Mineral exploration method based on multi-source data fusion

Abstract

The invention discloses a mineral exploration method based on multi-source data fusion, and relates to the technical field of mineral products. The method comprises the following steps: acquiring multi-source remote sensing data of a target area, wherein the multi-source remote sensing data comprises remote sensing data of a plurality of different satellites; performing image enhancement processing on the multi-source remote sensing data to obtain spatial distribution information of a target vein body with a target mineral; performing spectrum analysis on the multi-source remote sensing data to obtain spatial distribution information of the target mineral; and based on the spatial distribution information of the target vein body with the target mineral and the spatial distribution information of the target mineral, determining a metallogenic favorable target region of the target vein body containing the target mineral. The mineral exploration method based on multi-source data fusion is used for exploring the minerals in the target area and predicting the positions of the minerals, guidance is provided for mineral development in the target area, the prospecting period is shortened, and the prospecting efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of mineral technology, and in particular to a mineral exploration method based on multi-source data fusion. Background Art

[0002] In areas characterized by high altitudes and sharply dissected terrain, typical alpine and cold mountainous terrain, traditional geological exploration methods struggle to achieve large-scale mineral identification and prediction. While hyperspectral remote sensing technology has been widely used in mineral identification, geological mapping, alteration anomaly zoning, and prospecting, it currently relies primarily on airborne hyperspectral data, which presents technical bottlenecks such as high cost, long lead times, and limited coverage. Summary of the Invention

[0003] The purpose of this application is to provide a mineral exploration method based on multi-source data fusion, which is used to explore minerals in a target area, predict the location of minerals, provide guidance for mineral development in the target area, shorten the prospecting cycle, and improve prospecting efficiency.

[0004] In order to achieve the above objectives, this application provides the following technical solutions:

[0005] A mineral exploration method based on multi-source data fusion, the method comprising:

[0006] Acquiring multi-source remote sensing data of a target area, wherein the multi-source remote sensing data includes remote sensing data from multiple different satellites;

[0007] performing image enhancement processing on the multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals;

[0008] Performing spectral analysis on the multi-source remote sensing data to obtain spatial distribution information of the target mineral;

[0009] Based on the spatial distribution information of the target vein body containing the target mineral and the spatial distribution information of the target mineral, a favorable target area for mineralization of the target vein body containing the target mineral is determined.

[0010] Compared with the existing technology, the mineral exploration method based on multi-source data fusion provided by this application obtains multi-source remote sensing data of the target area and performs image enhancement processing on the multi-source remote sensing data to obtain the spatial distribution information of the target vein body with the target mineral, performs spectral analysis on the multi-source remote sensing data to obtain the spatial distribution information of the target mineral, and finally determines the mineralization favorable target area of ​​the target vein body containing the target mineral based on the spatial distribution information of the target vein body with the target mineral and the spatial distribution information of the target mineral. It can be seen that this application integrates remote sensing data of multiple different satellite categories to conduct targeted analysis of remote sensing data of different categories, obtains a prospecting method for target minerals in the target area, so as to improve the recognition accuracy and provide technical support and reference for subsequent prospecting work.

[0011] The present application also provides a mineral exploration device based on multi-source data fusion, the device comprising:

[0012] An acquisition module, wherein the acquisition module is used to acquire multi-source remote sensing data of a target area, wherein the multi-source remote sensing data includes remote sensing data of multiple different satellite categories;

[0013] an acquisition module, the acquisition module being used to perform image enhancement processing on the multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals;

[0014] The acquisition module is further used to perform spectral analysis on the multi-source remote sensing data to obtain spatial distribution information of the target mineral;

[0015] A determination module is used to determine a favorable target area for mineralization of a target vein body containing the target mineral based on the spatial distribution information of the target vein body having the target mineral and the spatial distribution information of the target mineral.

[0016] Compared with the prior art, the beneficial effects of the mineral exploration device based on multi-source data fusion provided in this application are the same as the beneficial effects of the mineral exploration method based on multi-source data fusion described in the above technical solution, and will not be repeated here.

[0017] The present application also provides an electronic device, comprising:

[0018] processor; and,

[0019] Memory for storing programs;

[0020] The program includes instructions, which, when executed by the processor, enable the processor to perform the method described in this application.

[0021] Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as the beneficial effects of the mineral exploration method based on multi-source data fusion described in the above technical solution, and will not be elaborated here.

[0022] The present application also provides a computer program product, which includes a computer program, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to perform the method described in the present application.

[0023] Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the mineral exploration method based on multi-source data fusion described in the above technical solution, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 A flowchart of a mineral exploration method based on multi-source data fusion provided by an exemplary embodiment of the present application is shown;

[0026] Figure 2 A schematic diagram of the Bailongshan area and the Akshayi area in the Dahongliutan region provided by an exemplary embodiment of the present application is shown;

[0027] Figure 3a Shows the hyperspectral data of the Bailongshan area before processing provided by an exemplary embodiment of the present application;

[0028] Figure 3b shows the hyperspectral data of the Bailongshan area after processing provided by the exemplary embodiment of the present application;

[0029] Figure 4a A picture of a spodumene-containing sample from the Bailongshan area provided by an exemplary embodiment of the present application is shown;

[0030] Figure 4b A picture of a cassiterite sample from the Bailongshan area provided by an exemplary embodiment of the present application is shown;

[0031] Figure 4c Shows a picture of a tourmaline sample from the Bailongshan area provided by an exemplary embodiment of the present application;

[0032] Figure 4d The measured spectrum curve of minerals in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0033] Figure 4eThe measured spectrum curve of rocks in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0034] Figure 4f shows a standard mineral spectrum curve provided by an exemplary embodiment of the present application;

[0035] Figure 5a A diagram showing the interpretation results of the pegmatite vein in the Bailongshan area provided by an exemplary embodiment of the present application is shown;

[0036] Figure 5b The interpretation mark of the stockwork pegmatite vein in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0037] Figure 5c The interpretation mark of the dendritic pegmatite vein in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0038] Figure 6a A comparison diagram of spodumene end-member spectra in the Bailongshan region provided by an exemplary embodiment of the present application is shown;

[0039] Figure 6b A comparison diagram of end-member spectra of muscovite in Bailong Mountain area provided by an exemplary embodiment of the present application is shown;

[0040] Figure 6c A comparison diagram of end-member spectra of albite in the Bailongshan region provided by an exemplary embodiment of the present application is shown;

[0041] Figure 7 The mineral mapping results of the Bailongshan area provided by the exemplary embodiment of the present application are shown;

[0042] Figure 8a A distribution map of field verification points in the No. VI anomaly area in the Bailongshan region provided by an exemplary embodiment of the present application is shown;

[0043] Figure 8b The ore-bearing pegmatite at the 509-2 verification point in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0044] Figure 8c The ore-bearing pegmatite body at the 509-1 verification point in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0045] Figure 8d It shows that the verification point 509-5 in the Bailongshan area provided by the exemplary embodiment of the present application does not contain a mineral pegmatite vein group;

[0046] Figure 8e The garnet mica pegmatite at the verification point 509-6 in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0047] Figure 8fThe tourmaline pegmatite at the 509-9 verification point in the Bailongshan area provided by the exemplary embodiment of the present application is shown;

[0048] Figure 9a An interpretation diagram of the pegmatite vein in the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0049] Figure 9b The dendritic pegmatite vein in the Akshayi region provided by the exemplary embodiment of the present application is shown. Figure 1 ;

[0050] Figure 9c The vein-shaped pegmatite vein in the Akshayi region provided by the exemplary embodiment of the present application is shown. Figure 1 ;

[0051] Figure 9d The vein-shaped pegmatite vein in the Akshayi region provided by the exemplary embodiment of the present application is shown. Figure 2 ;

[0052] Figure 9e The dendritic pegmatite vein in the Akshayi region provided by the exemplary embodiment of the present application is shown. Figure 2 ;

[0053] Figure 10a A comparison diagram of spodumene spectrum curves in the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0054] Figure 10b A comparison diagram of the spectrum curves of muscovite in the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0055] Figure 10c A comparison diagram of quartz spectrum curves in the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0056] Figure 10d A comparison diagram of the spectrum curves of albite in the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0057] Figure 11 The mineral mapping results of the Akshayi area provided by the exemplary embodiment of the present application are shown;

[0058] Figure 12 The mineral mapping results of the abnormal area No. V in the Akshayi region provided by the exemplary embodiment of the present application are shown;

[0059] Figure 13a A distribution map of field verification points in the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0060] Figure 13b The diagram of the mineralized pegmatite vein D1501 in the abnormal area No. 5 in the Akshayi region provided by the exemplary embodiment of the present application is shown;

[0061] Figure 13c The spodumene pegmatite vein diagram of D1501 in the No. 5 abnormal area of ​​Akshayi region provided by an exemplary embodiment of the present application is shown;

[0062] Figure 13d A photo of a hand specimen of spodumene pegmatite D1501 in the No. 5 abnormal area of ​​the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0063] Figure 13e The diagram of the D1503 trench in the abnormal area No. 5 in the Akshayi region provided by the exemplary embodiment of the present application is shown;

[0064] Figure 13f A photo of a hand specimen of spodumene pegmatite D1508 in the No. 5 abnormal area of ​​the Akshayi region provided by an exemplary embodiment of the present application is shown;

[0065] Figure 14 A schematic block diagram of functional modules of a mineral exploration device based on multi-source data fusion according to an exemplary embodiment of the present application is shown;

[0066] Figure 15 shows a schematic block diagram of a chip according to an exemplary embodiment of the present disclosure;

[0067] Figure 16 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0068] To facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. For example, the first threshold and the second threshold are merely used to distinguish between different thresholds and do not limit their order. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity or execution order, and words such as "first" and "second" do not necessarily mean that they are different.

[0069] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0070] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0071] Traditional geological exploration methods struggle to identify and predict large-scale mineral deposits in areas characterized by high altitude and sharply dissected terrain. For example, identifying lithium deposits in such areas typically characterized by high altitude and sharply dissected terrain requires multispectral data from ASTER and Landsat 8. Traditional methods utilize principal component analysis, RGB combination, and band ratios to identify traditional remote sensing alteration information, such as iron staining and hydroxyl groups, as well as lithium mineralization anomalies. Multispectral data has low spectral resolution and is significantly affected by isospectral variations, limiting its ability to identify lithium and non-lithium mineralization in pegmatites. To overcome these challenges, hyperspectral remote sensing technology has emerged in the field of mineral exploration. While it has been widely used in mineral identification, geological mapping, alteration anomaly zoning, and prospecting, it currently relies primarily on airborne hyperspectral data, which presents technical bottlenecks such as high cost, long turnaround times, and limited coverage.

[0072] The successful launch and operation of domestically produced hyperspectral satellites such as Ziyuan-1 02D, particularly the hyperspectral data they provide with a 30-meter spatial resolution and 166 bands, has created favorable conditions for the large-scale application of hyperspectral remote sensing technology. Currently, there is an urgent need to establish a comprehensive set of exploration techniques and methods suitable for granite pegmatite-type rare metal deposits in high-altitude, cold, and deeply dissected terrain.

[0073] The following uses the Dahongliutan area as an example. Located in the Western Kunlun Orogenic Belt, the Dahongliutan area is a typical location with the densest distribution of granite pegmatites and the highest degree of rare metal mineralization. The area's high altitude and sharply dissected terrain, typical of alpine and cold mountainous terrain, make it difficult to identify and predict mineral deposits over a large area using traditional geological exploration methods.

[0074] In order to overcome the above problems, an embodiment of the present application provides a mineral exploration method based on multi-source data fusion, which is used to predict the location of minerals in a target area and provide a reference for mineral prospecting.

[0075] Figure 1 FIG1 shows a flow chart of a mineral exploration method based on multi-source data fusion provided by an exemplary embodiment of the present application. Figure 1 As shown, the mineral exploration method based on multi-source data fusion provided in the embodiment of the present application includes:

[0076] Step 110: Acquire multi-source remote sensing data of the target area, where the multi-source remote sensing data includes remote sensing data from multiple different satellite categories. Exemplarily, the multi-source remote sensing data may include hyperspectral remote sensing data and high spatial resolution remote sensing data, where the resolution of the high spatial resolution remote sensing data is less than or equal to 0.8 m. The hyperspectral remote sensing data may be ZY1E satellite data; and the high spatial resolution remote sensing data may be one or both of GF-2 satellite data and WorldView-3 satellite data. It should be noted that the selection of hyperspectral remote sensing data and high spatial resolution remote sensing data may be determined based on actual conditions and is not limited here. It should be understood that the multiple remote sensing data from different satellite categories here refer to remote sensing data of different categories acquired by different satellites, for example, the hyperspectral remote sensing data and high spatial resolution remote sensing data of different categories involved in this application.

[0077] For example, the ZY1E satellite data has a spectral range of 395-2501nm and contains 166 continuous narrow bands. The visible-infrared band (395-1040nm) has 76 channels with a spectral resolution of 10nm, and the shortwave infrared band (1040-2501nm) has 90 channels with a spectral resolution of 20nm and a spatial resolution of 30m. GF-2 data offers sub-meter high-resolution data, with a panchromatic band resolution of 0.8m and a multispectral resolution of 3.2m. WorldView-3 data has a panchromatic band resolution of 0.3m, a multispectral data of eight bands with a resolution of 1.2m, and eight shortwave infrared bands with a resolution of 3.7m.

[0078] Step 120: Perform image enhancement processing on the multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals. Image enhancement of multi-source remote sensing data optimizes image contrast, effectively highlighting target vein information (e.g., spectral and morphological characteristics), while suppressing background interference, significantly improving the efficiency and accuracy of visual interpretation.

[0079] In practical applications, the above-mentioned image enhancement processing may further include a combination of one or more methods selected from the group consisting of principal component analysis, band ratio method, and band combination method. The actual image enhancement processing method can be selected according to actual needs and is not limited here. Among them, the principal component analysis method accurately identifies the principal component containing the target vein information by analyzing the correspondence between the eigenvector load value and the spectral characteristics. The band ratio method uses multi-band cross-ratio calculations and threshold segmentation or RGB false color synthesis technology to highlight the spectral characteristics of pegmatite veins. The band combination method can maximize the identification differences of different lithologies, clearly reflect the contact relationship between various geological bodies, and effectively indicate the occurrence location of pegmatite veins.

[0080] In some examples, the above-mentioned image enhancement processing of multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals can further include: first performing image enhancement processing on the multi-source remote sensing data, and then determining the spatial distribution information of the target veins containing target minerals based on the multi-source remote sensing data after image enhancement processing.

[0081] When the multi-source remote sensing data includes hyperspectral remote sensing data and high spatial resolution remote sensing data, determining the spatial distribution information of target veins containing target minerals based on the multi-source remote sensing data after image enhancement processing can further include: obtaining hyperspectral color data based on the hyperspectral remote sensing data after image enhancement processing; obtaining high spatial resolution color data based on the high spatial resolution remote sensing data after image enhancement processing; and determining remote sensing identification morphological marker information of the target vein based on the hyperspectral color data and the high spatial resolution color data. The remote sensing identification morphological marker information of the target vein includes the linear distribution characteristics, hue characteristics, texture characteristics, and comparative relationship with the surrounding rock of the target vein, etc., and is used for the identification and interpretation of pegmatite veins in the target area. The hyperspectral color data is true color image data, and the high spatial resolution color data is true color image data or false color image data. It should be noted that the high spatial resolution color data can be selected according to actual conditions and is not limited here.

[0082] In some embodiments, before determining the spatial distribution information of target veins containing target minerals based on multi-source remote sensing data after image enhancement processing, the mineral exploration method based on multi-source data fusion of the present application further includes removing areas with reflectivity greater than a threshold value to reduce interference with the identification results of target veins containing target minerals.

[0083] Step 130: Spectral analysis is performed on the multi-source remote sensing data to obtain spatial distribution information of the target mineral. The spatial distribution information of the target mineral is determined in the multi-source remote sensing data by extracting spectral features within the target area in the multi-source remote sensing data and determining the spectral features of the target mineral from the multiple spectral features.

[0084] However, in actual operation, due to the large spatial resolution of hyperspectral remote sensing data, a single surface pixel contains multiple characteristic features. This type of pixel is a mixed pixel. The spectral characteristics of the pixel are the result of the comprehensive superposition of multiple features. When performing mineral extraction, it is necessary to obtain pure pixels as the basis.

[0085] Based on this, the present application performs spectral analysis on multi-source remote sensing data to obtain spatial distribution information of target minerals, further including: performing minimum noise separation transformation and pure pixel index calculation on multi-source remote sensing data to obtain spatial distribution information of target minerals.

[0086] Step 140: Based on the spatial distribution information of the target vein containing the target mineral and the spatial distribution information of the target mineral, a favorable target area for mineralization of the target vein containing the target mineral is determined. For example, the spatial distribution information of the target vein containing the target mineral and the spatial distribution information of the target mineral can be overlaid and analyzed using an ArcGIS platform to determine a favorable target area for mineralization of the target vein containing the target mineral.

[0087] In order to further combine the method of the present application with actual exploration conditions, verify the accuracy of the method, and reveal the prospecting rules based on known mineral point information to guide the prediction of peripheral target areas, the above-mentioned determination of the mineralization favorable target area of ​​the target vein body containing the target mineral based on the spatial distribution information of the target vein body with the target mineral and the spatial distribution information of the target mineral can further include: determining the mineralization favorable target area of ​​the target vein body containing the target mineral based on the spatial distribution information of the target vein body with the target mineral, the spatial distribution information of the target mineral and the known mineral point data. It should be noted that when determining the mineralization favorable target area of ​​the target vein body containing the target mineral, it is also necessary to combine the known mineral data such as the mineral zoning rules for analysis. Finally, it is also necessary to conduct field verification of the delineated target area to determine the accuracy of the method of the present application and optimize the boundary of the mineralization favorable target area.

[0088] In some embodiments, before performing image enhancement processing on the multi-source remote sensing data, the method further includes: pre-processing the multi-source remote sensing data to improve the recognition accuracy of the multi-source remote sensing data.

[0089] In some embodiments, the preprocessing includes one or more of radiometric calibration, atmospheric correction, geometric correction, striping noise removal, and masking. Radiometric calibration is a key step in converting the digital quantization values ​​(DN values) of remote sensing image pixels into true radiance values ​​or reflectance. In the ENVI 5.6 software environment, the built-in "Radiometric Calibration Tool" automatically reads sensor parameters (such as gain, offset, irradiance, etc.) from metadata, automatically configures the input data type required for FLAASH atmospheric correction, and ultimately outputs radiance values.

[0090] The purpose of atmospheric correction is to eliminate interfering factors such as atmospheric scattering, absorption, and aerosols, converting radiance data into true surface reflectance to meet the requirements of quantitative analysis. The FLAASH module, based on the MODTRAN radiative transfer model, effectively corrects for atmospheric effects from the visible to the shortwave infrared band. Given the unique geographic and climatic conditions of the target area, the "Tropical" atmospheric model was selected based on a latitude-season comparison table.

[0091] The purpose of geometric correction is to correct the geometric errors in the original imagery and accurately display the spatial positions of features. All data is uniformly converted to the WGS-84 coordinate system (Gauss-Krüger projection). The RPC orthorectification tool in ENVI 5.6 software is used to eliminate geometric distortions introduced by the sensor imaging process based on satellite orbit parameters and RPC files. Typical feature points of features measured in the field are selected as control points to perform precise geometric correction on the high-resolution data, with correction accuracy controlled to within one pixel. Using the corrected high-resolution imagery as the spatial reference, spatial alignment of the hyperspectral data is achieved through image registration.

[0092] Removing data stripe noise is a key step in hyperspectral image preprocessing. Reducing the spectral bandwidth in hyperspectral imaging leads to a decrease in signal-to-noise ratio, and the sensor introduces various noise interferences during the imaging process. This application uses a noise removal method based on a Gaussian mixture model, leveraging the low-rank nature of hyperspectral data in the spectral domain and high correlation in the spatial domain to effectively remove stripe noise from the data using the MATLAB platform.

[0093] The mask processing method is a method for eliminating high-reflection interference such as snow and water bodies in the high-altitude environment in the target area. The mask processing method that combines multi-temporal image analysis with threshold segmentation can be used to eliminate interference factors.

[0094] In some embodiments, after performing image enhancement processing on the multi-source remote sensing data, the method provided herein further comprises: first acquiring spectral data for multiple ore samples containing the target mineral within the target region; and then, based on the spectral data for the multiple ore samples containing the target mineral within the target region, determining a database of ore spectra containing the target mineral within the target region. By establishing a database of ore spectra containing the target mineral within the target region, it is possible to better address spectral variation in complex geochemical environments, correct for variations such as weathering and alteration, and supplement spectra in a standard mineral spectral library.

[0095] In some embodiments, the above-mentioned spectral analysis of multi-source remote sensing data to obtain the spatial distribution information of the target mineral further includes: performing end-member spectral analysis on the multi-source remote sensing data to obtain the end-member spectra of multiple minerals in the target area; determining the end-member spectra of the ore containing the target mineral based on the end-member spectra of the multiple minerals in the target area, the ore spectrum database containing the target mineral in the target area, and the standard mineral spectrum library; and determining the spatial distribution information of the target mineral based on the end-member spectra of the ore containing the target mineral. By using the standard mineral spectrum library and the ore spectrum database containing the target mineral in the target area to jointly identify the end-member spectra of multiple minerals in the target area, the recognition accuracy of the end-member spectra of multiple minerals in the target area can be improved. Among them, the mineral spectrum of the standard mineral spectrum library has a wider coverage range and has a unified mineral spectrum standard to ensure the comparability of mineral mapping results in different regions and reduce the risk of different objects with the same spectrum. For minerals in the target area with unclear spectral differences in the ore spectrum database containing the target mineral, the standard mineral spectrum library provides more detailed spectral features. Combined with the angle threshold subdivision of the SAM algorithm, the mineral identification error rate can be reduced from 15% to 5%.

[0096] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0097] Example 1

[0098] Figure 2 The schematic diagram of the Bailongshan area and the Akshayi area in the Dahongliutan area provided by the exemplary embodiment of the present application is shown. Figure 2 As shown, this embodiment selects the Bailongshan area 201 in the Dahongliutan region as the target area, selects the granite pegmatite vein as the target vein body, and selects lithium ore as the target mineral. The multi-source remote sensing data for the target area can include hyperspectral data from the Resource-1 02D satellite (ZY1E) and high spatial resolution data from the GF-2 satellite.

[0099] The core data source is hyperspectral satellite data from the Resource-1 02D satellite (ZY1E), image number ZY1E_AHSI_E78.93_N35.73_20200930_005512_L1A0000170438, acquired on September 30, 2020. The onboard hyperspectral sensor boasts significant technical advantages. It simultaneously acquires 166 continuous narrow bands within the 395-2501nm spectral range, including 76 channels in the visible-near-infrared (VNIR) band (395-1040nm) with a spectral resolution of 10nm, and 90 channels in the shortwave infrared (SWIR) band (1040-2501nm) with a spectral resolution of 20nm. In terms of spatial characteristics, the ZY1E data has a ground resolution of 30 meters and an imaging width of 60 kilometers. This combination of high spectral resolution + moderate spatial resolution + large coverage makes it particularly suitable for large-area mineral mapping and alteration anomaly extraction, providing an ideal data basis for remote sensing exploration of rare lithium deposits in granite pegmatite veins.

[0100] The image numbers of the GF-2 satellite high spatial resolution data are GF2_PMS2_E79.0_N35.8_20200812_L1A0004986347, GF2_PMS2_E79.1_N36.0_20200812_L1A0004986345, GF2_PMS1_E79.3_N35.8_20201015_L1A0005140021, and GF2_PMS1_E79.3_N36.0_20201015_L1A0005140013, and the image acquisition times are August 12, 2020, August 12, 2020, October 15, 2020, and October 15, 2020, respectively. The GF-2 satellite is my country's first independently developed sub-meter high-resolution civilian satellite. Its panchromatic band spatial resolution reaches 0.8m, and the multispectral data (four bands of blue, green, red, and near-infrared) resolution reaches 3.2m. After fusion processing, the image resolution can reach sub-meter level, and the coverage range of a single image is 45km, combining the characteristics of high resolution and large coverage.

[0101] The preprocessing in this embodiment includes radiometric calibration, FLAASH atmospheric correction, and orthorectification of the original image. However, since the signal-to-noise ratio (SNR) of the image data is reduced due to the reduction of the spectral bandwidth of the hyperspectral data, stripe noise exists in some bands (such as Figure 3a As shown), based on this, the preprocessing of this embodiment also includes striping noise removal processing.

[0102] The above stripe noise removal process uses Gaussian mixture model to characterize the complex distribution of mixed noise, and uses MATLAB software to repair the stripe noise of hyperspectral data. The stripe removal effect is significant (such as Figure 3b shown).

[0103] Because the target area is at a high altitude, some areas have perennial snow, and rivers are subject to scouring, resulting in excessively high reflectivity in the image, all of which can affect the extraction of ground feature information. To minimize this impact, the preprocessing process in this embodiment also includes a masking method to remove areas within the target area where the reflectivity exceeds a threshold. For example, areas covered by perennial snow and large rivers within the target area are cropped. It should be understood that the threshold here can be set according to actual circumstances and is not limited here.

[0104] Figure 4a A picture of a spodumene-containing sample provided by an exemplary embodiment of the present application is shown; Figure 4b A picture of a cassiterite sample provided by an exemplary embodiment of the present application is shown; Figure 4c The image of the tourmaline sample provided by the exemplary embodiment of the present application is shown. By measuring the spectrum of the above rock sample, the target mineral measured spectrum of the representative rock sample is obtained (such as Figure 4d As shown in the figure) and the measured rock spectrum (as shown in the figure) Figure 4e Based on this, as Figure 4a-4e As shown, the spectrum data of multiple ore samples containing target minerals in the target area can be obtained by using the American OreXpress near-infrared full spectrum mineral analyzer to analyze typical rock and ore samples in the target area (such as Figure 4a-4c The system performs indoor spectrum measurement.

[0105] To ensure the accuracy and reliability of the spectral measurement data, typical rocks and minerals were measured indoors, effectively avoiding interference from outdoor weather conditions and variations in solar altitude. Secondly, a standard whiteboard calibration was performed before each sample measurement, and repeated measurements were performed at five different locations on each sample. Finally, ENVI 5.6 software was used to preprocess the raw spectral data, including averaging, noise removal, and resampling. Through this standardized measurement and processing process, a spectral database of typical rocks and minerals from the pegmatite vein lithium deposits in the Dahongliutan area was successfully constructed.

[0106] According to the ore spectrum database containing target minerals in the target area, that is, the measured spectrum results of typical minerals (such as Figure 4d and 4e As shown) and the standard mineral spectral library (as Figure 4f), compared with other minerals in the target area, the spodumene spectrum shows obvious absorption characteristics near wavelengths of 1910nm and 2200nm, and has obvious reflection characteristics around 1300nm and 2100nm. The spectrum of the monzonite granite sample (with a large amount of muscovite visible) has no obvious absorption characteristics at 1936nm, but has relatively obvious absorption characteristics around 2200nm. The spodumene pegmatite spectrum forms an extremely obvious absorption valley at a wavelength of 1910nm, and a secondary absorption valley appears at 2200nm. The sandstone surrounding rock spectrum has no obvious absorption and reflection characteristics near wavelengths of 1910nm and 2200nm, and the reflectivity is low.

[0107] Because pegmatites in the target area are primarily distributed at the interface between the Triassic intrusion and the Bayankala Mountain Group, the veins generally extend in a near-northwest-southeast direction and are generally light-toned, with darker tones observed from a distance. Therefore, this embodiment performs image enhancement processing on multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals. Specifically, this includes selecting GF-2 satellite data as a basemap, combining it with ZY1E satellite data for pegmatite vein identification, and performing panchromatic and multispectral data fusion to achieve a resolution better than 1 meter, enabling the identification of pegmatite veins of a certain size.

[0108] Among them, the true color image of RGB (321) combination used in the interpretation of pegmatite veins by GF-2 satellite data has certain limitations and cannot clearly show the contact boundary between the stratum and the rock mass. The spectrum measurement results show that the reflectivity of the monzonitic granite and the surrounding rock in the area is quite different at around 610nm, 2060nm, and 2290nm. The above bands are synthesized by RGB false color ( Figure 5a ), the Bayankala Mountains appear purple, the monzonitic granite appears green, and the contact boundary is clear. During the interpretation process, it was found that the reflectivity of the snow-covered area was too high, which greatly interfered with the pegmatite veins in the area. The snow was cropped, and the image characteristics of the pegmatite veins were more obvious. The pegmatite veins appeared grayish white in the image, which was significantly different from the surrounding gray-brown strata. In the exposed part of the bedrock, the pegmatite veins appeared as discontinuous strip-like ridges, and in the residual slope area, they were exposed in blocky and discontinuous blocks. The surface weathering and erosion in some areas of Dahongliu Beach was relatively serious, and the image characteristics of the pegmatite veins were not obvious. The pegmatite veins have various shapes, such as the mesh ( Figure 5b )Tree-shaped( Figure 5c Based on this, we identified pegmatite veins of a certain size and interpreted a total of 6 pegmatite vein groups.

[0109] Because hyperspectral data has ultra-high spectral resolution, it can support remote sensing mineral identification. Therefore, ZY1E hyperspectral data can be selected as a data source to facilitate the accurate identification of lithium-related minerals within the target area. Endmember spectra are extracted from the preprocessed ZY1E data. Similarity recognition is performed using a standard mineral spectral library and a database of ore spectra containing the target mineral within the target area as references. The mineral types identified by the endmember spectra are then determined, and hyperspectral mineral identification is performed.

[0110] Specifically, the above-mentioned endmember spectrum analysis of multi-source remote sensing data to obtain endmember spectra of multiple minerals in the target area may further include: selecting a pure pixel index method to extract endmember spectra of hyperspectral data. During extraction, the ZY1E hyperspectral data must first be subjected to minimum noise separation. While the transformation reduces the image noise, the data is subjected to dimensionality reduction processing so that the ground feature information is distributed in individual spectral bands. The larger the eigenvalue of each band, the greater the amount of information contained. Bands with larger eigenvalues ​​are selected and the data are subjected to multiple iterations of point projection transformation (PPI) in multidimensional space to obtain a pure pixel index map. At this time, the larger the pixel value, the higher the purity. The ROI tool is used to remove pixels with pixel values ​​below 10 to improve the purity of the pixels and enhance the similarity between the end-member spectrum and the standard mineral spectrum. Finally, the N-dimensional visualization tool of ENVI is used to select the MNF transformation result data with a PPI index above 10. By selecting appropriate bands and performing N-dimensional visual rotation, 15 categories of points that are clustered together at any angle are circled, and the average spectrum of each category in the original image is calculated.

[0111] Determining the end-member spectrum of the ore containing the target mineral can further include: comprehensively utilizing the spectral angle (SAM) and binary code matching (BE) method to match the collected end-member spectrum with the standard mineral spectrum library (USGS) and the ore spectrum database containing the target mineral in the target area. Due to the strong weathering of the surface, there are certain differences between the image end-member spectrum and the standard mineral spectrum library and the ore spectrum database containing the target mineral in the target area. Therefore, in determining the type of mineral represented by the end-member spectrum this time, based on the comprehensive utilization of SAM and BE, the absorption and reflection characteristics of the minerals were compared and judged, the accuracy of the classification of mineral types was improved, the probability of the occurrence of different materials with the same spectrum was reduced, and the end-member spectra of spodumene, muscovite and albite (such as Figure 6a-6c shown).

[0112] like Figure 6a-6cAs shown, the ZY1E end-member spectrum of spodumene closely matches the spectral database of minerals containing the target mineral within the target region. The end-member spectrum exhibits distinct absorption features at wavelengths of 1929 nm and 2230 nm, and distinct reflection features around 1257 nm and 2100 nm. These characteristics are generally consistent with the spectral characteristics of spodumene in the spectral database of minerals containing the target mineral within the target region, demonstrating high mineral identification accuracy. The spectral characteristics of the muscovite end-member spectrum in the visible and near-infrared range differ significantly from those in the standard mineral spectral database and the spectral database of minerals containing the target mineral within the target region. However, the spectrum is highly similar in the short-wave infrared range, with distinct absorption features at 1930 nm and 2284 nm, consistent with the spectral absorption characteristics of muscovite in the standard mineral spectral database. The spectral reflectance of the albite end-member spectrum is less than 0.2 across all wavelengths, with minimal spectral fluctuation. The shallow absorption feature is around 2200 nm, indicating that it is susceptible to the influence of minerals containing aluminum hydroxyls. However, the overall trend is highly consistent with the standard mineral spectrum database and the ore spectrum database containing target minerals in the target area.

[0113] After obtaining ZY1E data endmember spectra of spodumene, muscovite, albite, and other minerals in the area through image endmember spectrum extraction and mineral identification, determining the spatial distribution of target minerals based on the endmember spectra of ores containing the target minerals can further include using the spectral angle method for mineral identification. The spectral angle mapping method uses the target spectrum as a reference line and co-locates vectors in N-dimensional space with the image data spectrum to calculate the generalized angle between the vectors. The smaller the angle, the higher the degree of fit between the two, which improves the classification of weaker spectral information in the data.

[0114] Mineral mapping results (such as Figure 7 As shown in Figure 2, spodumene is distributed in discontinuous bands, extending northwest to southeast. Spodumene, albite, and muscovite exhibit distinct zoning in the Bailongshan area, along the 201 zone. From north to south, the spodumene-mucovite (small amount) zone, the muscovite-albite-spodumene zone, and the albite-spodumene (small amount) zone follow. However, albite is more widely distributed near the rock mass, due to the predominant rock mass in this area being monzogranite. Furthermore, the albite end-member spectral absorption feature is weak, with a shallow absorption feature near 2200 nm, making it susceptible to influence by other minerals containing aluminum hydroxyls, which can hinder the identification of mineralization anomalies.

[0115] According to the mineral assemblage zoning and distribution characteristics, six lithium-bearing anomaly areas were identified (such as Figure 7The results show that the exploration patterns are based on known mineral deposits. The area where the anomaly zone I is located is less explored, and the mineral information extraction results show strong mineralization characteristics. The anomaly zones II, III, IV, V, and VI include the discovered Aktas lithium mine, Dahongliutan North lithium mine, Dahongliutan South lithium mine, Fulugou South No. 2 lithium mine, and 509 lithium mine.

[0116] Anomaly Area II is located far from the rock mass within the Bayankala Mountain Group, home to the Aktas lithium deposit. Lithium mineralization in this anomaly is weak, with muscovite and albite more widespread. Hyperspectral data, affected by mountain shadows, exhibited low reflectivity, preventing effective identification of minerals in the northern upper body. Using GF-2 imagery, multiple vein-like pegmatite veins were identified within the anomaly, trending northwest.

[0117] Anomaly Zone III is located south of the Aktas lithium mine, encompassing the Dahongliutan North lithium mine, at the contact point between the intrusion and the formation. Spectral angular mapping results show that spodumene is primarily distributed at the contact edge between the intrusion and the formation. Mineral zoning within the zone is distinct and symmetrical, with the following sequence from north to south: spodumene-muscovite, spodumene (minor)-albite, and spodumene-muscovite. Multiple large-scale pegmatite veins have been interpreted in the northern part of the anomaly zone, revealing well-defined lithium mineralization.

[0118] The No. Ⅳ mineralized anomaly area is located at the contact between the rock mass and the Bayankala Mountain Group strata. The mineral mapping results show that the area has obvious mineral assemblage zoning, which is from north to south: muscovite (a small amount)-spodumene zone, albite-muscovite-spodumene zone, and albite-spodumene (a small amount) zone. The mineral extraction results show that the southern part is Late Triassic monzonite granite, and the mineralization near the intrusion body is poor. A series of pegmatite veins were identified in the anomaly area and its periphery using GF-2 imaging. The lithium mineralization range in the anomaly area can better distinguish between ore-bearing and non-ore-bearing pegmatite veins.

[0119] Anomaly Zone V lies at the interface between the rock mass and the Bayankala Mountain Group strata, encompassing the No. 2 lithium deposit in the south of the Fulugou Valley. Spectral angular mapping reveals weak lithium mineralization within this zone, with only a small amount occurring in the western portion. However, the zone exhibits a strong albite anomaly. GF-2 image analysis reveals that the weak mineralization is due to severe surface weathering and erosion, the high altitude, residual snow cover, and poor bedrock exposure.

[0120] Spodumene is widely distributed in the No. VI mineralized anomaly area, encompassing the 505 lithium deposit and part of the 509 Daobanxi lithium deposit. Mineral mapping results reveal distinct mineral zoning within the area, with the following progression from north to south: muscovite (minor)-spodumene zone, muscovite-albite-spodumene zone, and albite-spodumene (minor) zone. The distribution of spodumene decreases closer to the intrusion. GF-2 imaging identified a series of northwest-southeast-trending pegmatite dykes within the area. Those located in the northern part of the intrusion exhibit significant lithium mineralization, while those developed near or within the intrusion exhibit poor lithium mineralization.

[0121] Finally, the accuracy of the method of this embodiment has been verified through field verification. The field verification work on the mineralization of the granite pegmatite vein in the No. VI anomaly area is as follows:

[0122] A field survey of the ore-bearing and non-ore-bearing pegmatite veins in the No. VI anomaly area was conducted perpendicular to the mineral zoning direction (e.g. Figure 8a A large amount of spodumene pegmatite was found at both 509-1 and 509-2 field verification points (such as Figure 8b and Figure 8c As shown in Figure 2, minerals such as spodumene, tourmaline and quartz can be seen in the rock mass. Spodumene is light grey or white and is mostly semi-prophetic and plate-like, often accompanied by quartz. Pegmatite veins are mostly covered by Pleistocene residual slope deposits, and light-colored pegmatite vein outcrops appear intermittently on the surface. Garnet mica pegmatite and pegmatite vein groups (such as Figure 8d and Figure 8e As shown in Figure 2), the veins extend in a northwest or north-northwest direction, and the veins fill the formation cracks. The scale varies greatly. The content of spodumene in the pegmatite veins is low, and the content of plagioclase is high (as shown in Figure 2). Figure 8f This is consistent with the pattern of lithium mineralization becoming less common from north to south. Overlay analysis of field validation points with hyperspectral mineral mapping results revealed that the mineral types found in the field samples are generally consistent with the mineral mapping and mineral assemblage zoning results, demonstrating the high accuracy of the hyperspectral mineral mapping results of this example.

[0123] In summary, the method of this embodiment extracts endmember spectra of spodumene, albite, and muscovite by extracting endmember spectra from ZY1E satellite data in the Bailongshan area. The spodumene endmember spectrum forms absorption valleys near wavelengths of 1929nm and 2230nm, and exhibits distinct reflection characteristics around 1257nm and 2100nm. It closely matches the measured spectra of spodumene in the 1500-2500nm range from the spectral database of minerals containing the target minerals in the target area. The mineral endmember spectra have a low degree of fit with the measured spectra in the visible and near-infrared range, but a high degree of fit in the shortwave infrared range. The mineral distribution extracted from the endmember spectra identified by ZY1E satellite data exhibits significant regularity. First, spodumene extends in a northwest-southeast direction, primarily distributed at the contact point between the rock mass and the stratum. Second, the spatial distribution of spodumene, albite, and muscovite shows a relatively clear zoning near Bailongshan. It can be seen that mineral identification using ZY1E hyperspectral data has, to a certain extent, solved the problem of different materials with the same spectrum, improving the accuracy of extracting minerals related to lithium mineralization. Furthermore, based on the distribution and zoning characteristics of minerals such as spodumene, albite, and muscovite, combined with the results of high-resolution imagery pegmatite vein identification, five anomalous areas with known lithium deposits were identified. Field verification of both ore-bearing and non-ore-bearing pegmatite veins within some of these anomalous areas showed that the range of lithium mineralization within the anomalous areas can well indicate the distribution range of known ore-bearing pegmatite veins, and one key area for peripheral prospecting was predicted.

[0124] Example 2

[0125] like Figure 2 As shown, this embodiment selects the Akshayi region 202 in the Dahongliutan area as the target area, selects the granite pegmatite vein as the target vein body, and selects lithium ore as the target mineral. The multi-source remote sensing data for the target area can include hyperspectral data from the Resource-1 02D satellite (ZY1E) and high spatial resolution data from WorldView-3.

[0126] The ZY1E hyperspectral data includes one ZY1E hyperspectral remote sensing image acquired on November 27, 2020. The ZY1E satellite data covers visible, near-infrared, and shortwave infrared bands, with a spectral resolution of 10 to 20 nm and a spatial resolution of 30 m. Each image is approximately 60 km wide.

[0127] The WorldView-3 high-spatial-resolution data utilizes cloud-free Class 2A WorldView-3 imagery, acquired on August 31, 2023. Currently, the Worldview-3 satellite boasts the highest spatial resolution of any commercial satellite, providing panchromatic data at 0.3m resolution. Its multispectral data includes eight bands (1.2m resolution), along with unique shortwave infrared (SWIR) detection capabilities (eight bands, 3.7m resolution) and 12 CAVIS atmospheric correction bands. These bands clearly display pegmatite information, facilitating the precise identification of pegmatite veins. The satellite has an average revisit period of less than one day, collecting up to 680,000 square kilometers of data daily.

[0128] In this embodiment, ENVI software can be used to pre-process ZY1E and WorldView-3 remote sensing data. Through radiometric calibration, the pixel brightness value (DN value) of the original image is converted into the corresponding radiometric brightness value to reduce the impact of sensor errors. In order to reduce the impact of the atmosphere, the FLAASH atmospheric correction model is used to perform atmospheric correction to restore the true spectral information of the surface. Orthorectification improves the spatial accuracy of the image by correcting the geometric distortion caused by terrain, camera geometry and sensor errors. In addition, WorldView-3 data also undergoes geometric precision correction, data resampling, band fusion and band superposition processing to optimize image quality and improve the accuracy of mineral information extraction. It should be noted that the pre-processing methods designed in this embodiment are all existing methods and will not be described in detail here.

[0129] It should be noted that due to the high altitude within the target area, some areas are permanently covered by snow. Furthermore, due to the long-term erosion of river channels, snow and river channels exhibit high reflectivity in remote sensing imagery. These factors have a certain impact on the extraction of surface mineral information. To reduce these interferences, the preprocessing in this embodiment can also include removing areas with reflectivity above a threshold, that is, masking areas covered by perennial snow and large bodies of water.

[0130] This example uses an SVC HR-1024I spectrometer to perform spectral measurements on 66 pegmatite samples from a target area in a dark environment, generating a database of ore spectra containing target minerals within the target area. The analysis results show that, compared to other minerals, spodumene exhibits a stronger absorption signature at 1910 nm, a secondary absorption signature at 2200 nm, and a reflectance signature at 2130 nm. Albite exhibits absorption signatures at both 1910 nm and 2200 nm. Muscovite exhibits a significant absorption signature around 2200 nm, with a secondary absorption peak at 1410 nm and a visible reflectance signature at 2270 nm. The spectral curve of quartz is relatively flat, with the primary absorption signature occurring around 2200 nm. By extracting the spectral signatures of rocks and minerals from remotely sensed geological information, unique spectral reflectance curves are obtained for each rock and mineral. By analyzing the spectral signatures of minerals in specific wavelengths and combining them with mathematical methods, the accuracy of ground feature identification can be effectively improved, providing guidance for mineral prospecting.

[0131] Since the target area is located in the north of Dahongliutan, the width of the ore-bearing pegmatite vein group varies greatly, and there are obvious differences in scale and morphology between the vein groups. In addition, due to the special geographical environment of the high-altitude and cold regions, the veins have been subjected to strong weathering and erosion for a long time, and the surface Quaternary system covers a wide range, which makes surface identification difficult. In true color remote sensing images, lithium ore in granite pegmatite veins usually appears as light-colored or white strip-like features. Due to its high resistance to weathering, it often forms a prominent ridge-like structure. Most of the pegmatite veins in the target area are filled along fractures or faults, with regular morphology, usually in a dendritic or en echelon distribution, and accompanied by local bifurcation phenomena. Therefore, in order to improve the recognition accuracy of the spatial distribution characteristics of pegmatite veins, this embodiment uses WorldView-3 high spatial resolution remote sensing data to carry out interpretation work (such as Figure 9b-9e ).

[0132] Based on this, the WorldView-3 high-resolution remote sensing images can be enhanced using principal component analysis (PCA), band ratio method, and band combination method to highlight the spectral and morphological characteristics of the target dykes and improve the accuracy and reliability of remote sensing interpretation.

[0133] Principal component analysis (PCA) is a remote sensing data processing technique widely used in the geological field, often used for geological information extraction tasks such as lithology identification and structural extraction. This method uses mathematical transformations to compress highly correlated information between bands in multispectral imagery into several unrelated principal component bands, reducing data dimensionality while effectively minimizing redundant information and noise interference. This example uses principal component analysis to process WorldView-3 high-spatial-resolution remote sensing data, selecting the first three principal components (PC1, PC2, and PC3) for RGB false-color synthesis to enhance the contrast between granite pegmatites and the surrounding rock.

[0134] The band ratio method has important application value in the qualitative identification of lithologic units and the extraction of altered minerals. By constructing band ratios or spectral indices, this method can effectively reduce the illumination differences caused by topographical undulations and reduce the interference of surface shadow effects on remote sensing interpretation results. In addition, combining band ratios to generate color composite images not only improves the visualization of multispectral data, but also enhances the differences in geological features, helping to reveal details that are difficult to identify in single-band images. In this example, based on WorldView-3 high-spatial-resolution remote sensing data and the spectral characteristics of the target minerals, a Band 8 / 10 ratio combination scheme was constructed to improve the identification accuracy of pegmatite veins.

[0135] Based on the processing results of principal component analysis and band ratio method, two band combination schemes were constructed. One is RGB synthesis based on principal component analysis (R(PC1)G(PC2)B(PC3)), and the pegmatite veins appear yellow in the image; the other is RGB synthesis based on band ratio (R(7)G(8 / 10)B(4)), and the pegmatite veins appear light purple to nearly white. Based on these two significant feature combination schemes, the spatial distribution information of the target vein body with target minerals (such as Figure 9a A total of 198 pegmatite veins were identified, which were divided into five major pegmatite vein clusters.

[0136] When obtaining spatial distribution information on target minerals, the target area's mineralized structures are primarily composed of small or massive pegmatites, quartz-spodumene zones, and albite-quartz-spodumene zones. Quartz and spodumene are the primary minerals, with minor amounts of albite and muscovite. Pegmatites with full-vein spodumene mineralization are generally distributed as veins or vein swarms. Zoning of pegmatite veins is particularly pronounced. The 509 lithium-bearing pegmatite vein swarm is the most prominent, with a quartz-spodumene zone, albite-quartz-spodumene zone, and albite-quartz-muscovite zone from north to south. These zones exhibit strong lithium mineralization in the outer contact zone away from the intrusion, while the near-intrusion zone lacks lithium mineralization. Therefore, this embodiment uses ZY1E hyperspectral data to extract the mineral-bearing information of pegmatite veins, adopts end-member spectroscopy to extract the mineral spectral curve in the image, and combines the mineral standard spectrum in the standard mineral spectral library and the ore spectrum database containing the target mineral in the target area to determine the mineral type in the image, thereby realizing the extraction of the spatial distribution information of the target mineral.

[0137] First, the minimum noise factorization (MNF) method is used to suppress image noise and perform dimensionality reduction, concentrating the ground feature information on bands with larger eigenvalues, which usually contain more effective information. After multiple iterative operations on the data, the bands with higher eigenvalues ​​are selected, and a pure pixel index map is generated through scatter projection transformation. The ROI tool is used to remove low-value interference pixels (threshold <10). Based on the N-dimensional visualization tool, appropriate multidimensional rotation analysis is performed on the MNF transformation results, 15 types of cluster points are circled, and their average spectra in the original image are calculated. The extracted end-member spectra are matched and analyzed with the standard mineral spectrum library and the ore spectrum database containing the target minerals in the target area, and finally the spectral curve extraction of spodumene, muscovite, quartz and albite is achieved (such as Figure 10a-Figure 10d shown).

[0138] In this embodiment, the traditional spectral angle mapping (SAM) method is used to identify minerals such as spodumene, quartz, muscovite, and albite. The results show that ( Figure 11 The minerals are distributed in a banded pattern, with a high content of albite and a spodumene, which is relatively scarce and mainly concentrated in the northern part of the study area, while tourmaline and quartz are mainly distributed in the southwest.

[0139] The mineral mapping results show (such as Figure 11As shown in Figure 2, spodumene in this area is distributed along a northwest-southeast direction, exhibiting discontinuous banding. Mineral spatial zoning is evident in this region, with a quartz-spodumene-mucovite-albite zone, a mucovite-albite-spodumene zone, and a quartz-mucovite-spodumene zone, sequentially forming along the north-south direction. Albite is primarily found around rock masses, closely related to the geological setting of the region, where the rock masses are primarily composed of monzogranite. Furthermore, analysis of WorldView-3 imagery reveals significant weathering and fragmentation in some areas.

[0140] Due to Quaternary sedimentary layers, the surface extension of some pegmatite veins is not clearly visible, thus affecting their accurate identification. Furthermore, mountain shadows and snow cover in the image also affect the extraction of mineralized anomalies, resulting in weak mineralization in anomaly areas III and IV.

[0141] Using the ArcGIS platform, we conducted a spatial overlay analysis of remote sensing anomalies and known pegmatite lithium deposits, ultimately identifying five remote sensing anomaly areas with prospecting potential. The specific analysis results are as follows:

[0142] Anomaly Area I is located at the junction of the Huangyangling Group and the Kangxiwa Group. It exhibits mineral zoning from east to west, characterized by a muscovite (minor)-quartz-spodumene zone and albite-muscovite-spodumene zone. Twenty-three northwest-trending pegmatite veins have been identified within the area, exhibiting vein-like and dendritic morphologies with significant variation in vein width. Due to strong weathering at high altitude, the surface outcrop continuity of some veins is poor, and no lithium mineralization has yet been discovered in the area.

[0143] Anomaly Area II is located within the Huangyangling Group. Mineral distribution characteristics show that spodumene is primarily concentrated in the northern part of the anomaly, decreasing from north to south, while quartz and albite are widely distributed throughout the area. A total of 18 pegmatite veins were interpreted. These veins are generally narrow but have good extension and distinct morphological features. They trend primarily northwest and are likely influenced by regional faults or shear zones.

[0144] Anomaly Area III is located within the Kangxiwa Group, with Triassic monzonitic granite distributed in the southwest. Lithium mineralization is weak within the area, limited to localized development in the western part, while albite anomalies are more prominent near the northern edge of the intrusion. Thirty-five pegmatite veins have been identified, primarily occurring within the formation and trending northwest, indicating significant structural control. Due to the low level of exploration in this area, no known lithium mineralization has been discovered.

[0145] Anomaly Area IV is located at the contact zone between the Huangyangling Group and the Kangxiwa Group. The Kashitag lithium deposit and the Dahongliutan East lithium deposit have been discovered within the area. Mineral mapping results show that the Kangxiwa Group has high concentrations of spodumene and albite, while the Huangyangling Group is dominated by quartz. Twenty-two pegmatite veins were identified. These veins are large in size but generally have poor mineralization, indicating relatively limited mineralization potential.

[0146] Anomaly Area V involves the northern lithium deposit of Fulugou, located within the Triassic Bayankala Mountain Group. Mineral mapping reveals that spodumene is primarily concentrated in the central portion of the anomaly, with distinct mineral zoning patterns, from east to west, showing spodumene-muscovite-albite zones and quartz-spodumene (minor)-muscovite zones. Over 50 pegmatite veins were interpreted, with several larger ones in the northern region, accompanied by significant lithium mineralization. Known lithium deposits east of the anomaly further validate the accuracy of the mineral mapping results.

[0147] The presence of known mineral deposits in anomaly zones IV and V confirms the validity of the method and suggests that their periphery still has exploration value. However, there are no known mineral deposits in anomaly zones I, II, and III. Anomaly zone V has been assessed as the most promising due to its pegmatite vein development and significant lithium mineralization.

[0148] For the No. 5 anomaly area with great mineralization potential, this example uses the WorldView-3 high spatial resolution remote sensing data based on the ore spectrum database containing the target minerals in the target area to perform spectral angular mapping of spodumene, quartz, albite and muscovite in the area to further reveal the spatial distribution information of the minerals and their mineralization relationship with the pegmatite veins. The spectral angular mapping results are shown in Figure 2. Figure 12 shown.

[0149] Mineral mapping results show that the spatial distribution of minerals in this area has obvious directional characteristics, with an overall northwest-trending zonal distribution. This distribution trend is consistent with the direction of the main structural lines in the area, further indicating that fault structures played an important controlling role in the mineralization of pegmatite-type lithium deposits. Specifically, the mineral assemblage characteristics in the eastern part of the anomaly are significant, with high contents of spodumene, albite, and muscovite. In particular, spodumene shows a high enrichment trend in the northeastern part of the anomaly, near the river, while the distribution of quartz is relatively scattered, with no obvious enrichment zone.

[0150] The Fulugoubei lithium deposit lies within the relatively high spodumene concentration in the eastern part of the anomaly, demonstrating the reliability of the mineral mapping results for this area and further confirming the effectiveness of WorldView-3 data in the exploration of pegmatite-type lithium deposits. Combined with the distribution characteristics of known deposits, the zoning patterns of mineral assemblages, and remote sensing image interpretation, this area has excellent mineralization potential, particularly in the northeastern region with high spodumene enrichment, providing important evidence for subsequent prospecting.

[0151] Finally, the accuracy of the method of this embodiment has been verified through field verification. Field verification work was carried out on the No. 5 anomaly area with the greatest mineralization potential, and a total of 13 field verification points were investigated (such as Figure 13a-13f The results are consistent with expectations, as shown below:

[0152] Field investigations in the No. 5 anomaly area focused on mineral zoning. The field survey results for mineral zoning are consistent with those extracted from remote sensing images. The pegmatite veins in this area are primarily divided into two types: one containing spodumene and the other containing tourmaline. The distribution of these two types of veins follows a distinct pattern: spodumene-bearing pegmatite veins in the center, muscovite-bearing veins at the boundary, and tourmaline-bearing veins in the periphery. Exploration trenches were discovered at three verification points, and a marble vein approximately 100 meters wide was discovered at the foot of the mountain.

[0153] By comparing and analyzing the field verification data with the WorldView-3 mineral mapping results, the mineral types in the field samples and the mineral zoning characteristics in the remote sensing extraction results showed a high degree of consistency. This further verified the accuracy of the hyperspectral data mineral mapping of this embodiment. In summary, the method of combining hyperspectral and high-spatial resolution remote sensing data in the identification of lithium ore pegmatite veins not only provides important support for the study of mineral assemblage zoning characteristics within the mining area, but also effectively identifies potential mineral-bearing pegmatite veins outside the area, providing a theoretical basis and technical support for prospecting work, and has broad application prospects.

[0154] In summary, this example utilizes WorldView-3 high-spatial-resolution imagery, combined with three image enhancement techniques: principal component analysis, band ratio analysis, and band combination analysis. A total of 198 pegmatite veins were identified and five pegmatite vein clusters were delineated. Spectral measurements were performed on typical minerals in the target area, and a database of ore spectra (measured spectral library) containing target minerals within the target area was established. End-member spectra of spodumene, quartz, albite, and muscovite were extracted using ZY1E satellite data. ZY1E spectral angle mapping results show that spodumene is enriched in the strata along a northwest-southeast direction, forming mineral zoning structures near the Huangyangling Group: a quartz-spodumene-muscovite-albite zone, a muscovite-albite-spodumene zone, and a quartz-albite-spodumene zone. Ultimately, this example delineated five potential lithium mineralization anomalies, two of which coincided with known lithium deposits. The WorldView-3 spectral angle mapping results show that the No. 5 anomaly area has high mineralization potential. Field verification has determined that this area is a potential peripheral prospecting target area, providing an important basis for subsequent prospecting work.

[0155] The above mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of the server. It can be understood that in order to realize the above functions, the server includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0156] The embodiments of the present disclosure can divide the server into functional units according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0157] In the case of dividing each functional module according to each function, an embodiment of the present application further provides a mineral exploration device based on multi-source data fusion, which may be a server or a chip applied to a server. Figure 14 FIG1 shows a schematic block diagram of the functional modules of a mineral exploration device based on multi-source data fusion according to an exemplary embodiment of the present application. Figure 14As shown, the mineral exploration device 1400 based on multi-source data fusion includes:

[0158] An acquisition module 1401 is used to acquire multi-source remote sensing data of a target area, where the multi-source remote sensing data includes remote sensing data from multiple different satellite categories;

[0159] An acquisition module 1402 is used to perform image enhancement processing on multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals;

[0160] The acquisition module 1402 is also used to perform spectral analysis on multi-source remote sensing data to obtain spatial distribution information of target minerals;

[0161] The determination module 1403 is used to determine the mineralization favorable target area of ​​the target vein body containing the target mineral based on the spatial distribution information of the target vein body containing the target mineral and the spatial distribution information of the target mineral.

[0162] As a possible implementation method, the multi-source remote sensing data includes hyperspectral remote sensing data and high spatial resolution remote sensing data, and the resolution of the high spatial resolution remote sensing data is less than or equal to 0.8 m.

[0163] In some optional embodiments, the hyperspectral remote sensing data is ZY1E satellite data.

[0164] In some optional embodiments, the high spatial resolution remote sensing data is one or more of GF-2 satellite data and WorldView-3 satellite data.

[0165] In some optional embodiments, the acquisition module 1402 is further configured to pre-process multi-source remote sensing data.

[0166] In some optional embodiments, the preprocessing includes one or more of radiation calibration, atmospheric correction, geometric correction, stripe noise removal and mask processing.

[0167] In some optional embodiments, the acquisition module 1401 is further configured to acquire spectral data of a plurality of ore samples containing a target mineral in a target area;

[0168] The determination module 1403 is further configured to determine an ore spectrum database containing the target mineral in the target area based on spectral data of a plurality of ore samples containing the target mineral in the target area.

[0169] In some optional embodiments, the obtaining module 1402 is further configured to perform endmember spectrum analysis on multi-source remote sensing data to obtain endmember spectra of multiple minerals in the target area;

[0170] The determination module 1403 is also used to determine the end-member spectrum of the ore containing the target mineral based on the end-member spectrum of multiple minerals in the target area, the ore spectrum database containing the target mineral in the target area, and the standard mineral spectrum library; based on the end-member spectrum of the ore containing the target mineral, determine the spatial distribution information of the target mineral.

[0171] Figure 15 FIG. 1 shows a schematic block diagram of a chip according to an exemplary embodiment of the present disclosure. Figure 15 As shown, the chip 1500 includes one or more (including two) processors 1501 and a communication interface 1502. The communication interface 1502 can support the server to perform the data sending and receiving steps in the above-mentioned image processing method, and the processor 1501 can support the server to perform the data processing steps in the above-mentioned image processing method.

[0172] Optional, such as Figure 15 As shown, the chip 1500 also includes a memory 1503, which may include a read-only memory and a random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory (NVRAM).

[0173] In some embodiments, as Figure 15 As shown, the processor 1501 performs corresponding operations by calling the operation instructions stored in the memory (the operation instructions may be stored in the operating system). The processor 1501 controls the processing operations of any one of the terminal devices, and the processor may also be called a central processing unit (CPU). The memory 1503 may include a read-only memory and a random access memory, and provides instructions and data to the processor 1501. A portion of the memory 1503 may also include NVRAM. For example, in an application, the memory, the communication interface, and the memory are coupled together through a bus system, wherein the bus system may include a power bus, a control bus, and a status signal bus in addition to a data bus. However, for the sake of clarity, in Figure 15 Various buses are labeled as bus system 1504.

[0174] The methods disclosed in the above embodiments of the present disclosure can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. The above processor may be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0175] The exemplary embodiments of the present disclosure further provide an electronic device including: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which, when executed by the at least one processor, causes the electronic device to perform a method according to an exemplary embodiment of the present disclosure.

[0176] Exemplary embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform the method according to an embodiment of the present disclosure.

[0177] Exemplary embodiments of the present disclosure further provide a computer program product, including a computer program, wherein when the computer program is executed by a processor of a computer, it is used to cause the computer to perform the method according to the embodiment of the present disclosure.

[0178] refer to Figure 16, a block diagram of an electronic device 1600 that can serve as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0179] like Figure 16 As shown, electronic device 1600 includes a computing unit 1601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1602 or a computer program loaded from a storage unit 1608 into a random access memory (RAM) 1603. Various programs and data required for the operation of electronic device 1600 can also be stored in RAM 1603. Computing unit 1601, ROM 1602, and RAM 1603 are connected to each other via a bus 1604. An input / output (I / O) interface 1605 is also connected to bus 1604.

[0180] Multiple components within electronic device 1600 are connected to I / O interface 1605, including an input unit 1606, an output unit 1607, a storage unit 1608, and a communication unit 1609. Input unit 1606 can be any type of device capable of inputting information into electronic device 1600. Input unit 1606 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 1607 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 1608 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 1609 allows electronic device 1600 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0181] The computing unit 1601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1601 performs the various methods and processes described above. For example, in some embodiments, the method of the exemplary embodiments of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1600 via the ROM 1602 and / or the communication unit 1609. In some embodiments, the computing unit 1601 may be configured to perform the method of the exemplary embodiments of the present disclosure by any other appropriate means (e.g., by means of firmware).

[0182] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0183] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0184] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0186] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0187] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0188] In the above embodiments, they can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present disclosure are performed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD).

[0189] Although the present disclosure has been described with reference to specific features and embodiments thereof, it will be apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely illustrative of the present disclosure as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is intended to include such modifications and variations if they fall within the scope of the claims of the present disclosure and their equivalents.

Claims

1. A mineral exploration method based on multi-source data fusion, characterized in that: The method comprises: Acquiring multi-source remote sensing data of a target area, wherein the multi-source remote sensing data includes remote sensing data from multiple different satellite categories; performing image enhancement processing on the multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals; Performing spectral analysis on the multi-source remote sensing data to obtain spatial distribution information of the target mineral; Based on the spatial distribution information of the target vein body containing the target mineral and the spatial distribution information of the target mineral, a favorable target area for mineralization of the target vein body containing the target mineral is determined.

2. The mineral exploration method based on multi-source data fusion according to claim 1, characterized in that: The multi-source remote sensing data includes hyperspectral remote sensing data and high spatial resolution remote sensing data, and the resolution of the high spatial resolution remote sensing data is less than or equal to 0.8 m.

3. The mineral exploration method based on multi-source data fusion according to claim 2, characterized in that: The hyperspectral remote sensing data is ZY1E satellite data; and / or, The high spatial resolution remote sensing data is one or more of GF-2 satellite data and WorldView-3 satellite data.

4. The mineral exploration method based on multi-source data fusion according to claim 1, characterized in that: Before performing image enhancement processing on the multi-source remote sensing data, the method further includes: preprocessing the multi-source remote sensing data.

5. The mineral exploration method based on multi-source data fusion according to claim 4 is characterized in that: The preprocessing includes one or more of radiation calibration, atmospheric correction, geometric correction, stripe noise removal and mask processing.

6. The mineral exploration method based on multi-source data fusion according to claim 1, characterized in that: After performing image enhancement processing on the multi-source remote sensing data, the method further includes: Acquiring spectral data of a plurality of ore samples containing the target mineral in the target area; Based on the spectral data of a plurality of ore samples containing the target mineral in the target area, a spectral database of ore containing the target mineral in the target area is determined.

7. The mineral exploration method based on multi-source data fusion according to claim 6, characterized in that: The performing spectral analysis on the multi-source remote sensing data to obtain spatial distribution information of the target mineral includes: performing endmember spectrum analysis on the multi-source remote sensing data to obtain endmember spectra of multiple minerals in the target area; Determining the end-member spectrum of the ore containing the target mineral based on end-member spectra of multiple minerals in the target area, a spectral database of ores containing the target mineral in the target area, and a standard mineral spectral library; Based on the end-member spectrum of the ore containing the target mineral, the spatial distribution information of the target mineral is determined.

8. A mineral exploration device based on multi-source data fusion, characterized in that: The device comprises: An acquisition module, wherein the acquisition module is used to acquire multi-source remote sensing data of a target area, wherein the multi-source remote sensing data includes remote sensing data of multiple different satellite categories; an acquisition module, the acquisition module being used to perform image enhancement processing on the multi-source remote sensing data to obtain spatial distribution information of target veins containing target minerals; The acquisition module is further used to perform spectral analysis on the multi-source remote sensing data to obtain spatial distribution information of the target mineral; A determination module is used to determine a favorable target area for mineralization of a target vein body containing the target mineral based on the spatial distribution information of the target vein body having the target mineral and the spatial distribution information of the target mineral.

9. An electronic device, characterized in that: include: processor; as well as, Memory for storing programs; The program includes instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program comprises a computer program, wherein the computer program, when executed by a processor of a computer, is configured to cause the computer to perform the method according to any one of claims 1 to 7.

Images