A method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints

Abstract

The present invention discloses a method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints, belonging to the technical field of mineral exploration, and comprising the following steps: S1, extracting the spatial distribution of catchment basins in the study area; S2, calculating the singularity index of geochemical elements; S3, establishing a spatial coupling relationship between catchment basins and mineral types; S4, establishing a unique correspondence relationship between the singularity index and the ore-forming indication type; S5, training a random forest algorithm model; S6, evaluating the mineralization potential based on the random forest algorithm model to obtain the ore deposit type with the greatest potential in the catchment basin. The method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints according to the present invention, aiming at the geochemical characteristics of "weak", "mixed", and "lacking" of key metal mineral resources, establishes geochemical fingerprints of different mineral types based on the singularity characteristics of geochemical elements, and realizes the classification of different ore-forming indication types in catchment basins.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral exploration, and particularly to a method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints. Background Art

[0002] Critical mineral resources refer to the general term of a class of minerals that are essential in modern society but have a relatively high risk of secure supply, mainly including rare metals, scattered metals, rare earths, and some rare precious metals, etc. Stream sediments are one of the most commonly used sampling media in exploration geochemistry, and significant achievements have been made in geological and mineral exploration based on stream sediment data. Current research is mostly applied to the exploration of outcrop minerals. For current covered areas and deep prospecting, especially for critical mineral resources with "rare", "fine", and "associated" complex geochemical behaviors, satisfactory results are often difficult to obtain, and there is an urgent need to develop new methods for mining geochemical mineralization information for such minerals. Currently, the mining of mineralization information of critical mineral resources based on geochemical exploration data mainly uses the research and analysis of geochemical element contents, ignoring key elements such as the sampling principle of stream sediments and weak information extraction. These ignored characteristic parameters are of great significance for the exploration of critical minerals.

[0003] Based on the above content, a method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints is proposed. Summary of the Invention

[0004] The object of the present invention is to provide a method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints. Aiming at the "weak", "mixed", and "lacking" geochemical characteristics of critical metal mineral resources, based on the singularity characteristics of geochemical elements, geochemical fingerprints of different mineral types are established as the geochemical element combination marks of different mineralization types, realizing the classification of different mineralization indication types.

[0005] To achieve the above object, the present invention provides a method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints, including the following steps:

[0006] S1. Extract the spatial distribution of catchment basins in the study area through a high-precision remote sensing digital elevation dataset;

[0007] S2. Calculate the singularity index of each stream sediment sampling position to obtain the singularity index that can characterize the element concentration degree in each catchment basin;

[0008] S3. Based on the systematic study of the metallogenic geological background of the study area, classify the discovered deposit types in the study area according to the metallogenic type, and establish the spatial coupling relationship between catchment basins and mineral types;

[0009] S4. Based on the spatial coupling relationship in S3, establish the unique corresponding relationship between the singularity index of geochemical elements and the ore-forming indication type;

[0010] S5. According to the unique corresponding relationship in S4, train the random forest algorithm model;

[0011] S6. Through the trained random forest classification model, obtain the geochemical fingerprints of each mineral type in the study area, and evaluate the ore-forming potential based on the prediction probabilities of different ore-forming types within each catchment basin, so as to obtain the ore deposit type with the greatest potential in each catchment basin.

[0012] Preferably, in S1, through hydrological analysis, extract the spatial distribution of catchment basins suitable for 1:200,000 scale stream sediment in the study area, and correct the catchment basins in the study area through existing hydrological data to obtain a high-precision catchment basin distribution.

[0013] Preferably, in S2, based on the singularity index analysis, calculate the singularity index of geochemical elements at each sampling point location, and through the spatial superposition relationship between the spatial distribution of the singularity index and the catchment basin, calculate the average value of the singularity index of sampling points within each catchment basin to obtain a comprehensive singularity index that can characterize the concentration degree of elements in each catchment basin.

[0014] Preferably, in S3, the ore-forming geological background includes regional spatio-temporal ore-forming laws, tectonic background, ore-forming age, ore deposit type, and structural ore-forming relationship.

[0015] Preferably, in S4, based on the spatial coupling relationship in S3, establish the exclusivity of the ore-forming type of each catchment basin to obtain the ore-forming indication type of each catchment basin.

[0016] Preferably, in S5, use the catchment basins containing discovered ore deposits as training data, divide the training set and test set according to a ratio of 7:3, and train the random forest model.

[0017] Preferably, in S6, it specifically includes the following steps:

[0018] S61. Predict and classify the test set of catchment basins in the study area through the trained model, and evaluate the prediction accuracy through the spatial coupling relationship between the classification results and the discovered ore deposits and mineralization points;

[0019] S62. Based on the variable importance analysis of the random forest model, obtain the change combination relationship of the singularity index of geochemical elements corresponding to each ore type to obtain the geochemical fingerprints of each polymetallic ore-forming type;

[0020] Based on the different geochemical fingerprint characteristics in S62, predict the mineralization combination types of the catchment basins, and obtain the occurrence probabilities of each catchment basin for each metallogenic type according to the prediction probabilities. The metallogenic type with a large occurrence probability is the key ore species for the next exploration of the catchment basin, thereby completing the importance evaluation of each metallogenic type.

[0021] Preferably, the steps of the above-mentioned mineralization potential evaluation method are completed by an electronic device.

[0022] Preferably, the electronic device includes a memory, a processor, and a computer program stored in the memory, and the computer program runs on the processor.

[0023] Therefore, the method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints according to the present invention breaks through the traditional exploration geochemistry processing idea for the "weak", "rare", and "fine" geochemical signal characteristics of key metal mineral resources; it can maximize the excavation of geochemical characteristic information of strategic and key minerals, and based on the singularity characteristics of geochemical elements, ensure the recognition accuracy of different mineralization types, and point out the direction for the next mineral exploration types in different regions.

[0024] Next, through the drawings and embodiments, the technical solutions of the present invention will be further described in detail. Description of the Drawings

[0025] Figure 1 is the flowchart of the embodiment of the present invention;

[0026] Figure 2 is the schematic diagram of the geochemical fingerprints of different mineral types in the embodiment of the present invention;

[0027] Figure 3 is the distribution diagram of the occurrence probabilities of different mineral types in the catchment basin in the embodiment of the present invention. Detailed Embodiments

[0028] The following further illustrates the technical solutions of the present invention through the drawings and embodiments.

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0030] The following further illustrates the present invention through examples in detail.

[0031] Taking the 1:200,000 stream sediment in Wulanchabu area, Inner Mongolia as an example, the study area belongs to hilly landform, and the spatial distribution of geochemical anomalies is greatly affected by catchment basins. For example, Figure 1 As shown below, the specific implementation steps are as follows:

[0032] (1) Based on the high-precision ASTER GDEM V3 digital elevation dataset, through the hydrological analysis function of ArcGIS, extract the spatial distribution of catchment basins in the study area, and correct the extracted catchment basins by combining the existing river spatial distribution in the study area to obtain the spatial distribution of catchment basins in the study area.

[0033] (2) Calculate the spatial distribution of singularity indices of 39 geochemical elements in 1:200,000 stream sediment. Select 3×3, 5×5, 7×7, 9×9, 11×11 as the calculation windows to calculate the singularity index at the central position.

[0034] (3) Through the spatial superposition relationship between the spatial distribution of singularity indices and catchment basins, calculate the mean value of singularity indices of sampling points within each catchment basin to obtain the singularity index of geochemical elements representing each catchment basin, which characterizes the concentration degree of geochemical elements in this catchment basin.

[0035] (4) According to the metallogenic geological background of the study area, classify the discovered minerals into five polymetallic metallogenic types: Au, Cu, Fe, Mo, and Pb-Zn. Then, based on the spatial coupling relationship between these discovered deposit types and catchment basins, establish the exclusivity of the metallogenic type for each catchment basin, that is, obtain the metallogenic indication type for each catchment basin.

[0036] (5) Establish a unique spatial correspondence between the established metallogenic indication type of the catchment basin and the comprehensive singularity index expressing its element concentration degree. Based on the consistency relationship between the comprehensive singularity index and the metallogenic type, train the random forest algorithm model, and then adjust the model parameters to make the model reach the optimal state.

[0037] (6) Use the trained model to predict and classify all catchment basins in the study area. Based on the variable importance analysis of the random forest model, obtain the combination of singularity indices of geochemical elements corresponding to each ore type, that is, the geochemical fingerprint of each polymetallic metallogenic type. As Figure 2 shown, it is found that each mineral type has a different combination of geochemical element characteristics, and the geochemical element combination relationship has metallogenic exclusivity. Then, according to the prediction probability, obtain the occurrence probability of each catchment basin for each polymetallic metallogenic type. The ore type with a high occurrence probability is the key ore type for the next exploration of the catchment basin. As Figure 3 shown.

[0038] Therefore, a method for evaluating the mineralization potential of catchment basins based on geochemical fingerprints in the present invention, aiming at the "weak", "mixed", and "lacking" geochemical characteristics of key metal mineral resources, establishes geochemical fingerprints of different mineral types based on the singularity characteristics of geochemical elements, as geochemical combination markers of different mineralization types, and realizes the classification of different mineralization indication types.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the present invention or make equivalent replacements, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for evaluating the mineralization potential of a catchment basin based on geochemical fingerprints, characterized in that: The following steps are involved: S1. Extract the spatial distribution of the catchment basins in the study area through high-precision remote sensing digital elevation data sets; extract the spatial distribution of the catchment basins of the river system sediments at a scale of 1:200,000 suitable for the study area through hydrological analysis, and correct the catchment basins in the study area through the existing hydrological data to obtain high-precision catchment basin distribution; S2. Calculate the spatial distribution of the singularity index of 39 geochemical elements in stream sediments at a scale of 1:200,000, calculate the singularity index of each stream sediment sampling location, select 3×3, 5×5, 7×7, 9×9, and 11×11 as the calculation window, calculate the singularity index of the central location, and obtain the singularity index that can characterize the concentration of elements in each catchment basin: Based on the singularity index analysis, calculate the singularity index of geochemical elements at each sampling point, calculate the average singularity index of the sampling points in each catchment basin through the spatial distribution of the singularity index and the spatial superposition relationship of the catchment basin, and obtain the comprehensive singularity index that can characterize the concentration of elements in each catchment basin; S3. Based on the systematic study of the mineralization geological background of the study area, the types of mineral deposits discovered in the study area are classified according to the mineralization type, and the spatial coupling relationship between the catchment basin and the mineral type is established; S4. Based on the spatial coupling relationship in S3, the specificity of the mineralization type of each catchment basin is established, the mineralization indicator type of each catchment basin is obtained, and the unique corresponding relationship between the geochemical element singularity index and the mineralization indicator type is established; S5. According to the unique corresponding relationship in S4, the random forest algorithm model is trained, the catchment basin containing the discovered mineral deposit is used as training data, the training set and the test set are divided into a ratio of 7:3, and the random forest model is trained; S6. The geochemical fingerprint of each mineral type in the study area is obtained through the trained random forest classification model, and the mineralization potential of each catchment basin is evaluated based on the predicted probability of different mineralization types in each catchment basin to obtain the most potential mineral deposit type in each catchment basin; The specific steps include: S61. Use the trained model to predict and classify the test set of the catchment basin in the study area, and evaluate the prediction accuracy through the spatial coupling relationship between the classification results and the discovered mineral deposits and mineralization points; S62. Based on the variable importance analysis of the random forest model, the changing combination relationship of the geochemical element singularity index corresponding to each mineral type is obtained, and the geochemical fingerprint of each polymetallic mineralization type is obtained; S63. Based on the different geochemical fingerprint features in S62, the mineralization combination types of the catchment basin are predicted, and the probability of occurrence of each mineralization type in each catchment basin is obtained according to the predicted probability. The mineralization type with a high probability of occurrence is the key mineral species for the next exploration of the catchment basin, thereby completing the importance evaluation of each mineralization type.

2. The method for evaluating the mineralization potential of a catchment basin based on geochemical fingerprint according to claim 1, characterized in that: In S3, the metallogenic geological background includes regional temporal and spatial metallogenic laws, tectonic background, metallogenic age, ore deposit type, and structural metallogenic relationship.

3. The method for evaluating the mineralization potential of a catchment basin based on geochemical fingerprint according to claim 2, characterized in that: The steps of the mineralization potential evaluation method described in any one of claims 1 to 2 are completed by an electronic device.

4. The method for evaluating the mineralization potential of a catchment basin based on geochemical fingerprint according to claim 3, characterized in that: The electronic device comprises a memory, a processor and a computer program stored in the memory, the computer program running on the processor.

Images