Uranium copper multi-metal remote sensing prospecting method and system

Abstract

The invention relates to the technical field of remote sensing prospecting, and discloses a uranium-copper multi-metal remote sensing prospecting method which comprises the following steps: S1, data acquisition and preprocessing; s2, alteration information is extracted; s3, multi-source information comprehensive analysis and prospecting prediction; s4, alteration abnormity verification is carried out; and S5, delineating the prospecting target area. According to the method, vegetation spectrum interference is stripped by carrying out principal component analysis on visible light-short wave infrared of a remote sensing image, weak iron staining and hydroxyl alteration signals are extracted, a geological and remote sensing coupling technology is carried out, alteration anomaly is superposed with a geological map, geochemical data and a construction interpretation result, a comprehensive remote sensing anomaly map is obtained, and the comprehensive remote sensing anomaly map is obtained. According to the method, the multi-parameter grading model GGS is established, and the target region is graded based on the multi-parameter grading model GGS, so that the probability of missed judgment of the target region is reduced.

Description

Technical Field

[0001] This invention relates to the field of remote sensing mineral exploration technology, specifically to a method and system for remote sensing mineral exploration of uranium-copper polymetallic minerals. Background Technology

[0002] Remote sensing prospecting utilizes remote sensing technology to acquire electromagnetic wave information of surface and near-surface features, and then processes and analyzes this data to identify mineralization alteration zones, tectonic ore-controlling characteristics, or directly detect mineral distribution. It enables rapid and large-scale screening of prospecting target areas, reducing exploration costs.

[0003] A search revealed that patent application number CN202311764576.0 discloses a remote sensing prospecting method, apparatus, equipment, and medium based on a polymetallic deposit remote sensing prospecting model. The method includes: firstly, analyzing the regional geological background, mineralization geological characteristics, and typical deposits of a predetermined area to establish ore-controlling elements and metallogenic regularities. Then, based on the ore-controlling elements and metallogenic regularities, the method uses remote sensing imagery to reveal differences in remote sensing alteration information characteristics of the predetermined area, establishing remote sensing prospecting indicators. These indicators are then enhanced and extracted using a density segmentation method to establish a polymetallic deposit remote sensing prospecting model. Finally, based on this polymetallic deposit remote sensing prospecting model, the predetermined area is analyzed and verified using an evidence weighting method to complete the remote sensing technology for mineral exploration. This disclosed embodiment, by establishing a polymetallic deposit remote sensing prospecting model and using this model to predict prospective areas, improves the potential for mineral resource development in uninhabited areas and safeguards national mineral resource security.

[0004] Traditional remote sensing prospecting techniques mainly rely on extracting remote sensing alteration anomaly information from single remote sensing image data, while neglecting the analysis of metallogenic geological elements such as ore-bearing host rocks and ore-controlling structures, as well as geochemical characteristics. This leads to missed or incorrect identification of prospecting target areas extracted by remote sensing techniques. Therefore, we need to propose a remote sensing prospecting method and system for uranium-copper polymetallic minerals. Summary of the Invention

[0005] The purpose of this invention is to provide a remote sensing prospecting method and system for uranium-copper polymetallic minerals. This method uses radar to estimate vegetation layer thickness and identify vegetation porosity. Principal component analysis of visible and short-wave infrared remote sensing images is used to remove spectral interference from vegetation and extract weak iron staining and hydroxyl alteration signals. Through geological and remote sensing coupling technology, alteration anomalies are superimposed with geological maps, geochemical data, and tectonic interpretation results. A hierarchical analysis method is used to assign weights to different alteration types. Then, the weights of alteration intensity, fracture density, and geochemical data are spatially weighted and superimposed to obtain a comprehensive remote sensing anomaly map, thereby solving the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a remote sensing prospecting method for uranium-copper polymetallic minerals, comprising the following steps:

[0007] S1. Data Acquisition and Preprocessing: Based on the geological characteristics of the target mining area, select remote sensing data sources, including multispectral data, hyperspectral data, and radar satellite data, and preprocess the selected data.

[0008] S2. Alteration Information Extraction: Based on the spectral characteristics of minerals, alteration anomalies are extracted, and the alteration situation is classified according to the alteration intensity. The spatial distribution of alteration anomalies and the relationship with geological structure are analyzed.

[0009] S3. Multi-source information integrated analysis and mineral exploration prediction: Through the coupling technology of geology and remote sensing, the spatial coupling between alteration anomalies and ore-controlling elements is analyzed, and a comprehensive remote sensing anomaly map is generated.

[0010] S4. Alteration Anomaly Verification: Surface sampling is performed on the anomaly areas delineated in the remote sensing anomaly map, and shortwave infrared spectroscopy analysis is used to identify the alteration mineral assemblage.

[0011] S5. Mineral exploration target area delineation: Based on the intensity of alteration anomalies, ore-controlling elements, and geological mineralization conditions, the target area is divided into three levels of prospective mineral exploration areas.

[0012] Preferably, in step S1, the geological features include regional geological background, ore-bearing host rocks, ore-controlling structures, and typical deposit features. Multispectral data is used for iron staining and hydroxyl alteration extraction, and hyperspectral data is used for fine identification of different types of alteration minerals. By combining multispectral data and hyperspectral data, the detection needs of different alteration types are covered.

[0013] Preferably, in step S1, the data preprocessing includes: geometric correction to eliminate topographic distortion, radiometric correction to reduce atmospheric radiation, remote sensing image fusion to improve spatial resolution, and remote sensing image mosaicking to cover the entire study area.

[0014] Preferably, in step S2, the spectral characteristics of the mineral include: absorption valleys of iron staining alteration between 0.45-0.50 μm and 0.85-0.9 μm, and reflection peaks between 0.65-0.7 μm and 1.60-1.65 μm; absorption valleys of hydroxyl groups between 0.85-0.9 μm and 2.28-2.32 μm, and reflection peaks between 0.50-0.55 μm and 1.62-1.68 μm. During mineral identification, feature band extraction is first performed using a technique based on matching mineral absorption / reflection characteristics with a spectral library to avoid misidentifying minerals with similar spectra. Then, density segmentation is used to separate weak alteration signals under vegetation cover. Finally, deep learning is used for identification to reduce errors in manual threshold setting.

[0015] Preferably, in step S2, when classifying the intensity of alteration anomalies, the mean and standard deviation of alteration in the study area are calculated. When the alteration anomaly index is ≥ the mean alteration index + 2.5 times the standard deviation, it is marked as a first-level anomaly; when the mean alteration index + 2.0 times the standard deviation is ≤ the alteration anomaly index < the mean alteration index + 2.5 times the standard deviation, it is marked as a second-level anomaly; when the mean alteration index + 1.5 times the standard deviation is < the alteration anomaly index ≤ the mean alteration index + 2.0 times the standard deviation, it is marked as a third-level anomaly.

[0016] Preferably, in step S3, the geological and remote sensing coupling technology is as follows: the alteration anomaly is superimposed with the geological map, geochemical data, and structural interpretation results. The remote sensing alteration anomaly data is used to delineate the iron staining / hydroxyl alteration core area, the geological map is used to identify the ore-bearing host rock and the contact zone of the ore-bearing lithology, the geochemical data is used to locate the polymetallic assemblage anomaly, and the structural interpretation is used to quantify the ore-controlling probability at the fault intersection.

[0017] The analytic hierarchy process (AHP) was used to assign weights to different alteration types. Then, the weights of alteration intensity, fracture density, and geochemical data were spatially weighted and superimposed to obtain a comprehensive remote sensing anomaly map.

[0018] Preferably, in step S4, surface sampling includes: automatic sampling using a UAV grid, then real-time analysis of the collected samples using a portable ground object spectrometer, and finally full-spectrum scanning using a hyperspectral core scanner;

[0019] In shortwave infrared spectroscopy analysis, mineral abundance = α * 2140 吸收深度 +β*2200 吸收宽度 , where α is the weight of the absorption depth at 2140 nm and β is the weight of the absorption width at 2200 nm.

[0020] Preferably, in step S5, a multi-parameter classification model GGS is established, where GGS = α * alteration anomaly index + β fracture density + γ * uranium abundance + δ * mineralization rate, and α = 0.4, β = 0.25, γ = 0.2, and δ = 0.15.

[0021] Preferably, when the multi-parameter grading model GGS ≥ 0.85, the mineral exploration target area is classified as Level 1; when 0.7 ≤ GGS < 0.85, the mineral exploration target area is classified as Level 2; and when GGS < 0.7, the mineral exploration target area is classified as Level 3.

[0022] Based on the above-described remote sensing prospecting method for uranium-copper polymetallic minerals, this invention also provides a remote sensing prospecting system for uranium-copper polymetallic minerals, including a multi-source data management module, a preprocessing module, an alteration interpretation module, a three-dimensional prediction module, an anomaly verification module, a resource evaluation module, and a central control module.

[0023] The multi-source data management module, preprocessing module, alteration interpretation module, 3D prediction module, anomaly verification module, and resource evaluation module are connected in sequence, and the alteration interpretation module, 3D prediction module, and anomaly verification module are all connected to the central control module.

[0024] Compared with the prior art, the beneficial effects of the present invention are:

[0025] 1. This invention uses radar to estimate the thickness of the vegetation layer and identify the vegetation porosity. It also uses principal component analysis of visible light and shortwave infrared remote sensing images to remove vegetation spectral interference, extract weak iron staining and hydroxyl alteration signals, and carry out geological and remote sensing coupling technology to improve the accuracy of vegetation alteration detection.

[0026] 2. This invention employs the analytic hierarchy process (AHP) to assign weights to different alteration types and performs spatial weighted overlay to obtain a comprehensive remote sensing anomaly map. During sampling, UAVs are used for automatic grid-based sampling, and portable ground object spectrometers are used for real-time analysis of the collected samples. A hyperspectral core scanner is used for full-spectrum scanning. A multi-parameter hierarchical model (GGS) is established, and based on the GGS, the target area is classified into different levels, reducing the probability of missed detections. Attached Figure Description

[0027] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Please see Figure 1 This invention provides a technical solution: a remote sensing prospecting method for uranium-copper polymetallic minerals, comprising the following steps:

[0030] S1. Data Acquisition and Preprocessing: Based on the geological characteristics of the target mining area, select remote sensing data sources, including multispectral data (such as Land Sat 8 / Sentinel-2A / ASTER), hyperspectral data (such as GF-5), and radar satellite data (such as Sentinel-1), and preprocess the selected data.

[0031] In step S1, geological features include regional geological background, ore-bearing host rocks, ore-controlling structures, and typical deposit characteristics. Multispectral data is used for remote sensing of iron staining and hydroxyl alteration minerals, identifying alteration minerals with broad bands (such as iron staining oxidation zones and clay minerals). Hyperspectral data is used for refined identification of different types of alteration minerals (such as hematite, pyrite, and hydromica), effectively distinguishing minerals with similar spectral characteristics. The GF-5 blue-green band (450-500nm) is sensitive to hematite. By combining multispectral and hyperspectral data, the detection needs of different alteration types are covered. Radar satellite data penetrates vegetation / shallow overburden layers to detect concealed structures.

[0032] In step S1, data preprocessing includes:

[0033] Geometric correction to eliminate terrain distortion, thus eliminating image warping caused by terrain undulations;

[0034] Reduce atmospheric radiation through radiation correction, minimize the effects of atmospheric scattering / absorption, and restore the true reflectivity of ground objects;

[0035] Improving the spatial resolution of remote sensing images through fusion, enhancing the spatial resolution of multispectral images (e.g., 15m→2m) while preserving spectral information;

[0036] Remote sensing images covering the entire study area are mosaicked to eliminate color differences between multiple images and construct a seamless image of the study area.

[0037] S2. Alteration Information Extraction: Based on the spectral characteristics of minerals, alteration anomalies are extracted, and the alteration situation is classified according to the alteration intensity. The spatial distribution of alteration anomalies and the relationship with geological structure are analyzed.

[0038] In step S2, the spectral characteristics of the mineral include: absorption valleys of iron staining alteration between 0.45-0.50 μm and 0.85-0.9 μm, and reflection peaks between 0.65-0.7 μm and 1.60-1.65 μm; absorption valleys of hydroxyl groups between 0.85-0.9 μm and 2.28-2.32 μm, and reflection peaks between 0.50-0.55 μm and 1.62-1.68 μm.

[0039] When identifying minerals, feature bands are first extracted, and a technique based on a spectral library (such as USGS) to match mineral absorption / reflection features is used to avoid misjudging minerals with similar spectra. Then, density segmentation is used to separate weak alteration signals under vegetation cover. Finally, deep learning is used for identification, employing a convolutional neural network (CNN) to train mineral spectral curves and automatically identify complex alteration combinations, reducing errors from manual threshold setting.

[0040] In step S2, when classifying the intensity of alteration anomalies, the mean and standard deviation of alteration in the study area are calculated. When the alteration anomaly index is greater than or equal to the mean alteration index plus 2.5 times the standard deviation, it is marked as a first-level anomaly; when the mean alteration index plus 2.0 times the standard deviation is less than or equal to the mean alteration index plus 2.5 times the standard deviation, it is marked as a second-level anomaly; and when the mean alteration index plus 1.5 times the standard deviation is less than or equal to the mean alteration index plus 2.0 times the standard deviation, it is marked as a third-level anomaly.

[0041] Iron dye (Fe) 3+ The anomalies are mostly distributed within the uranium-copper polymetallic ore bodies, while the hydroxyl (OH-) anomalies are mostly distributed on the periphery of the uranium-copper polymetallic ore bodies. The overlapping area of ​​the two can be used to locate the uranium-copper polymetallic deposit.

[0042] S3. Multi-source information integrated analysis and mineral exploration prediction: Through the coupling technology of geology and remote sensing, the spatial coupling between alteration anomalies and ore-controlling elements is analyzed, and a comprehensive remote sensing anomaly map is generated.

[0043] In step S3, the geological and remote sensing coupling technology is as follows: the alteration anomaly is superimposed with the geological map, geochemical data, and structural interpretation results. The remote sensing alteration anomaly data is used to delineate the iron staining / hydroxyl alteration core area, the geological map is used to identify the ore-bearing host rock and the contact zone of the ore-bearing lithology, the geochemical data is used to locate the polymetallic assemblage anomaly, and the structural interpretation is used to quantify the ore-controlling probability at the fault intersection.

[0044] The processing techniques for remote sensing alteration anomalies are PCA band compression and anomaly intensity classification; the processing techniques for geological maps are convolutional neural networks (CNN) for automatic extraction of structure and lithology; the processing techniques for geochemical data are Kriging interpolation and element combination entropy analysis; and the processing techniques for tectonic interpretation are azimuth filtering and fault density field modeling.

[0045] The analytic hierarchy process (AHP) was used to assign weights to different alteration types. Then, the weights of alteration intensity, fracture density, and geochemical data were spatially weighted and superimposed to obtain a comprehensive remote sensing anomaly map.

[0046] The method to improve deep-seated prediction capabilities by penetrating the overburden layer is to establish a three-dimensional prediction system of "air-ground-depth", including:

[0047] Wide-area electromagnetic method (WFEM): Detection depth up to 2 km underground, resistivity error <5%, identifying hidden interfaces between different lithologies;

[0048] Gravity gradient inversion: vertical resolution of 100m, delineation of high-density mineralization bodies;

[0049] 3D geological modeling (GOCAD): Construct ore body-scale (50m×50m×20m) units to visualize deep alteration-tectonic coupling relationships.

[0050] S4. Alteration Anomaly Verification: Surface sampling is performed on the anomaly areas delineated in the remote sensing anomaly map, and shortwave infrared spectroscopy analysis is used to identify the alteration mineral assemblage.

[0051] In step S4, surface sampling includes: using UAVs for gridded automatic sampling (increasing sampling density by 300% and avoiding human error in missing areas), then using a portable ground object spectrometer to analyze the collected samples in real time (identifying elements in 2 seconds), and finally using a hyperspectral core scanner to perform full-spectrum scanning (completing mineral mapping of kilometer-long borehole cores in a single day).

[0052] In shortwave infrared spectroscopy analysis, the mineral abundance = α * 2140 absorption depth + β * 2200 absorption width, where α is the weight of the 2140 nm absorption depth and β is the weight of the 2200 nm absorption width.

[0053] S5. Mineral exploration target area delineation: Based on the intensity of alteration anomalies, ore-controlling elements, and geological mineralization conditions, the target area is divided into three levels of prospective mineral exploration areas.

[0054] In step S5, a multi-parameter classification model GGS is established. The multi-parameter classification model GGS = α*alteration anomaly index + β fracture density + γ*uranium abundance + δ*mineralization rate, where α = 0.4, β = 0.25, γ = 0.2, and δ = 0.15.

[0055] When the multi-parameter grading model GGS ≥ 0.85, the target area is classified as Level 1, and drilling work is prioritized; when the multi-parameter grading model GGS < 0.85, the target area is classified as Level 2, and anomaly verification work is carried out selectively; when the multi-parameter grading model GGS < 0.7, the mineral exploration target area is classified as Level 3, and geological survey work is carried out.

[0056] Then, the resource potential of the target area is assessed. Machine learning feedback is used to train a random forest based on the Cu / U grade of the borehole to predict the continuity of deep mineralization and reduce the error in resource estimation. Three-dimensional geological modeling is used to construct the ore body outline and integrate alteration-geophysical-geological data to reduce the error in ore body boundary delineation. A block model is used to estimate the resource quantity in 50m×50m×25m unit blocks.

[0057] Based on the above-described method for remote sensing prospecting of uranium-copper polymetallic minerals, this invention also provides a remote sensing prospecting system for uranium-copper polymetallic minerals, comprising:

[0058] Multi-source data management module: Integrates multispectral / hyperspectral / radar remote sensing data with geological, geochemical, and geophysical data to establish a standardized database;

[0059] Preprocessing module: Automates geometric correction, radiometric correction, fusion, and mosaicking of remote sensing images;

[0060] Alteration interpretation module: Extracts mineral spectral features, classifies alteration anomalies, and correlates them with geological structures;

[0061] 3D prediction module: Integrates geological, geophysical, and geochemical data to construct a quantitative mineral exploration model;

[0062] Anomaly Detection Module: Intelligently plans field anomaly detection routes, analyzes SWIR data in real time, and provides feedback for model optimization;

[0063] Resource assessment module: Delineate graded target areas and estimate resource quantity and economic value;

[0064] Overall control module: Intelligent scheduling and decision support for the entire process.

[0065] The multi-source data management module, preprocessing module, alteration interpretation module, 3D prediction module, anomaly verification module, and resource evaluation module are connected in sequence, and the alteration interpretation module, 3D prediction module, and anomaly verification module are all connected to the central control module.

[0066] The multi-source data management module outputs standardized images → the intelligent preprocessing module eliminates interference → the alteration interpretation module extracts mineral anomalies. The spatial resolution of the fused images in the preprocessing module determines the accuracy of alteration identification.

[0067] The alteration interpretation module provides an alteration anomaly classification map → the 3D prediction module couples geophysical data → the overall control system generates dynamic prediction weights;

[0068] The anomaly detection module directs the UAV to conduct precise sampling (prioritizing the primary target area) → the resource evaluation module integrates drilling data → and outputs a recoverable reserve model.

[0069] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A uranium-copper polymetallic remote sensing prospecting method, characterized in that, The method comprises the following steps: S1, data acquisition and preprocessing: according to the geological characteristics of the target mining area, the remote sensing data source is selected, the data source includes multispectral data, hyperspectral data and radar satellite data; and the selected data is preprocessed; S2, alteration information extraction: based on the spectral characteristics of altered minerals, remote sensing alteration anomalies are extracted, and the alteration conditions are graded according to the intensity of remote sensing alteration, and the spatial distribution of remote sensing alteration anomalies and the relationship with geological structure are analyzed; S3, comprehensive analysis and ore prediction of multi-source information: through the coupling technology of geology and remote sensing, the spatial coupling of remote sensing alteration anomalies and ore-controlling elements is analyzed, and a comprehensive remote sensing alteration anomaly map is generated; S4, alteration anomaly verification: surface sampling is carried out on the anomaly area circled in the remote sensing alteration anomaly map, and short-wave infrared spectrum analysis is carried out to identify the alteration mineral combination; S5, delineation of ore prospecting target area: according to the alteration anomaly intensity, ore-controlling elements and geological ore-forming conditions, the target area is divided into one to three ore prospecting prospective areas.

2. The method according to claim 1, characterized in that: In step S1, the geological characteristics include regional geological background, ore-hosting wall rock, ore-controlling structure and typical deposit characteristics, multispectral data is used for remote sensing of iron staining and hydroxyl alteration minerals, hyperspectral data is used for fine identification of different types of altered minerals, and through the combination of multispectral data and hyperspectral data, different alteration types are covered from different levels to meet the detection requirements.

3. The method according to claim 1, characterized in that: In step S1, the preprocessing of the data includes: geometric correction to eliminate terrain distortion, radiation correction to reduce atmospheric radiation, remote sensing image fusion to improve spatial resolution, and remote sensing image mosaic to cover the entire study area.

4. The method according to claim 1, characterized in that: In step S2, the spectral characteristics of the minerals include: iron staining alteration in the absorption valleys of 0.45-0.50 μm and 0.85-0.9 μm and the reflection peaks of 0.65-0.7 μm and 1.60-1.65 μm, and hydroxyl in the absorption valleys of 0.85-0.9 μm and 2.28-2.32 μm and the reflection peaks of 0.50-0.55 μm and 1.62-1.68 μm. When identifying minerals, first extract the characteristic waveband, use the technology of matching mineral absorption / reflection characteristics based on the spectral library to avoid misjudgment of similar spectral minerals, then use the density segmentation method to separate the weak alteration signal under vegetation coverage, and finally use deep learning identification to reduce the error of manual threshold setting.

5. The method according to claim 1, characterized in that: In step S2, when grading the intensity of alteration anomalies, first calculate the mean and standard deviation of the alteration in the study area. When the alteration anomaly index is greater than or equal to the mean plus 2.5 times the standard deviation, it is marked as a first-level anomaly; when the alteration anomaly index is greater than or equal to the mean plus 2.0 times the standard deviation and less than the mean plus 2.5 times the standard deviation, it is marked as a second-level anomaly; when the alteration anomaly index is greater than or equal to the mean plus 1.5 times the standard deviation and less than the mean plus 2.0 times the standard deviation, it is marked as a third-level anomaly.

6. The method according to claim 1, characterized in that: In step S3, the geology and remote sensing coupling technology is: superimposing the alteration anomaly and the geological map, geochemical data, and structural interpretation results, wherein the remote sensing alteration anomaly data is used to delineate the iron staining / hydroxyl alteration core area, the geological map is used to identify the ore-bearing wall rock and ore-bearing lithological contact zone, the geochemical data is used to locate the polymetallic combination anomaly, and the structural interpretation is used to quantify the ore-controlling probability at the intersection of fractures; The analytic hierarchy process is used to give different alteration types different weights, and then the weights of alteration intensity, fracture density, and geochemical data are spatially weighted and superimposed to obtain a comprehensive remote sensing anomaly map.

7. The method according to claim 1, characterized in that: In step S4, surface sampling includes: using unmanned aerial vehicle grid automatic sampling, then using a portable ground object spectrometer to analyze the collected samples in real time, and finally using a hyperspectral core scanner to scan the full spectrum. In shortwave infrared spectroscopy analysis, mineral abundance = α * 2140 吸收深度 +β*2200 吸收宽度 , where α is the weight of the absorption depth at 2140 nm and β is the weight of the absorption width at 2200 nm.

8. The method according to claim 5, characterized in that: In step S5, a multi-parameter grading model GGS is established, and the multi-parameter grading model GGS = α*alteration anomaly index + β*fracture density + γ*uranium abundance + δ*ore occurrence rate, wherein α = 0.4, β = 0.25, γ = 0.2, and δ = 0.

15.

9. The uranium-copper polymetallic remote sensing prospecting method according to claim 8, characterized in that: When the multi-parameter grading model GGS is greater than or equal to 0.85, the prospecting target area is classified as first grade; when 0.7 ≤ multi-parameter grading model GGS < 0.85, the prospecting target area is classified as second grade; and when the multi-parameter grading model GGS is less than 0.7, the prospecting target area is classified as third grade.

10. A uranium-copper polymetallic remote sensing ore-prospecting system based on the uranium-copper polymetallic remote sensing ore-prospecting method of any one of claims 1-9, characterized in that: The system includes a multi-source data management module, a preprocessing module, an alteration interpretation module, a three-dimensional prediction module, an anomaly verification module, a resource evaluation module, and a general control module. The multi-source data management module, the preprocessing module, the alteration interpretation module, the three-dimensional prediction module, and the anomaly verification module are sequentially connected, and the alteration interpretation module, the three-dimensional prediction module, and the anomaly verification module are connected with the general control module.

Images