinguishing feature information includes explicit distinguishing information and implicit distinguishing information, include: obtaining the topographic information of the target basin region, laying multiple associated feature points on the target basin region according to the topographic information, and extracting the feature information corresponding to the multiple associated feature points to form the geological structure feature information in the target database; arranging filling points corresponding to the initial geological model to form a filling frame; obtaining the same data in the geological structure feature information and the preselected database, and filling the feature points corresponding to the geological structure feature information into the filling frame of the initial geological model according to the same data to form an initial 3D model; taking the geological structure feature information in the target database corresponding to the unfilled filling points on the filling frame as explicit distinguishing information; comparing the target database with the preselected database, and extracting other distinguishing information that is not explicit distinguishing information as implicit distinguishing information; forming distinguishing feature information based on the explicit distinguishing information and the implicit distinguishing information, and marking the filling points corresponding to the distinguishing feature information in the initial geological model to obtain marked filling points;

[0051] Specifically, the filling points are on the initial geological model, the feature points are on the target basin area corresponding to the target database, the feature points are bound to the explicit feature information, the explicit feature information is used to compare with the pre-selected database to determine the explicit distinguishing information through the filling frame, and the explicit distinguishing information and implicit distinguishing information are determined according to the position correspondence between the filling points and the feature points, so as to facilitate the subsequent adjustment of the initial geological model; use remote sensing technology or field measurement to obtain the terrain information of the target basin area, including but not limited to elevation, slope, landform type, etc.

[0052] According to the terrain information, multiple characteristic points with correlation are laid out in the target basin area. These characteristic points can be the intersection points of geological structure lines, stratigraphic interface points, lithology change points, etc., to ensure that the characteristic points can fully reflect the geological characteristics of the target area; geological surveys are conducted on each characteristic point, and the corresponding characteristic information, such as lithology, stratigraphy, structure, etc., are collected and recorded to form the geological structure characteristic information in the target database; filling points are laid out in the initial geological model to form a filling frame, and these filling points serve as carriers for subsequent filling of geological structure characteristic information; the same data as that in the pre-selected database are extracted from the target database, where the same data refers to the same data items, such as the stratigraphy in the geological structure characteristic information in the target database. The information is the same as the stratigraphic information in the pre-selected database, where the stratigraphic information at least includes the thickness, lithology combination, sedimentary structure and other characteristics of the stratigraphic formation, so as to judge whether the stratigraphic information is the same through the sedimentary sequence of the stratigraphic formation, and then determine the same data in the pre-selected database and the target database, and when determining the same data, a certain deviation threshold can also be set. For example, when the stratigraphic information in the pre-selected database is not completely consistent with the stratigraphic information in the target database, it means that there is a deviation between the two. When the deviation between the two is less than the preset deviation threshold, the two can also be considered to be the same data. When the deviation between the two is greater than the preset deviation threshold, it is determined to be different data, that is, data belonging to distinguishing characteristic information;

[0053] According to multiple geological structure characteristic information, the characteristic points corresponding to the geological structure characteristic information in the target database are filled into the filling frame of the initial geological model to form an initial three-dimensional model. The unfilled filling points on the filling frame are identified and marked, and the geological structure characteristic information in the target database corresponding to these filling points is the explicit difference information. The target database and the preselected database are comprehensively compared, and other difference information except the explicit difference information is extracted, such as the differences in geological structure details, formation thickness changes, etc., such as the difference information of geophysical characteristic information and the difference information of geochemical characteristic information, as the implicit difference information. The implicit difference information is obtained by analyzing the implicit characteristic information, and the implicit characteristic information is characteristics such as groundwater flow patterns and geological stress states that need to be obtained through model simulation or complex analysis. Based on the explicit difference information and the implicit difference information, a complete difference characteristic information is constituted;

[0054] In the initial geological model, the filling points corresponding to the difference characteristic information are marked to obtain marked filling points, which are used to reflect the differences in geological structure characteristic information between the target database and the preselected database. For subsequent adjustment of the initial geological model according to the marked filling points, so as to improve the accuracy and practicability of the model, realize the rapid comparison and difference identification of geological structure characteristic information between the target database and the preselected database, and improve the efficiency of three-dimensional geological model construction. Through the comprehensive extraction and marking of the explicit difference information and the implicit difference information, the differences in geological structure characteristic information of the target basin area can be more comprehensively reflected, thus improving the accuracy of three-dimensional geological model construction.

[0055] The steps of obtaining the terrain information of the target basin area, setting multiple associated characteristic points according to the terrain information, and extracting the characteristic information corresponding to the multiple associated characteristic points to form the geological structure characteristic information in the target database include: obtaining the terrain information of the target basin area, obtaining the characteristic lines and corner points of the terrain information, laying multiple characteristic points in the target basin area corresponding to the corner points and the characteristic lines, where the characteristic line is a line segment with an obvious trend or morphological change in the terrain information, and the corner point is a point where the characteristic lines intersect or the morphology changes significantly; extracting the corner points corresponding to each terrain information and the characteristic points corresponding to the characteristic lines and connecting them in sequence according to the terrain information to obtain multiple associated characteristic points, and extracting the characteristic information corresponding to the multiple associated characteristic points to form the geological structure characteristic information in the target database;

[0056] It should be noted that the terrain information may include characteristic information indicating the terrain conditions such as fault information, fold information, joint information, formation information, and thickness information;

[0057] The specific content of laying multiple feature points for the corresponding corner points and feature lines within the target basin area is as follows: According to the fault information, determine the strike and fault plane of the fault line, set fault feature points at the intersections of the fault line and the fault plane, and lay fault-related feature points on both sides of the fault line at a certain distance and angle; According to the fold information, determine the strike and fold form of the fold axis, set fold feature points at the inflection points of the fold axis, and lay fold-related feature points on both sides of the fold axis according to the changing trend of the fold form; According to the joint information, determine the strike and dip angle of the joint plane, set joint feature points at the intersections of the joint planes, and lay joint-related feature points on the extension direction of the joint plane at a certain distance and angle; According to the stratigraphic information, determine the stratification interface and formation thickness of the strata, set stratigraphic feature points at the intersections of the stratification interfaces of the strata, and lay stratum-related feature points inside the strata according to the changing trend of the formation thickness; According to the thickness information, determine the range of changes in the formation thickness within the target basin area, set thickness feature points in areas with significant thickness changes, and lay thickness-related feature points around the thickness change area according to the changing trend of the thickness. Herein, the "area with significant thickness changes" refers to the area where the thickness of the strata or ore bodies has an obvious difference compared with the adjacent area. For example, at certain positions, the thickness of the strata or ore bodies may suddenly increase or decrease, forming an obvious discontinuity. It is possible to judge whether there is an obvious difference between the thickness of the target area and the thickness of the adjacent area by presetting a difference threshold. When it exceeds the preset difference threshold, it indicates an obvious difference, that is, it indicates that the target area and the adjacent area belong to the area with significant thickness changes. Otherwise, it indicates that there is no obvious difference, that is, it indicates that the target area and the adjacent area do not belong to the area with significant thickness changes.

[0058] Specifically, obtain the topographic information of the target basin area through geological exploration and remote sensing technology, including fault information, fold information, joint information, stratigraphic information, and thickness information.

[0059] Then, according to the topographic information, determine the feature lines and corner points. For example, the fault line is the feature line of the fault information, and the intersection of the fault line and the fault plane is the fault feature point; the fold axis is the feature line of the fold information, and the inflection point of the fold axis is the fold feature point; the joint plane is the feature plane of the joint information, and the intersection of the joint planes is the joint feature point; the stratification interface of the strata is the feature plane of the stratigraphic information, and the intersection of the stratification interfaces of the strata is the stratigraphic feature point; the area with significant thickness changes is the feature area of the thickness information, and the points in this area are the thickness feature points.

[0060] Next, multiple feature points are laid out in the target basin area. Specifically, according to the fault information, the fault feature point is set at the intersection of the fault line and the fault plane, and the fault-related feature points are laid on both sides of the fault line at a certain distance and angle (such as every 100 meters and 45 degrees); according to the fold information, the fold feature point is set at the turning point of the fold axis, and the fold-related feature points are laid on both sides of the fold axis according to the change trend of the fold morphology (such as the bending degree and direction of the fold); according to the joint information, the joint feature point is set at the intersection of the joint plane, and the joint-related feature points are laid in the extension direction of the joint plane at a certain distance and angle (such as every 50 meters and 30 degrees); according to the formation information, the formation feature point is set at the intersection of the formation stratification interface, and the formation-related feature points are laid inside the formation according to the change trend of the formation thickness (such as gradually thickening or thinning); according to the thickness information, the thickness feature point is set in the area where the thickness changes significantly, and the thickness-related feature points are laid around the thickness change area according to the thickness change trend (such as from thick to thin or from thin to thick).

[0061] Finally, the corner points corresponding to each terrain information and the feature points corresponding to the feature lines are extracted, and they are connected in sequence according to the terrain information to obtain multiple feature points with associated relationships. Then, the feature information of these feature points (such as location coordinates, elevation, stratigraphic code, lithology description, etc.) is extracted to form the geological structure feature information in the target database.

[0062] It can obtain the topographic information of the target basin area, set multiple characteristic points with correlation based on the topographic information, and then extract the characteristic information of these characteristic points to form the geological structure characteristic information in the target database, so as to realize the automatic and accurate extraction of the geological structure characteristic information of the target basin area, and facilitate the subsequent evaluation of the resource volume;

[0063] The step of adjusting the geological model template based on the distinguishing characteristic information to obtain the three-dimensional geological model corresponding to the target database includes: obtaining each filling point of the initial geological model, and registering the monitoring end corresponding to the filling point; establishing a connection link between the monitoring end corresponding to the filling point and the monitoring end of the geological structure characteristic information in the target database, and setting a trigger condition and a transmission switch corresponding to the connection link, wherein the trigger condition is that there is explicit distinguishing information at the filling point corresponding to the connection link; when the link link corresponding to the marked filling point reaches the trigger condition, the transmission switch of the corresponding link link is started, and the geological structure characteristic information in the target database is transmitted to the corresponding marked filling point via the connection link, and the geological structure characteristic information of the pre-selected database corresponding to the filling point is replaced, and the initial three-dimensional model is preliminarily adjusted based on the replaced geological structure characteristic information; implicit distinguishing information is obtained, and the initial three-dimensional model after the preliminary adjustment is adjusted again based on the implicit distinguishing information to obtain the three-dimensional geological model corresponding to the target database;

[0064] Specifically, a geological information may include multiple filling points. The filling points of the initial geological model have the same function as the characteristic points of the target basin area. One is used to determine the distribution of the preselected database corresponding to the initial geological model on the initial geological model, and the other is used to determine the distribution of the target database on the target basin area. And an explicit characteristic information of a virtual target basin area is constructed according to the characteristic points, and the explicit characteristic information of the target basin area is compared with the explicit characteristic information of the initial geological model to obtain explicit difference information. Among them, the explicit characteristic information is characteristics such as formation thickness and lithology distribution that can be directly observed; the initial geological model is filled through the filling points, and the filling points with the same data as the target basin area are found, and the unfilled filling points are marked. The initial geological model after filling and marking is used as the initial three-dimensional model, and the geological structure characteristic information of the preselected database corresponding to the explicit difference information is transmitted to the corresponding filling points according to the trigger condition and the transmission switch, so as to complete the preliminary adjustment of the initial three-dimensional model. Then, the initial three-dimensional model is adjusted twice according to the implicit difference information to obtain a three-dimensional geological model. By distinguishing and processing the explicit difference information and the implicit difference information, the precise adjustment of the initial three-dimensional geological model is realized. The adjusted model can more accurately reflect the geological structure characteristic information in the target database;

[0065] S3: Obtain the three-dimensional geological models corresponding to multiple historical basin areas respectively and extract the corresponding brine characteristic information. Among them, the brine characteristic information includes brine level distribution, longitudinal burial depth characteristic information and ore-forming mechanism characteristic information; Train a brine ore-forming prediction model based on the brine characteristic information;

[0066] The steps of obtaining the three-dimensional geological models corresponding to multiple historical basin areas respectively and extracting the corresponding brine characteristic information, and training a brine ore-forming prediction model based on the brine characteristic information include: Obtain the three-dimensional geological models corresponding to multiple historical basin areas respectively and perform coincidence processing on the three-dimensional geological models corresponding to multiple historical basin areas in space to generate a coincidence area and non-coincidence areas; Identify and separate the brine characteristic information of the coincidence area and multiple non-coincidence areas; Perform comprehensive processing on the separated brine characteristic information, remove the brine characteristic information of the coincidence area, and retain the data of the non-coincidence areas to form an optimized data set, and use the optimized data set to train an ore-forming prediction model;

[0067] Specifically, the "3D geological models of multiple historical basin regions" refer to the 3D geological models of different historical periods corresponding to multiple different basins. Then, extract the brine characteristic information corresponding to each of the multiple 3D geological models, and use the brine characteristic information presented by these previously adopted 3D geological models to train and verify the ore-forming prediction model. The extraction of brine activity characteristic information means analyzing the flow path, activity intensity, etc. of brine in the 3D geological model. Combining geological structures, stratigraphic information, etc., infer the source, migration, and enrichment laws of brine; the extraction of ore-forming mechanism characteristic information means studying the relationship between brine and ore-forming elements, analyzing how brine carries, transports, and precipitates ore-forming elements, analyzing the impact of brine activity on ore-forming potential, and determining the favorable conditions and regions for ore formation; by overlapping the 3D geological models of multiple historical basin regions, identify and separate the overlapping regions. Here, the classification is to only separate the redundant overlapping regions. For example, if there is an overlapping region between two 3D geological models, only keep the overlapping region part of one 3D geological model; integrate the part of the overlapping region that is retained with the non-overlapping region parts. Here, the non-overlapping regions include the non-overlapping regions of the two 3D geological models, which is equivalent to having three parts of content, one is the overlapping region, one is the non-overlapping region of one 3D geological model, and the non-overlapping region of the other 3D geological model, and obtain the comprehensive brine characteristic information of the three to train the ore-forming prediction model, so as to avoid data redundancy, improve the representativeness and efficiency of the data set, and thus improve the training efficiency of the ore-forming prediction model.

[0068] It should be noted that the specific content of training the brine ore-forming prediction model based on brine characteristic information is as follows: According to the brine characteristic information, select the characteristic variables that have an important impact on brine ore formation. Further process the characteristic variables, such as feature scaling, feature transformation, etc., to improve the prediction performance of the model; select a suitable machine learning algorithm or deep learning model as the brine ore-forming prediction model, such as logistic regression, support vector machine, random forest, convolutional neural network, etc. Use the prepared data and characteristic variables to train the model, learn the relationship between brine ore formation and geological attributes, and use methods such as cross-validation to verify the model and evaluate the prediction performance and stability of the model. Optimize the model according to the verification results, including adjusting model parameters, adding characteristic variables, etc., to improve the prediction accuracy of the model.

[0069] S4: Obtain the 3D geological model corresponding to the target basin region and extract the brine characteristic information corresponding to the target basin region to obtain the target brine characteristic information; input the target brine characteristic information into the brine ore-forming prediction model to generate the brine ore-forming prediction result;

[0070] S5: Compare and evaluate the brine ore-forming prediction result with the standard brine deposit, and divide the target basin region into different grades of ore-forming potential regions based on the evaluation result.

[0071] The steps of comparing and evaluating the brine mineralization prediction results with standard brine deposits and dividing the target basin area into ore-forming potential areas of different grades based on the evaluation results include: obtaining the information of standard brine deposits, determining the brine mineralization information of the target basin area based on the brine mineralization prediction results, and comparing the brine deposit information with the brine mineralization information to determine the difference information; determining the division criteria for dividing the ore-forming potential areas based on the difference information; dividing the target basin area into ore-forming potential areas of different grades based on the division criteria;

[0072] Specifically, by consulting relevant literature and geological data, collect information such as the geological characteristics, geochemical characteristics, ore-forming mechanism, and resource volume of standard brine deposits. According to the results output by the brine mineralization prediction model, sort out information such as the brine mineralization possibility, enrichment degree, and distribution range of the target basin area. Compare the similarity and difference between the prediction results and standard brine deposits. Compare and analyze the similarities and differences between the prediction results and standard brine deposits from aspects such as geological background, geochemical characteristics, and ore-forming mechanism. According to the comparative analysis results, combined with the geological characteristics and brine mineralization laws of the target basin area, determine the criteria for dividing the ore-forming potential areas. The division criteria can include multiple aspects such as the possibility of brine mineralization, enrichment degree, distribution range, and ore-controlling factors. According to the division criteria, divide the target basin area into ore-forming potential areas of different grades. The grade division can include high-potential areas, medium-potential areas, low-potential areas, etc. Draw the ore-forming potential map with the division results to visually display the ore-forming potential distribution of the target basin area. The ore-forming potential map should include information such as geological background, brine mineralization prediction results, division criteria, and grade division. By comparing and evaluating the brine mineralization prediction results with standard brine deposits and dividing the target basin area into ore-forming potential areas of different grades based on the evaluation results, estimate the resource volume of deep brine according to parameters such as the distribution range, thickness, and porosity of the brine reservoir, and evaluate the resource potential of brine mineralization in combination with the content of key ore-forming elements in the brine; according to the evaluation results of the ore-forming model and resource potential, optimize the favorable sections for deep brine exploration.

[0073] In the present invention, by collecting the geological structure feature information, geophysical feature information, and geochemical feature information of the basin area, and uniformly uploading them to the database for classification and storage, a multi-source database is constructed. This method can effectively integrate multiple data sources, providing comprehensive data support for subsequent three-dimensional geological modeling and brine mineralization prediction; based on the multi-source database, by comparing the historical database with the target database, the differential feature information is identified, and the initial geological model is adjusted to obtain the three-dimensional geological model corresponding to the target database, which can more accurately describe the geological features of the basin area, improving the accuracy and reliability of the three-dimensional geological model; by extracting the brine feature information of multiple historical basin areas and training the brine mineralization prediction model based on these feature information, the influence of multiple data sources on brine mineralization can be comprehensively considered. By optimizing the data set, removing the brine feature information in the overlapping areas and retaining the data in the non-overlapping areas, the accuracy and generalization ability of the prediction model are further improved; by automatically collecting, integrating, and analyzing the multi-source data information of the basin area, constructing an accurate three-dimensional geological model, and conducting brine mineralization prediction, the efficiency and accuracy of geological exploration are improved, realizing the intelligent management and efficient prediction of brine resources.

[0074] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0075] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the steps of any one of the above methods are implemented.

[0076] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0077] 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 principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for analyzing and evaluating deep brine mineralization in basin areas, characterized in that, The following steps are involved: Acquire the prospecting element characteristic information of the basin area to build a multi-source database, wherein the prospecting element characteristic information includes geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information; the multi-source database includes the prospecting element characteristic information and the monitoring terminals corresponding to each prospecting element characteristic information; Constructing a 3D geological model based on a multi-source database, wherein the multi-source database is divided into a historical database and a target database; Obtain three-dimensional geological models corresponding to multiple historical basin areas and extract corresponding brine characteristic information, wherein the brine characteristic information includes brine surface distribution and vertical burial depth characteristic information and mineralization mechanism characteristic information; train a brine mineralization prediction model based on the brine characteristic information; Acquire a three-dimensional geological model corresponding to the target basin area and extract brine characteristic information corresponding to the target basin area to obtain target brine characteristic information; input the target brine characteristic information into a brine mineralization prediction model to generate a brine mineralization prediction result; The brine mineralization prediction results are compared and evaluated with standard brine deposits, and the target basin area is divided into different levels of mineralization potential areas based on the evaluation results.

2. The method for analyzing and evaluating deep brine mineralization in basin areas according to claim 1, wherein: The step of acquiring the prospecting element characteristic information of the basin area and constructing a multi-source database, wherein the prospecting element characteristic information includes geological structure characteristic information, geophysical characteristic information, and geochemical characteristic information, comprises: Collect geological structure characteristic information, geophysical characteristic information and geochemical characteristic information of the basin area; upload the geological structure characteristic information, geophysical characteristic information and geochemical characteristic information to the database and store them by category; register monitoring terminals corresponding to the geological structure characteristic information, geophysical characteristic information and geochemical characteristic information respectively; form a multi-source database based on the prospecting element characteristic information and the monitoring terminals corresponding to each prospecting element characteristic information.

3. A method for analyzing and evaluating deep brine mineralization in basin areas according to claim 1, characterized in that: The step of constructing a three-dimensional geological model of deep brine in a basin area based on a multi-source database comprises: Acquire multiple historical databases by obtaining multi-source databases corresponding to three-dimensional geological models of multiple geological evolution stages corresponding to multiple historical basin areas; collect characteristic information of prospecting elements in the target basin area to construct a multi-source database to obtain a target database; select a historical database with the highest similarity to the target database from multiple historical databases to obtain a pre-selected database, and obtain a three-dimensional geological model corresponding to the pre-selected database to obtain an initial geological model; determine distinguishing feature information based on the target database and the pre-selected database, wherein the distinguishing feature information includes explicit distinguishing information and implicit distinguishing information; adjust the initial geological model based on the distinguishing feature information to obtain a three-dimensional geological model corresponding to the target database.

4. A method for analyzing and evaluating deep brine mineralization in basin areas according to claim 3, characterized in that: The step of determining the distinguishing characteristic information based on the target database and the pre-selected database, wherein the distinguishing characteristic information includes explicit distinguishing information and implicit distinguishing information, comprises: Acquire terrain information of a target basin area, lay a plurality of characteristic points with correlation relationship in the target basin area according to the terrain information, extract characteristic information corresponding to the plurality of characteristic points with correlation relationship respectively to form geological structure characteristic information in a target database; Arrange filling points corresponding to the initial geological model to form a filling framework; obtain the same data as that in the preselected database for the geological structure feature information, and fill the feature points corresponding to the geological structure feature information into the filling framework of the initial geological model according to the same data to form an initial three-dimensional model; Take the geological structure feature information in the target database corresponding to the unfilled filling points on the filling framework as explicit difference information; compare the target database with the preselected database, and extract other difference information that is not explicit difference information as implicit difference information; Construct difference feature information based on the explicit difference information and the implicit difference information, and mark the filling points corresponding to the difference feature information in the initial geological model to obtain marked filling points.

5. A method for analyzing and evaluating deep brine mineralization in basin areas according to claim 4, characterized in that: The steps of obtaining the topographic information of the target basin area, setting multiple feature points with associated relationships according to the topographic information, and extracting the feature information corresponding to the multiple feature points with associated relationships respectively to form the geological structure feature information in the target database include: Obtain the topographic information of the target basin area, and obtain the feature lines and corner points of the topographic information; Lay multiple feature points corresponding to the corner points and the feature lines within the target basin area, where the feature line is a line segment with an obvious trend or morphological change in the topographic information, and the corner point is a point where the feature lines intersect or the morphology changes significantly; Extract the corner points corresponding to each topographic information and the feature points corresponding to the feature lines, and connect them in sequence according to the topographic information to obtain multiple feature points with associated relationships; Extract the feature information corresponding to the multiple feature points with associated relationships respectively to form the geological structure feature information in the target database.

6. The method for analyzing and evaluating deep brine mineralization in a basin area according to claim 5, characterized in that: The steps of adjusting the geological model template based on the difference feature information to obtain the three-dimensional geological model corresponding to the target database include: Obtain each filling point of the initial geological model, and register a monitoring end corresponding to the filling point; establish a connection link between the monitoring end corresponding to the filling point and the monitoring end of the geological structure feature information in the target database, and set a trigger condition and a transmission switch for the connection link, where the trigger condition is that there is explicit difference information for the filling point corresponding to the connection link; When the connection link corresponding to the marked filling point reaches the trigger condition, start the transmission switch of the corresponding connection link, transmit the geological structure feature information in the target database to the corresponding marked filling point via the connection link, replace the geological structure feature information of the corresponding preselected database of the filling point, and perform a preliminary adjustment on the initial three-dimensional model based on the replaced geological structure feature information; Obtain the implicit difference information, and perform a secondary adjustment on the initially adjusted initial three-dimensional model based on the implicit difference information to obtain the three-dimensional geological model corresponding to the target database.

7. A method for analyzing and evaluating deep brine mineralization in basin areas according to claim 1, characterized in that: The steps of obtaining the three-dimensional geological models corresponding to multiple historical basin areas respectively and extracting the corresponding brine feature information, where the brine feature information includes brine level distribution and longitudinal burial depth feature information and ore-forming mechanism feature information; training the brine ore-forming prediction model based on the brine feature information include: Obtain three-dimensional geological models corresponding to multiple historical basin areas respectively, and perform superposition processing on the three-dimensional geological models corresponding to multiple historical basin areas in space to generate a superposed area and a non-superposed area; identify and separate the brine characteristic information of the superposed area and multiple non-superposed areas; perform comprehensive processing on the separated brine characteristic information, remove the brine characteristic information of the superposed area, retain the data of the non-superposed area, form an optimized data set, and use the optimized data set to train a metallogenic prediction model.

8. A method for analyzing and evaluating deep brine mineralization in basin areas according to claim 1, characterized in that: The step of comparing and evaluating the brine metallogenic prediction result with the standard brine ore deposit and dividing the target basin area into different grades of metallogenic potential areas based on the evaluation result includes: Obtain the information of the standard brine ore deposit, determine the brine metallogenic information of the target basin area based on the brine metallogenic prediction result, and compare the brine ore deposit information with the brine metallogenic information to determine the difference information; determine the division criteria for dividing the metallogenic potential area based on the difference information; divide the target basin area into different grades of metallogenic potential areas based on the division criteria.

Images