Method, device and equipment for analyzing iron-rich ore information in coverage area and storage medium

Abstract

This invention relates to the field of mineralization analysis technology, and particularly to a method, apparatus, equipment, and storage medium for analyzing information on rich iron ore deposits in covered areas. The method integrates multi-dimensional information such as gravity data, magnetic aerobatic ΔT data, remote sensing images, and geological data of the area to be predicted, constructing a feature system that comprehensively reflects mineralization conditions. This overcomes the limitations of single data source analysis, providing a rich and accurate data foundation for the intelligent delineation of mineralization target areas and significantly improving the accuracy of mineralization prediction. Furthermore, the method employs a collaborative analysis of fracture inference maps, regional magnetic anomaly plane maps, three-dimensional probability models of magnetic bodies, and hydroxyl anomaly distribution vector maps. This not only provides a rich and accurate data foundation for the intelligent delineation of mineralization target areas and further improves the accuracy of mineralization prediction, but also significantly enhances the systematic nature of concealed ore body identification. Compared with traditional methods relying on human experience, this method effectively improves the objectivity of mineralization prediction.

Description

Technical Field

[0001] This invention relates to the field of mineralization analysis technology, and in particular to a method, apparatus, equipment and storage medium for analyzing information on rich iron ore deposits in covered areas. Background Technology

[0002] In the field of iron ore exploration in covered areas, regional geological structure analysis and gravity field characteristic analysis are fundamental tasks supporting target area delineation and mineralization potential evaluation.

[0003] Regional tectonic analysis, through a systematic assessment of the morphology, occurrence, contact relationships, and tectonic activity remnants of geological bodies, aims to reveal the regional tectonic framework, evolutionary history, and deep geological mechanisms, providing crucial geological evidence for identifying ore-controlling structures and locating concealed mineralization zones. However, traditional tectonic analysis methods heavily rely on field geological mapping, outcrop observation, drilling sampling, and indoor petrological and structural analysis. This not only has limitations such as being time-consuming, labor-intensive, and costly, but also shows significant shortcomings in detecting covered areas and deep concealed structures, making it difficult to quickly obtain regional-scale tectonic distribution characteristics, thus restricting the efficiency and accuracy of iron-rich ore target area prediction.

[0004] Gravity exploration, as an important geophysical tool for regional geological research, indirectly reflects the spatial distribution of geological bodies of different densities underground by capturing subtle changes in the Earth's gravity field, i.e., gravity anomalies. This provides effective clues for inferring deep structural boundaries, dividing geological units, and identifying concealed rock masses and mineralized bodies. Its data has advantages such as wide coverage, large detection depth, and relatively low acquisition cost, and is widely used in the exploration of rich iron ore. However, traditional processing and interpretation processes face significant bottlenecks when dealing with massive amounts of gravity field data: on the one hand, data processing involves multiple steps such as topographic correction, anomaly separation, and feature extraction, which are cumbersome and highly specialized; on the other hand, the interpretation process is highly dependent on human experience, and different personnel are prone to subjective differences in the identification and inference of anomalies, making it difficult to guarantee the objectivity and efficiency of the initial screening of gravity fields, which directly affects the rapid identification of favorable target areas for rich iron ore in the covered area.

[0005] It is evident that existing technologies still need improvement and enhancement. Summary of the Invention

[0006] To fill the gaps in the existing technology, the present invention aims to provide a method for analyzing information on rich iron ore deposits in covered areas, which breaks through the limitations of traditional single-data prediction and significantly improves the accuracy and reliability of mineralization target area prediction through progressive fusion of multi-source data.

[0007] The first aspect of this invention provides a method for analyzing information on rich iron ore deposits in a covered area, comprising: acquiring and processing gravity data of the area to be predicted to obtain information on high gravity value areas; generating a fault inference map based on the acquired high gravity value area information; acquiring and processing magnetic and aerobatic ΔT data of the area to be predicted to generate a regional magnetic anomaly plane map; identifying potential mineralization areas based on the fault inference map and the regional magnetic anomaly plane map; acquiring and processing magnetic profile data of the potential mineralization areas to obtain a three-dimensional probability model of magnetic bodies; acquiring and processing remote sensing images of the area to be predicted to generate a hydroxyl anomaly distribution vector map; acquiring geological data of the area to be predicted; and generating a mineralization probability target area map based on the geological data, the fault inference map, the regional magnetic anomaly plane map, the three-dimensional probability model of magnetic bodies, and the hydroxyl anomaly distribution vector map.

[0008] Optionally, in a first implementation of the first aspect of the present invention, the step of acquiring and processing gravity data of the region to be predicted to obtain information on high gravity values, and generating a fracture prediction map based on the acquired high gravity value information, includes: acquiring 1:50,000 gravity data of the region to be predicted after terrain interference processing; performing a 3-level decomposition of the gravity data using the db5 wavelet to separate the regional field with wavelength >10km and the local field with wavelength in the range of 2-5km; acquiring a regional geological map, verifying the separated local field based on the regional geological map to obtain information on high gravity values; calculating the total horizontal gradient of the local field, and extracting gradient abrupt change zones of the local field using the Canny algorithm based on the calculated total horizontal gradient; and generating a fracture prediction map based on the extracted gradient abrupt change zones.

[0009] Optionally, in a second implementation of the first aspect of the present invention, the step of acquiring and processing the magneto-aerial ΔT data of the region to be predicted to generate a regional magnetic anomaly planar map includes: acquiring 1:50,000 magneto-aerial ΔT data of the region to be predicted, where ΔT represents the total magnetic field strength anomaly; performing polarization processing and 5km upward extension processing on the magneto-aerial ΔT data to obtain processed magnetic anomaly data; calculating the total horizontal gradient of the processed magnetic anomaly data; extracting gradient abrupt change zones based on the calculated total horizontal gradient using the Canny algorithm; and generating a regional magnetic anomaly planar map based on the extracted gradient abrupt change zones.

[0010] Optionally, in a third implementation of the first aspect of the present invention, the step of confirming the mineralization potential region based on the fracture inference map and the regional magnetic anomaly planar map, obtaining and processing the magnetic profile data of the mineralization potential region to obtain a three-dimensional probability model of the magnetic body includes: overlaying the fracture inference map and the regional anomaly planar map to confirm the mineralization potential region; obtaining 1:10,000 magnetic profile data within the confirmed mineralization potential region; performing a two-level decomposition of the magnetic profile data using the sym8 wavelet, retaining effective magnetic anomaly data of 50-500 nT through threshold noise reduction; inputting the effective magnetic anomaly data and gravity high value region information into a pre-trained UNet++ model to obtain regional probability information; and generating a three-dimensional probability model of the magnetic body based on the regional probability information.

[0011] Optionally, in a fourth implementation of the first aspect of the present invention, the step of acquiring and processing the remote sensing image of the region to be predicted to generate a hydroxyl anomaly distribution vector map includes: acquiring the remote sensing image of the region to be predicted, wherein the remote sensing image is a Landsat 9 OLI image; performing radiometric calibration, atmospheric correction, and geometric correction on the remote sensing image to obtain a preprocessed remote sensing image; calculating the spectral indices of the preprocessed remote sensing image, wherein the calculated spectral indices include the hydroxyl index, the iron staining index, and the normalized vegetation index; superimposing the original RGB bands of the preprocessed remote sensing image with the calculated spectral indices to construct a 7-band dataset; and inputting the constructed 7-band dataset into a pre-trained U-Net classification model to obtain a hydroxyl anomaly distribution vector map.

[0012] Optionally, in the fifth implementation of the first aspect of the present invention, the step of acquiring geological data of the area to be predicted and generating a mineralization probability target area map based on the geological data, fault inference map, regional magnetic anomaly plane map, three-dimensional probability model of magnetic body, and hydroxyl anomaly distribution vector map includes: acquiring geological data of the area to be predicted, wherein the geological data is a depth model of the top surface of Ordovician limestone; converting the geological data fault inference map, regional magnetic anomaly plane map, three-dimensional probability model of magnetic body, and hydroxyl anomaly distribution vector map into raster data in the unified coordinate system of ArcGIS Pro; extracting 12 index features reflecting mineralization conditions from the raster data to construct a multi-source feature dataset; inputting the multi-source feature dataset into a pre-trained XGBoost classifier to obtain the mineralization probability; and constructing a mineralization probability target area map based on the mineralization probability.

[0013] Optionally, in a sixth implementation of the first aspect of the present invention, the step of constructing a mineralization probability target area map based on the mineralization probability further includes: obtaining drilling verification results, the drilling verification results including well logging data at the borehole location and surface geophysical data around the borehole location; constructing borehole constraints based on the drilling verification results; and adjusting the feature weights of the XGBoost classifier using the least squares inversion method based on the constructed borehole constraints.

[0014] A second aspect of the present invention provides an information analysis device for rich iron ore in a covered area, comprising: a first generation module for acquiring and processing gravity data of the area to be predicted to obtain information on high gravity value areas, and generating a fault inference map based on the acquired high gravity value area information; a second generation module for acquiring and processing magnetic-aerial ΔT data of the area to be predicted to generate a regional magnetic anomaly plane map; a first processing module for acquiring magnetic profile data of the mineralization potential area based on the fault inference map and the regional magnetic anomaly plane map, processing the magnetic profile data of the mineralization potential area to obtain a three-dimensional probability model of magnetic bodies; a second processing module for acquiring and processing remote sensing images of the area to be predicted to generate a hydroxyl anomaly distribution vector map; and a third generation module for acquiring geological data of the area to be predicted, and generating a mineralization probability target area map based on the geological data, the fault inference map, the regional magnetic anomaly plane map, the three-dimensional probability model of magnetic bodies, and the hydroxyl anomaly distribution vector map.

[0015] A third aspect of the present invention provides a coverage area rich iron ore information analysis device, the coverage area rich iron ore information analysis device comprising: a memory and at least one processor, the memory storing instructions; at least one processor calling the instructions in the memory to cause the coverage area rich iron ore information analysis device to perform the various steps of the coverage area rich iron ore information analysis method described in any of the preceding claims.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of the method for analyzing rich iron ore information in the covered area as described above.

[0017] The technical solution of this invention integrates multi-dimensional information such as gravity data, magnetic aerial ΔT data, remote sensing images, and geological data of the area to be predicted, constructing a feature system that comprehensively reflects the mineralization conditions. This breaks through the limitations of traditional single-data source analysis, providing a rich and accurate data foundation for the intelligent delineation of mineralization target areas, thereby significantly improving the accuracy of mineralization prediction. Furthermore, the method employs a collaborative analysis of fracture inference maps, regional magnetic anomaly plane maps, three-dimensional probability models of magnetic bodies, and hydroxyl anomaly distribution vector maps. This not only provides a rich and accurate data foundation for the intelligent delineation of mineralization target areas, further improving the accuracy of mineralization prediction, but also significantly enhances the systematic nature of concealed ore body identification. Compared with traditional methods relying on human experience, this method effectively improves the objectivity of mineralization prediction. Attached Figure Description

[0018] Figure 1 A logical flowchart of the method for analyzing information on rich iron ore deposits in a covered area provided in an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the structure of the coverage area rich iron ore information analysis device provided in an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of the information analysis device for rich iron ore in the coverage area provided in an embodiment of the present invention. Detailed Implementation

[0021] This invention provides a method, apparatus, device, and storage medium for analyzing information on rich iron ore deposits in a covered area. In this invention, the terms "first," "second," "third," "fourth," etc. (if applicable) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0022] This application discloses a method for analyzing information on rich iron ore deposits in a covered area. For ease of understanding, the specific process of the embodiments of this invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the method for analyzing information on rich iron ore in the covered area according to the present invention includes:

[0023] 101. Obtain and process the gravity data of the area to be predicted to obtain information on high gravity value areas, and generate a fracture prediction map based on the obtained high gravity value area information.

[0024] In this embodiment, the underground density difference in the area to be predicted is analyzed by gravity data. Gravity data is the basic data for identifying geological bodies such as concealed rock masses and fault zones.

[0025] 102. Obtain and process the magnetic aerial ΔT data of the area to be predicted to generate a regional magnetic anomaly planar map;

[0026] In this embodiment, magnetic aeronautical data is used to reflect the distribution of underground magnetic bodies in the area to be predicted.

[0027] 103. Based on the fracture inference map and the regional magnetic anomaly plan map, the mineralization potential area is identified, the magnetic profile data of the mineralization potential area is obtained and processed to obtain a three-dimensional probability model of the magnetic body.

[0028] In this embodiment, the superimposed fracture inference map and the regional magnetic anomaly plan map are used to select the superimposed tectonic-magnetic anomaly area as the mineralization potential area. Based on the magnetic profile data of the mineralization potential area, a three-dimensional probability distribution is output to realize the quantitative prediction of the spatial location of the ore body.

[0029] 104. Acquire and process remote sensing images of the area to be predicted to generate a vector map of hydroxyl anomaly distribution;

[0030] In this embodiment, the remote sensing image contains visible light to shortwave infrared bands and is sensitive to the spectral characteristics of altered minerals; the generated hydroxyl anomaly distribution vector map reflects the correlation between surface alteration and mineralized hydrothermal activity.

[0031] 105. Obtain geological data of the area to be predicted, and generate a mineralization probability target area map based on the geological data, fault inference map, regional magnetic anomaly plane map, three-dimensional probability model of magnetic body and hydroxyl anomaly distribution vector map.

[0032] This application discloses a method for analyzing information on rich iron ore deposits in a covered area. It integrates multi-dimensional information such as gravity data, magnetic aerial ΔT data, remote sensing images, and geological data of the area to be predicted, constructing a feature system that comprehensively reflects the mineralization conditions. This method overcomes the limitations of traditional single-data source analysis, providing a rich and accurate data foundation for the intelligent delineation of mineralization target areas, thereby significantly improving the accuracy of mineralization prediction. Furthermore, the method employs a collaborative analysis of fracture inference maps, regional magnetic anomaly plane maps, three-dimensional probability models of magnetic bodies, and hydroxyl anomaly distribution vector maps. This not only provides a rich and accurate data foundation for the intelligent delineation of mineralization target areas, further improving the accuracy of mineralization prediction, but also significantly enhances the systematic nature of concealed ore body identification. Compared with traditional methods relying on human experience, this method effectively improves the objectivity of mineralization prediction.

[0033] Furthermore, in this embodiment of the invention, the step of acquiring and processing gravity data of the region to be predicted to obtain high gravity value region information, and generating a fracture prediction map based on the acquired high gravity value region information, includes:

[0034] 201. Obtain 1:50,000 gravity data of the area to be predicted after terrain interference processing;

[0035] In this embodiment, 1:50,000 gravity data of the area to be predicted is obtained after only processing for terrain interference. Terrain undulations, such as mountains and depressions, can interfere with gravity measurement results, such as lower gravity values ​​at higher elevations and higher gravity values ​​at lower elevations. The Bouguer correction method is used to perform terrain correction processing on the gravity data. The influence of terrain undulations on gravity values ​​is calculated by formula and eliminated to ensure that the data only reflects the density differences of underground materials, such as the difference between high-density rock masses and low-density surrounding rocks.

[0036] 202. The gravity data was decomposed into three layers using the db5 wavelet to separate the regional field with wavelength > 10 km and the local field with wavelength in the range of 2-5 km.

[0037] In this embodiment, the db5 wavelet is used to decompose the gravity data into three layers: the first layer decomposition extracts the regional field with wavelengths greater than 10km, revealing the undulation characteristics of the deep crustal basement; the second and third layers decomposition extract the local field with wavelengths between 2-5km, reflecting the density anomalies of shallow rock masses and ore bodies; the wavelet decomposition, through multi-scale analysis, enables the layered identification of geological bodies at different depths, effectively solving the problem of separating deep and shallow information in traditional methods.

[0038] 203. Obtain regional geological maps, and verify the separated local fields based on the regional geological maps to obtain information on high gravity value areas;

[0039] In this embodiment, a regional geological map containing information on known rock outcrops and stratigraphic distribution is used to verify the local field. If the high-value area of ​​the local field coincides spatially with a known diorite outcrop or is located in a tectonic intersection zone, it is determined to be a high-gravity area (potential concealed rock mass). This provides density constraints for subsequent screening of mineralized areas and improves the accuracy of identifying high-gravity areas.

[0040] 204. Calculate the total horizontal gradient of the local field, and based on the calculated total horizontal gradient, use the Canny algorithm to extract the gradient abrupt change band of the local field;

[0041] In this embodiment, the total horizontal gradient of the local field is calculated using derivatives, which accurately reflects the rate of change of gravity values ​​in space. Then, the Canny algorithm is used to effectively extract gradient abrupt change zones by means of double threshold detection and edge connection. These gradient abrupt change zones correspond to fracture boundaries with significant density differences. Finally, a fracture inference map is generated, which details the fracture direction and length, providing valuable quantitative evidence for mineralized tectonic analysis.

[0042] 205. Generate a fracture prediction map based on the extracted gradient abrupt change bands.

[0043] Furthermore, in this embodiment of the invention, the step of acquiring and processing the magnetic aerial ΔT data of the region to be predicted to generate a regional magnetic anomaly planar map includes:

[0044] 301. Obtain 1:50,000 scale magneto-aerial ΔT data for the region to be predicted, where ΔT represents the total magnetic field anomaly.

[0045] In this embodiment, ΔT represents the total magnetic field strength anomaly, which is defined as the difference between the measured total magnetic field strength and the theoretical normal magnetic field, and the unit is nanotesla (nT). The magnetic aeronautical ΔT data obtained by the airborne magnetic survey has the characteristics of wide coverage and can reflect the distribution characteristics of underground magnetic bodies, such as magnetite and magnetic rock masses. The data scale is 1:50,000, which reflects the matching relationship between the data spatial resolution and coverage.

[0046] 302. The magnetic aeronautical ΔT data were subjected to polarization processing and 5km upward extension processing to obtain the processed magnetic anomaly data.

[0047] In this embodiment, the magnetic anomaly is transformed to a magnetic pole coordinate system through coordinate transformation, thereby eliminating the magnetic anomaly offset caused by geomagnetic tilt. For example, in the Northern Hemisphere, magnetic anomalies usually shift northward. After pole-shifting, the peak value of the anomaly can be aligned with the planar position of the magnetic body. Furthermore, Fourier transform is used to extend the magnetic anomaly upward by 5 km to suppress shallow magnetic interference. Shallow magnetic factors, such as ferromagnetic minerals in the soil, can interfere with the magnetic anomaly. The upward extension process can effectively suppress their influence, thereby highlighting the overall anomaly characteristics of the magnetic body in the deep region, such as the anomaly characteristics of intrusive rock masses. By combining pole-shifting and upward extension processes, the interpretability of the magnetic anomaly is significantly improved.

[0048] 303. Calculate the total horizontal gradient of the processed magnetic anomaly data, and extract gradient abrupt change zones based on the calculated total horizontal gradient using the Canny algorithm;

[0049] In this embodiment, the total horizontal gradient of the processed magnetic anomaly data is calculated, and the gradient abrupt change zone is extracted using the Canny algorithm. This gradient abrupt change zone is the boundary feature of the magnetic body. Subsequently, this boundary feature is superimposed on the regional geological map to generate a regional magnetic anomaly planar map. In the regional magnetic anomaly planar map, the intersection of the high-value area and the abrupt change zone is the distribution area of ​​potential magnetic ore bodies. By generating the regional magnetic anomaly planar map, key magnetic constraints are provided for the preliminary delineation of the mineralization potential area.

[0050] 304. Generate a regional magnetic anomaly planar map based on the extracted gradient abrupt change bands.

[0051] Furthermore, in this embodiment of the invention, the step of confirming the mineralization potential area based on the fracture inference map and the regional magnetic anomaly planar map, obtaining the magnetic profile data of the mineralization potential area and processing it to obtain a three-dimensional probabilistic model of the magnetic body includes:

[0052] 401. Overlay the fault inference map and the regional anomaly plan map to confirm the mineralization potential area;

[0053] In this embodiment, the fracture inference map and the regional magnetic anomaly plan map are overlaid on the ArcGIS platform (with the unified coordinate system set to CGCS2000). The overlapping areas of the dense fracture zone and the high magnetic anomaly zone are selected and identified as mineralization potential areas. The mineralization potential areas have both tectonic channels (fractures) and magnetic materials (ore bodies / rock bodies), and the mineralization conditions are relatively favorable.

[0054] 402. Within the confirmed mineralization potential area, obtain 1:10,000 magnetic profile data;

[0055] In this embodiment, within the mineralization potential area, survey lines are laid out along the direction perpendicular to the fracture strike. Magnetic profile data with a scale of 1:10,000 is obtained using ground-based magnetic surveying instruments, with a measurement point spacing of 50 meters, to ensure a precise depiction of local anomalies. The obtained magnetic profile data is used for a detailed inversion of the three-dimensional spatial distribution of magnetic bodies (ore bodies / rock bodies).

[0056] 403. The magnetic profile data is decomposed into two levels using the sym8 wavelet, and effective magnetic anomaly data of 50-500 nT is retained by threshold noise reduction.

[0057] In this embodiment, the data is decomposed into two layers using the sym8 wavelet, and threshold noise reduction is used to retain anomalies in the range of 50-500 nT, while removing instrument noise and surface interference, thereby obtaining effective magnetic anomaly data.

[0058] 404. Input the effective magnetic anomaly data and gravity high value area information into the pre-trained UNet++ model to obtain regional probability information;

[0059] 405. Generating a three-dimensional probabilistic model of a magnetic body based on regional probability information;

[0060] In this embodiment, the UNet++ model selects 100 sets of magnetic anomaly profile data of known ore bodies as input, and uses the ore body distribution verified by boreholes as output to form training samples. Iterative training is carried out using the Adam optimizer until the model error is reduced to below 5%, completing the pre-training of the UNet++ model. Then, effective magnetic anomaly data and gravity high-value area information (as prior constraints) are input into the trained UNet++ model, and the model outputs the probability of the existence of a magnetic body at each spatial point, with the probability value between 0 and 1. Next, a three-dimensional probability model of the magnetic body is constructed using an interpolation algorithm, with an X / Y / Z resolution of 100m×100m×50m. By combining high-resolution magnetic profile data with a deep learning model, a three-dimensional quantitative prediction of the spatial distribution of magnetic bodies is achieved, effectively solving the problem that traditional two-dimensional inversion cannot reflect the vertical changes of ore bodies, and providing accurate spatial coordinate references for subsequent drilling design.

[0061] Furthermore, in this embodiment of the invention, the step of acquiring and processing the remote sensing image of the area to be predicted to generate a hydroxyl anomaly distribution vector map includes:

[0062] 501. Acquire remote sensing images of the area to be predicted, wherein the remote sensing images are Landsat 9 OLI images;

[0063] In this embodiment, Landsat 9 OLI imagery is selected. Landsat 9 is an Earth observation satellite, and its onboard Land Imager (OLI) can acquire remote sensing images in the visible to shortwave infrared bands, which cover eight multispectral bands and one panchromatic band. Landsat 9 OLI imagery has high sensitivity to the absorption characteristics of hydroxyl minerals (such as kaolinite and montmorillonite), making it suitable for the identification of alteration zones.

[0064] 502. Perform radiometric calibration, atmospheric correction and geometric correction on the remote sensing images to obtain preprocessed remote sensing images;

[0065] In this embodiment, radiometric calibration converts the digital quantization (DN) values ​​of the image into surface reflectance or radiance values, eliminating the influence of sensor response differences and giving the data physical meaning. Atmospheric correction uses the FLAASH model to eliminate interference from atmospheric scattering and aerosol absorption on electromagnetic wave transmission, restoring the true surface reflectance characteristics, such as the spectral characteristics of altered minerals. Geometric correction uses the CGCS2000 coordinate system (38° zone) as a reference and performs geometric fine correction on the image through ground control points to ensure that the spatial registration error of different bands is <0.5 pixels, thus ensuring the accuracy of subsequent multi-band data fusion.

[0066] 503. Calculate the spectral indices of the preprocessed remote sensing images. The calculated spectral indices include the hydroxyl index, iron staining index, and normalized vegetation index.

[0067] In this embodiment, the hydroxyl index (NDSI) is used to identify hydroxyl alteration. Specifically, NDSI = (Green band - SWIR1 band) / (Green + SWIR1), with a threshold > 0.2; the iron staining index (Fe) is used to identify iron oxides. Specifically, Fe = (Red band - Blue band) / (Red + Blue), with a threshold > 0.1; and the normalized vegetation index (NDVI) is used to distinguish vegetation cover disturbance. Specifically, NDVI = (NIR - Red) / (NIR + Red).

[0068] 504. Overlay the original RGB bands of the preprocessed remote sensing image with the calculated spectral indices to construct a 7-band dataset;

[0069] In this embodiment, the original RGB bands (Bands2, Bands3, Bands4) are superimposed with three indices to construct a 7-band dataset, which contains spectral and alteration information.

[0070] 505. Input the constructed 7-band dataset into the pre-trained U-Net classification model to obtain the hydroxyl anomaly distribution vector map;

[0071] In this embodiment, remote sensing image slices of known alteration zones are used as training samples to pre-train the U-Net classification model. The trained U-Net classification model is then used to classify the 7-band dataset. Based on the input 7-band dataset, the U-Net classification model outputs a vector map of hydroxyl anomaly distribution, where regions with a probability > 0.5 are identified as alteration anomaly zones. Through multi-band fusion technology and deep learning classification methods, automated identification of hydroxyl alteration zones is achieved. Compared with traditional visual interpretation methods, this not only significantly improves identification efficiency but also has the ability to capture weak alteration signals, providing a reliable and effective basis for accurately delineating mineralized hydrothermal activity zones.

[0072] Furthermore, in this embodiment of the invention, the step of acquiring geological data of the area to be predicted, and generating a mineralization probability target area map based on the geological data, fault inference map, regional magnetic anomaly planar map, three-dimensional probability model of magnetic bodies, and hydroxyl anomaly distribution vector map, includes:

[0073] 601. Obtain geological data of the area to be predicted, wherein the geological data is a depth model of the top surface of Ordovician limestone;

[0074] In this embodiment, a depth model of the top surface of the Ordovician limestone in the area to be predicted is collected. The depth model of the top surface of the Ordovician limestone is generated by interpolation of borehole data and can reflect the spatial distribution of the ore-bearing surrounding rocks. The depth model of the top surface of the Ordovician limestone provides geological constraints for the ore-bearing strata, because most iron ore-rich deposits are associated with the limestone contact zone.

[0075] 602. In ArcGIS Pro's unified coordinate system, convert geological data fault inference maps, regional magnetic anomaly plane maps, three-dimensional probability models of magnetic bodies, and hydroxyl anomaly distribution vector maps into raster data;

[0076] In this embodiment, in ArcGIS Pro, geological data, fracture inference maps, regional magnetic anomaly plane maps, three-dimensional probability models of magnetic bodies, and hydroxyl anomaly distribution vector maps are uniformly converted into raster data (resolution of 50m, coordinate system CGCS2000 38° zoning) to ensure spatial matching of data.

[0077] 603. Extract 12 indicator features reflecting mineralization conditions from raster data to construct a multi-source feature dataset;

[0078] In this embodiment, 12 index features reflecting mineralization conditions are extracted from raster data, including: structural density (fracture length / unit area), magnetic probability value, gravity gradient value, hydroxyl anomaly probability, distance from the fault, resistivity value, iron staining index, rock mass burial depth, magnetic anomaly intensity, fault strike consistency, ring structure density, and Ordovician limestone top surface depth. These index features cover multi-dimensional information from structural, geophysical, remote sensing, and geological perspectives.

[0079] 604. Input the multi-source feature dataset into the pre-trained XGBoost classifier to obtain the mineralization probability;

[0080] In this embodiment, the XGBoost classifier is used to predict mineralization. First, known ore bodies are used as positive samples and non-ore bodies are used as negative samples. The n_estimators parameter is set to 800 and the max_depth parameter is set to 5. The model parameters are optimized by 5-fold cross-validation, and then the model training is completed.

[0081] In the pre-trained XGBoost classifier, each feature has a different weight, reflecting their importance in mineralization prediction. For example, the magnetic probability value has a weight of 0.35, which directly reflects the magnetic anomalies of the ore body. Since the magnetic characteristics of the ore body often lead to anomalies in magnetic measurements, the magnetic probability value plays a crucial role in determining the existence of an ore body. The gravity gradient value has a weight of 0.25, indicating the location of the contact zone between rock masses. Contact zones are often favorable locations for mineralization because material exchange and chemical reactions between different rock masses can promote ore formation. Hydroxyl... The weight of the hydroxyl anomaly probability is 0.2, reflecting the correlation between surface alteration and deep mineralization. Surface alteration is the manifestation of deep mineralization on the surface. By analyzing the hydroxyl anomaly probability, it is possible to infer whether there is deep mineralization. The weight of the distance from the fault is 0.15. Fault structures provide favorable tectonic space for mineralization. Ore-forming fluids may migrate and precipitate along the fault zone, so the distance from the fault has a certain influence on mineralization. The weight of the resistivity value is 0.05. Low resistivity areas often indicate fluid migration channels. The flow of ore-forming fluids will change the resistivity of rocks. Therefore, the resistivity value can be used as an indicator to judge the fluid migration situation.

[0082] The multi-source feature dataset is input into a pre-trained XGBoost classifier, which outputs the mineralization probability, a value between 0 and 1. Based on this probability, the region to be predicted is divided into target areas, generating a mineralization probability target area map. The specific division criteria are as follows:

[0083] Grade A target areas: mineralization probability greater than 0.8, magnetic probability greater than 0.7, and hydroxyl probability greater than 0.6; these target areas have a high mineralization potential and should be prioritized for drilling to verify the existence of ore bodies.

[0084] Grade B target areas: mineralization probability is between 0.6 and 0.8. For these target areas, it is necessary to conduct additional work such as soil magnetics or induced polarization sounding to verify and further determine their mineralization potential.

[0085] 605. Construct a mineralization probability target area map based on the aforementioned mineralization probability;

[0086] In this embodiment, the application of multi-source feature fusion technology effectively overcomes the significant limitations of using single data for prediction. In traditional prediction scenarios, relying solely on single data for analysis often leads to significant deviations and a lack of comprehensiveness in the prediction results due to factors such as missing data dimensions and incomplete information. Multi-source feature fusion, on the other hand, integrates data from different channels and types, fully exploring the potential correlations and complementary information between various data sources, thereby constructing a richer and more accurate dataset, providing a solid foundation for subsequent analysis and prediction.

[0087] As an advanced machine learning algorithm, the XGBoost model can perform in-depth analysis of data after the fusion of multiple features by automatically learning feature weights. During the learning process, the XGBoost model dynamically assigns corresponding weights according to the degree of influence of each feature on the target variable (i.e., the probability of mineralization). This automatic learning mechanism enables the model to accurately capture key information related to mineralization in the data, thereby achieving accurate quantitative calculation of the probability of mineralization.

[0088] Compared with traditional target area delineation methods, target area delineation using multi-source feature fusion and quantitative calculation results from the XGBoost model can identify potential mineralized areas more scientifically and accurately, greatly improving the accuracy of target area delineation.

[0089] Furthermore, in this embodiment of the invention, the step of constructing a mineralization probability target area map based on the mineralization probability further includes:

[0090] 701. Obtain drilling verification results, which include well logging data at the borehole location and surface geophysical data around the borehole location;

[0091] In this embodiment, well logging data at the borehole location is collected, such as magnetic logging curves to identify the depth of magnetic ore bodies, gamma logging to distinguish alteration types, and ground geophysical data, namely gravity and magnetic re-measurement data within 500m around the borehole, to form a joint well and ground verification dataset, namely the drilling verification results.

[0092] 702. Based on the drilling verification results, borehole constraints are constructed, and based on the constructed borehole constraints, the feature weights of the XGBoost classifier are adjusted using the least squares inversion method.

[0093] In this embodiment, constraints are constructed based on drilling results to provide hard constraints for model optimization. For example, the constraints include: the top depth of the magnetic body is set to ±100m of the top depth of the ore body as interpreted by well logging, and the resistivity constraint adopts the apparent resistivity value of the formation revealed by the borehole.

[0094] The least squares inversion method is used to adjust the feature weights of the XGBoost classifier using the drilling verification results as the true values. For example, if the gravity value is high in a certain area but there is no mineral deposit in the actual drilling, the gravity feature weight is reduced by 5%-10%, that is, the weight of the gravity gradient value is adjusted to 0.15-0.2, so that the prediction results of the XGBoost classifier are more consistent with the actual drilling situation.

[0095] By using actual drilling data as feedback to optimize the XGBoost classifier, a closed loop of prediction, verification, and iteration is formed, which effectively solves the problem of possible bias in the initial training data of the model, and enables the subsequent target area prediction accuracy to be continuously improved, providing technical support with dynamic optimization capabilities for mineral exploration.

[0096] The above describes the method for analyzing rich iron ore information in covered areas according to embodiments of the present invention. The following describes the apparatus for analyzing rich iron ore information in covered areas according to embodiments of the present invention. Please refer to [link / reference]. Figure 2 One embodiment of the iron ore rich ore information analysis device for the covered area in this invention includes:

[0097] The first generation module 801 is used to acquire and process gravity data of the region to be predicted in order to obtain information on high gravity value areas and generate a fracture prediction map based on the acquired high gravity value area information.

[0098] The second generation module 802 is used to acquire and process the magnetic aerial ΔT data of the area to be predicted in order to generate a regional magnetic anomaly plan map.

[0099] The first processing module 803 is used to obtain magnetic profile data of the mineralization potential area based on the fracture inference map and the regional magnetic anomaly plane map, and to process the magnetic profile data of the mineralization potential area to obtain a three-dimensional probability model of the magnetic body.

[0100] The second processing module 804 is used to acquire and process remote sensing images of the area to be predicted in order to generate a vector map of hydroxyl anomaly distribution.

[0101] The third generation module 805 is used to acquire geological data of the area to be predicted, and generate a mineralization probability target area map based on the geological data, fault inference map, regional magnetic anomaly plane map, three-dimensional probability model of magnetic body and hydroxyl anomaly distribution vector map.

[0102] Based on the same ideas as the methods in the above embodiments, the apparatus provided in this application can implement the methods in the above embodiments.

[0103] above Figure 2 The coverage area rich iron ore information analysis device in the embodiments of the present invention will be described in detail from the perspective of modular functional entities. The coverage area rich iron ore information analysis device in the embodiments of the present invention will be described in detail from the perspective of hardware processing.

[0104] Figure 3 This is a schematic diagram of the structure of a coverage area rich iron ore information analysis device 900 provided in an embodiment of the present invention. The coverage area rich iron ore information analysis device 900 can vary considerably due to different configurations or performance. It may include one or more central processing units (CPUs) 910 and memory 920, and one or more storage media 930 (e.g., one or more mass storage devices) for storing application programs 933 or data 932. The memory 920 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the coverage area rich iron ore information analysis device 900. Furthermore, the processor 910 may be configured to communicate with the storage media 930 and execute a series of instruction operations in the storage media 930 on the coverage area rich iron ore information analysis device 900 to implement the steps of the coverage area rich iron ore information analysis method provided in the above-described method embodiments.

[0105] The information analysis equipment 900 for rich iron ore in the coverage area may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 3 The structure of the iron ore information analysis equipment shown does not constitute a limitation on the iron ore information analysis equipment for the covered area. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0106] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the method for analyzing information on rich iron ore in a covered area.

[0107] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0108] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing information on rich iron ore deposits in a covered area, characterized in that, include: Gravity data of the region to be predicted is acquired and processed to obtain information on high gravity value areas. Based on the acquired information on high gravity value areas, a fracture prediction map is generated. The magnetic aerobatic ΔT data of the region to be predicted is acquired and processed to generate a regional magnetic anomaly planar map; Based on the fracture inference map and the regional magnetic anomaly plan map, the mineralization potential area was identified. The magnetic profile data of the mineralization potential area was obtained and processed to obtain a three-dimensional probability model of the magnetic body. Remote sensing images of the area to be predicted are acquired and processed to generate a vector map of hydroxyl anomaly distribution; Geological data of the area to be predicted is acquired. Based on the geological data, fault inference map, regional magnetic anomaly planar map, three-dimensional probability model of magnetic bodies, and hydroxyl anomaly distribution vector map, a mineralization probability target area map is generated. Specifically: Geological data of the area to be predicted is acquired, wherein the geological data is a depth model of the top surface of Ordovician limestone; in the unified coordinate system of ArcGIS Pro, the geological data, fault inference map, regional magnetic anomaly planar map, three-dimensional probability model of magnetic bodies, and hydroxyl anomaly distribution vector map are converted into raster data; 12 index features reflecting mineralization conditions are extracted from the raster data to construct a multi-source feature dataset; the multi-source feature dataset is input into a pre-trained XGBoost classifier to obtain the mineralization probability; and a mineralization probability target area map is constructed based on the mineralization probability.

2. The method for analyzing information on rich iron ore deposits in a covered area according to claim 1, characterized in that, The process of acquiring and processing gravity data of the region to be predicted to obtain information on high gravity value areas, and generating a fracture prediction map based on the acquired high gravity value area information, includes: Obtain 1:50,000 gravity data of the area to be predicted after terrain interference processing; The gravity data was decomposed into three layers using the db5 wavelet to separate the regional field with wavelength >10km and the local field with wavelength in the range of 2-5km. Obtain regional geological maps, and verify the separated local fields based on the regional geological maps to obtain information on high gravity value areas; The total horizontal gradient of the local field is calculated, and the gradient abrupt change band of the local field is extracted based on the calculated total horizontal gradient. A fracture prediction map is generated based on the extracted gradient abrupt change bands.

3. The method for analyzing information on rich iron ore deposits in a covered area according to claim 1, characterized in that, The process of acquiring and processing the magnetic aerial ΔT data of the region to be predicted to generate a regional magnetic anomaly planar map includes: Obtain 1:50,000 magneto-aerial ΔT data for the region to be predicted, where ΔT represents the total magnetic field strength anomaly. The magnetic aeronautical ΔT data were subjected to polarization processing and 5km upward extension processing to obtain processed magnetic anomaly data. The total horizontal gradient is calculated for the processed magnetic anomaly data. Based on the calculated total horizontal gradient, the Canny algorithm is used to extract gradient abrupt change bands. A regional magnetic anomaly planar map is generated based on the extracted gradient abrupt change bands.

4. The method for analyzing information on rich iron ore deposits in a covered area according to claim 1, characterized in that, The process involves identifying mineralization potential areas based on fracture inference maps and regional magnetic anomaly plane maps, acquiring and processing magnetic profile data of these potential areas to obtain a three-dimensional probabilistic model of the magnetic body, including: The fault inference map and the regional anomaly plan map are overlaid to confirm the mineralization potential area; Within the identified mineralization potential area, obtain 1:10,000 magnetic profile data; The magnetic profile data were decomposed into two levels using the sym8 wavelet, and effective magnetic anomaly data of 50-500 nT were retained by threshold noise reduction. The effective magnetic anomaly data and gravity high value area information are input into the pre-trained UNet++ model to obtain regional probability information; A three-dimensional probability model of a magnetic object is generated based on regional probability information.

5. The method for analyzing information on rich iron ore deposits in a covered area according to claim 1, characterized in that, The process of acquiring and processing remote sensing images of the region to be predicted to generate a vector map of hydroxyl anomaly distribution includes: Acquire remote sensing images of the area to be predicted, wherein the remote sensing images are Landsat 9 OLI images; The remote sensing images were subjected to radiometric calibration, atmospheric correction and geometric correction to obtain preprocessed remote sensing images. Calculate the spectral indices of the preprocessed remote sensing images. The calculated spectral indices include the hydroxyl index, iron staining index, and normalized vegetation index. The original RGB bands of the preprocessed remote sensing image are superimposed with the calculated spectral index to construct a 7-band dataset. The constructed 7-band dataset was input into the pre-trained U-Net classification model to obtain a vector map of hydroxyl anomaly distribution.

6. The method for analyzing information on rich iron ore deposits in a covered area according to claim 1, characterized in that, The process of constructing a mineralization probability target area map based on the mineralization probability further includes: Obtain drilling verification results, which include well logging data at the borehole location and surface geophysical data around the borehole location; Based on the drilling verification results, borehole constraints are constructed, and based on the constructed borehole constraints, the feature weights of the XGBoost classifier are adjusted using the least squares inversion method.

7. A device for analyzing information on rich iron ore deposits in a covered area, characterized in that, include: The first generation module is used to acquire and process gravity data of the region to be predicted in order to obtain information on high gravity value areas, and generate a fracture prediction map based on the acquired high gravity value area information. The second generation module is used to acquire and process the magnetic aerial ΔT data of the area to be predicted in order to generate a regional magnetic anomaly plan map. The first processing module is used to obtain magnetic profile data of the mineralization potential area based on the fracture inference map and the regional magnetic anomaly plan map, and to process the magnetic profile data of the mineralization potential area to obtain a three-dimensional probability model of the magnetic body. The second processing module is used to acquire and process remote sensing images of the area to be predicted in order to generate a vector map of hydroxyl anomaly distribution. The third generation module is used to acquire geological data of the area to be predicted. Based on the geological data, fault inference map, regional magnetic anomaly planar map, three-dimensional probability model of magnetic bodies, and hydroxyl anomaly distribution vector map, a mineralization probability target area map is generated. Specifically: the geological data of the area to be predicted is acquired, which is a depth model of the top surface of Ordovician limestone; in the unified coordinate system of ArcGIS Pro, the geological data, fault inference map, regional magnetic anomaly planar map, three-dimensional probability model of magnetic bodies, and hydroxyl anomaly distribution vector map are converted into raster data; 12 indicator features reflecting mineralization conditions are extracted from the raster data to construct a multi-source feature dataset; the multi-source feature dataset is input into a pre-trained XGBoost classifier to obtain the mineralization probability; and a mineralization probability target area map is constructed based on the mineralization probability.

8. A device for analyzing information on rich iron ore deposits in a covered area, characterized in that, The information analysis device for rich iron ore in the coverage area includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the covered area rich iron ore information analysis device to perform the various steps of the covered area rich iron ore information analysis method as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the method for analyzing rich iron ore information in the covered area as described in any one of claims 1-6.

Images