Intelligent delineation method and system for mineral target area based on multi-source heterogeneous geoscience data

Abstract

The embodiment of the application provides a kind of mineral target area intelligent delineation method and system based on multi-source heterogeneous geosciences data, it is related to mineral resources exploration technical field, first, the multi-source heterogeneous geosciences data set containing geological structure, geochemistry, geophysics and remote sensing image data is divided into multiple data modules according to the influence range of geological action, each data module records spatial distribution and attribute information, then the dynamic mapping relationship of data module and mineralization mechanism is constructed, the mineralization association chain between data modules is generated based on the dynamic mapping relationship, the cooperative change law of node and connection path is clarified, then the target area feature set meeting the mineralization association chain is screened, finally, the coincidence degree of target area feature set spatial unit and mineralization condition is judged according to the cooperative change law, the spatial boundary range is dynamically adjusted, and the mineral target area delineation result is generated, so as to comprehensively utilize multi-source data, deeply mine the relationship with mineralization mechanism, and improve the accuracy and reliability of mineral target area delineation.

Description

Technical Field

[0001] This application relates to the field of mineral resource exploration technology, and more specifically, to a method and system for intelligent delineation of mineral target areas based on multi-source heterogeneous geoscience data. Background Technology

[0002] In the field of mineral resource exploration, accurate delineation of mineral target areas is crucial for improving exploration efficiency, reducing exploration costs, and discovering new mineral resources. Traditional methods for delineating mineral target areas mainly rely on single types of geological data, such as analysis based solely on geological structural data or geochemical data. However, mineral formation is a complex geological process influenced by multiple geological processes, involving factors such as geological structure, geochemistry, geophysics, and surface remote sensing. A single data source often cannot comprehensively and accurately reflect the complete information on mineral formation, easily leading to misjudgment or omission of mineral target areas.

[0003] While existing multi-source data fusion methods integrate different types of data to some extent, most simply overlay the data or perform preliminary correlation analysis, lacking the ability to explore the deep, dynamic relationships between different types of geoscientific data and mineralization mechanisms. The roles of different geoscientific data at different stages of mineralization and their synergistic changes have not been fully understood and utilized. This results in significant limitations in the accuracy and reliability of existing mineral target area delineation methods, making it difficult to meet the demands of modern mineral exploration for efficient and precise target area delineation. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method and system for intelligent delineation of mineral target areas based on multi-source heterogeneous geoscience data.

[0005] According to a first aspect of this application, a method for intelligent delineation of mineral target areas based on multi-source heterogeneous geoscientific data is provided, the method comprising:

[0006] The multi-source heterogeneous geoscientific dataset is divided into multiple data modules according to the scope of geological influence. The multi-source heterogeneous geoscientific dataset includes geological structural data, geochemical data, geophysical data and remote sensing image data. Each data module corresponds to a geoscientific data type, and each data module contains spatial distribution information and attribute information of the geoscientific data type. The spatial distribution information is recorded in the form of geographic coordinate sequence, and the attribute information is recorded in the form of geological feature description entries.

[0007] A dynamic mapping relationship between multiple data modules and mineralization mechanisms is constructed. The dynamic mapping relationship is generated based on the correlation between the attribute information of different data modules and the geological processes in the mineralization process. The mineralization process includes three stages: material accumulation in the early stage of mineralization, energy transformation in the middle stage of mineralization, and ore body stabilization in the later stage of mineralization. The correlation relationship is obtained by analyzing the impact of geological processes in each stage on different geoscientific data types.

[0008] Based on dynamic mapping relationships, a mineralization correlation chain is generated between multiple data modules. The mineralization correlation chain takes data modules as nodes and the interaction relationship between different data modules in each mineralization stage as the connection path. Each connection path contains the coordinated change law of data module attribute information. The coordinated change law reflects the synchronous evolution characteristics of attribute information of different data modules within the same mineralization stage.

[0009] Filter the target area feature set that matches the mineralization association chain. The target area feature set consists of attribute information and spatial distribution information that match the connection path of the mineralization association chain in multiple data modules.

[0010] Based on the synergistic change patterns in the mineralization correlation chain, the spatial unit of the target area feature set is determined to match the mineralization conditions. The spatial boundary range of the target area feature set is adjusted according to the matching degree. The adjustment process is repeated until no new spatial unit that meets the matching degree requirements can be included, thus generating the delineation result of the mineral target area. The matching degree reflects the degree of matching between the attribute information within the spatial unit and the synergistic change patterns in the mineralization correlation chain.

[0011] According to a second aspect of this application, a smart delineation system for mineral target areas based on multi-source heterogeneous geoscientific data is provided. The smart delineation system for mineral target areas based on multi-source heterogeneous geoscientific data includes a processor and a readable storage medium. The readable storage medium stores a program that, when executed by the processor, implements the aforementioned smart delineation method for mineral target areas based on multi-source heterogeneous geoscientific data.

[0012] Based on any of the above aspects, multi-source heterogeneous geoscientific datasets are divided into multiple data modules according to the scope of geological influence. These modules encompass various types of geoscientific data, including geological structures, geochemistry, geophysics, and remote sensing imagery. Each data module contains spatial distribution and attribute information. A dynamic mapping relationship between multiple data modules and mineralization mechanisms is then constructed. The correlation between the attribute information of different data modules and geological processes during mineralization is deeply explored. This allows for precise understanding of the roles of different geoscientific data in various stages of mineralization, including pre-mineralization material accumulation, mid-mineralization energy transformation, and post-mineralization orebody stabilization. Based on this, mineralization correlation chains are generated among multiple data modules, with each data module serving as a reference. Nodes and interactions form the connection paths, and the collaborative change patterns of attribute information within these paths are clearly defined. This fully presents the dynamic correlation of various data modules during the mineralization process. Target feature sets that conform to the mineralization correlation chain are selected to ensure that the selected information is highly correlated with the mineralization process. Finally, based on the collaborative change patterns, the fit between the spatial units of the target feature set and the mineralization conditions is determined, and the spatial boundary range is dynamically adjusted until accurate and reliable mineral target area delineation results are generated. This approach comprehensively considers the complex relationship between multi-source heterogeneous geoscientific data and mineralization mechanisms, effectively improving the accuracy and reliability of mineral target area delineation and significantly enhancing the efficiency and success rate of mineral resource exploration. Attached Figure Description

[0013] Figure 1 The illustration shows a flowchart of the intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscience data provided in this application embodiment. Detailed Implementation

[0014] Figure 1 The flowchart of the intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscience data provided in this application embodiment is shown. The detailed steps are described below.

[0015] Step S110: Divide the multi-source heterogeneous geoscientific data set into multiple data modules according to the scope of influence of geological processes. The multi-source heterogeneous geoscientific data set includes geological structural data, geochemical data, geophysical data and remote sensing image data. Each data module corresponds to a geoscientific data type, and each data module contains the spatial distribution information and attribute information of the geoscientific data type. The spatial distribution information is recorded in the form of geographic coordinate sequence, and the attribute information is recorded in the form of geological feature description entries.

[0016] In this embodiment, a prospective copper-polymetallic volcanic rock deposit can be selected as the study area. This study area features complex geological structures, diverse geochemical anomalies, and significant geophysical field variations. The multi-source heterogeneous geoscientific dataset encompasses geological survey data from recent years for this area, requiring systematic classification of the data. Geological structural data primarily originates from regional geological mapping reports and specialized research literature, recording information such as stratigraphic contact relationships, fault occurrence elements, and fold geometry. The influence of geological processes covers the entire study area. Geochemical data includes rock geochemical profile data and soil geochemical measurement data, reflecting the enrichment characteristics of ore-forming elements in different geological bodies. Its influence is mainly concentrated in the mineralization zone and surrounding alteration areas. Geophysical data includes high-precision gravity measurement data, magnetic exploration data, and controlled-source audio-frequency magnetotelluric sounding data, used to reveal differences in density, magnetism, and conductivity of geological bodies at different depths. The influence range is consistent with the coverage area of ​​the measurement profile or network. The remote sensing imagery data, using Gaofen-7 satellite imagery and aerial remote sensing data, can provide macroscopic information on surface rock outcrops, linear structures, and vegetation development in the study area, with an influence range covering the entire study area.

[0017] For the geological structure data module, spatial distribution information describes the spatial location of each structural element through a sequence of geographic coordinates. For example, the spatial distribution information of a thrust fault consists of thirty-six consecutive geographic coordinate points, arranged sequentially according to the fault strike. Attribute information is recorded in the form of geological feature description entries, including the fault's dip angle, dip angle, fracture zone width, infill composition, fold axis direction, interlimb angle, and hinge undulation. The geochemical data module records the latitude and longitude coordinates of soil sampling points, with each sampling point corresponding to a unique geographic coordinate, forming a regular survey network distribution. Attribute information includes descriptions of copper, lead, and zinc content, and the copper-lead-zinc ratio for each sampling point, while also recording the sampling medium type (e.g., colluvial soil, alluvial soil) and sampling depth. The geophysical data module's spatial distribution information includes the coordinate grid of gravity measurement points, the start and end coordinates of magnetic profiles, and the location coordinates of controlled-source audio-frequency magnetotelluric sounding points. The attribute information includes descriptive entries for physical parameters such as gravity anomalies, total magnetic field strength, and apparent resistivity, along with the measuring instrument model, measurement accuracy, and data correction method. The spatial distribution information of the remote sensing image data module is the four-corner coordinates of the image, using the Gauss-Kruger projection coordinate system. The attribute information includes descriptive entries such as the area percentage of exposed rock, vegetation cover level, and statistical results of the trend rose diagram of linear structures, obtained through professional remote sensing interpretation software.

[0018] Step S120: Construct a dynamic mapping relationship between multiple data modules and mineralization mechanisms. The dynamic mapping relationship is generated based on the correlation between the attribute information of different data modules and the geological processes during mineralization. The mineralization process includes three stages: material accumulation in the early stage of mineralization, energy transformation in the middle stage of mineralization, and ore body stabilization in the later stage of mineralization. The correlation relationship is obtained by analyzing the impact of geological processes at each stage on different geoscientific data types.

[0019] In the aforementioned prospective volcanic copper-polymetallic deposits, the mineralization process underwent three distinct stages. The pre-mineralization stage, characterized by material accumulation, was primarily associated with Yanshanian granodiorite magmatic activity, with the magma intrusion bringing abundant ore-forming materials. The mid-mineralization stage, marked by energy transformation, was characterized by intense tectonic activity, leading to large-scale migration of ore-bearing hydrothermal fluids. The late-mineralization stage, characterized by orebody stabilization, was accompanied by regional uplift and erosion, with the orebody forming secondary enrichment zones under weathering. A systematic analysis is needed to determine how the geological processes of these three stages affect the attribute information of each data module, thereby establishing a dynamic mapping relationship.

[0020] Step S121: Extract the geological response signal types from the attribute information of each data module. The geological response signal types of the geological structure data module include stratigraphic sequence change signals, fault activity signals, and fold morphology signals. The geological response signal types of the geochemical data module include element content change signals, element combination signals, and isotope ratio signals. The geological response signal types of the geophysical data module include gravity anomaly signals, magnetic field change signals, and resistivity change signals. The geological response signal types of the remote sensing image data module include rock exposure signals, vegetation distribution signals, and linear structure signals.

[0021] In this prospective copper-polymetallic deposit formed in volcanic rocks, in-depth analysis of the attribute information of each data module was conducted to extract the types of geological response signals. The attribute information for the geological structure data module was derived from a 1:50,000 regional geological survey report, which details the contact relationships and tectonic deformation characteristics of strata at different geological periods. The attribute information for the geochemical data module came from laboratory analysis reports, including elemental test results and isotope analysis data for various samples. The attribute information for the geophysical data module was provided by a geophysical data processing report, recording the physical field parameters obtained through various geophysical methods. The attribute information for the remote sensing image data module was obtained from remote sensing interpretation reports, including professional interpretation of image features.

[0022] Step S1211: Analyze the attribute information of the geological structure data module. The attribute information is recorded in the form of geological exploration report entries. Extract the entries describing the chronological order of strata formation from the data. Define the signals corresponding to the entries describing the chronological order of strata formation as stratum sequence change signals.

[0023] The attribute information of the geological structure data module is recorded in the form of geological exploration report entries, which are organized according to the categories of geological phenomena. During the analysis process, special attention is paid to entries describing the contact relationships between different stratigraphic units, such as "Upper Jurassic rhyolite unconformably overlying Lower Triassic sandstone." These entries clearly reflect the chronological order of stratigraphic formation. The signals corresponding to these entries are defined as stratigraphic sequence change signals, and the corresponding report chapter number and specific description are recorded for subsequent tracing and verification.

[0024] Step S1212: Extract the entries describing the frequency and range of fault occurrence from the attribute information of the geological structure data module, and define the signals corresponding to the entries describing the frequency and range of fault occurrence as fault activity signals.

[0025] In the attribute information of the geological structure data module, entries describing fault activity characteristics are selected. These entries may involve the activity phases of the faults, the displacement of faults at different times, and the variation in the width of the fault breccia zone. For example, "There are 12 northeast-trending faults in the study area, among which the F1 fault's most recent activity period is the Late Pleistocene, with a horizontal displacement of several hundred meters and a breccia zone width varying between 5 and 20 meters." The signals corresponding to these entries describing the frequency and extent of fault activity are defined as fault activity signals, and the attribute characteristics of each signal are recorded in detail, including fault strike, dip, dip angle, and activity intensity level.

[0026] Step S1213: Extract the entries describing the fold bending morphology and extension direction from the attribute information of the geological structure data module, and define the signals corresponding to the entries describing the fold bending morphology and extension direction as fold morphology signals.

[0027] Descriptive entries related to folds are extracted from the attribute information of the geological structure data module. These entries typically include information such as the axial plane orientation, hinge strike, and dip angle of the limb strata. For example, "A broad and gentle anticline develops in the area, with an axial track trending northeast-east, approximately 8 kilometers long. The dip angle of the strata on the northern limb is between 15 and 25 degrees, and the dip angle of the strata on the southern limb is between 10 and 20 degrees. The hinge exhibits undulating undulations." The signals corresponding to the entries describing the fold bending morphology and extension direction are defined as fold morphology signals. Simultaneously, auxiliary information such as fold type (e.g., anticline, syncline) and scale level (e.g., regional fold, local fold) is recorded.

[0028] Step S1214: Analyze the attribute information of the geochemical data module. The attribute information is recorded in the form of element detection report entries. Extract the entries describing the differences in the content of target mineral-related elements in different regions. Define the signals corresponding to the entries describing the differences in the content of target mineral-related elements in different regions as element content change signals.

[0029] The attribute information of the geochemical data module is recorded in the form of elemental analysis report entries, with each entry corresponding to the analysis result of one sample. During the analysis process, the focus is on the content data of target mineral-related elements (such as copper, lead, and zinc), extracting entries describing the differences in the content of these elements in different sampling areas. For example, "The copper content of soil samples in the mineralized zone is tens of times higher than that in the background area, with the highest value appearing in the altered sericitization zone, gradually decreasing towards both sides." The signals corresponding to these entries are defined as elemental content change signals, and parameters such as the element name, content unit, background value range, and anomaly lower limit are recorded.

[0030] Step S1215: Extract entries from the geochemical data module attribute information that describe the types and proportions of different elements that appear together, and define the signals corresponding to the entries that describe the types and proportions of different elements that appear together as element combination signals.

[0031] Entries describing the characteristics of elemental assemblages are selected from the attribute information of the geochemical data module. These entries are typically based on the results of elemental correlation analysis and cluster analysis. For example, "Copper and molybdenum show a significant positive correlation with a correlation coefficient of 0.85, forming a copper-molybdenum elemental assemblage; lead and zinc are closely associated, constituting a lead-zinc elemental assemblage." The signals corresponding to the entries describing the types and proportions of different elements occurring together are defined as elemental assemblage signals. Information such as the name of the elemental assemblage, the ratio range of each element within the assemblage, and the type of geological body in which the assemblage occurs are also recorded.

[0032] Step S1216: Extract the entries describing the changes in the atomic ratio of the target isotope from the attribute information of the geochemical data module, and define the signals corresponding to the entries describing the changes in the atomic ratio of the target isotope as isotope ratio signals.

[0033] The geochemical data module contains isotope analysis data in its attribute information. Entries describing changes in the atomic ratios of target isotopes are extracted. For example, "The ratios of lead-206 to lead-204, lead-207 to lead-204, and lead-208 to lead-204 in the ore show a regular variation, gradually increasing from the center of the ore body towards the edge." The signals corresponding to these entries are defined as isotope ratio signals, recording the type of isotope, the ratio representation (e.g., lead-206 / lead-204), the range of ratio changes, and the corresponding geological significance.

[0034] Step S1217: Analyze the attribute information of the geophysical data module. The attribute information is recorded in the form of geophysical survey report entries. Extract the entries describing the difference between the gravity value of the study area and the standard gravity field. Define the signal corresponding to the entry describing the difference between the gravity value of the study area and the standard gravity field as a gravity anomaly signal.

[0035] The attribute information of the geophysical data module is recorded in the form of geophysical survey report entries, with a focus on gravity measurement data during the analysis process. Entries describing the differences between gravity values ​​in the study area and the standard gravity field are extracted, such as "A near-circular high gravity anomaly exists in the central part of the study area, with an anomaly amplitude of tens of milligallograms, an anomaly range of approximately 5 kilometers along the long axis and approximately 3 kilometers along the short axis, presumed to be caused by a high-density rock mass." The signals corresponding to these entries are defined as gravity anomaly signals, and the amplitude, range, morphological characteristics of the anomaly, and the inferred type of geological body causing the anomaly are recorded.

[0036] Step S1218: Extract the entries describing the changes in the magnetic induction intensity of the geomagnetic field in the study area from the attribute information of the geophysical data module, and define the signals corresponding to the entries describing the changes in the magnetic induction intensity of the geomagnetic field in the study area as magnetic field change signals.

[0037] Entries related to changes in the geomagnetic field magnetic induction intensity are extracted from the attribute information of the geophysical data module. These entries may involve anomalies in the total magnetic field intensity, vertical component anomalies, and horizontal component anomalies. For example, "A strip-shaped magnetic anomaly develops along the F2 fault zone, with the total magnetic field intensity hundreds of nanotes above the background value. The anomaly strike is consistent with the fault strike, presumably due to the enrichment of magnetic minerals within the fault zone." The signals corresponding to these entries describing changes in the geomagnetic field magnetic induction intensity in the study area are defined as magnetic field change signals, and the intensity, gradient, extent, and corresponding geological interpretation of the anomalies are recorded.

[0038] Step S1219: Extract the entries describing the differences in the ability of materials in the study area to impede current from the attribute information of the geophysical data module, and define the signals corresponding to the entries describing the differences in the ability of materials in the study area to impede current as resistivity change signals.

[0039] In the attribute information of the geophysical data module, entries describing the resistivity characteristics of materials are selected. These entries are usually derived from electrical exploration data, such as "Controlled-source audio-frequency magnetotelluric sounding results show the existence of a low-resistivity body deep underground, with a resistivity value of only a few ohm-meters, a thickness of hundreds of meters, and a lateral extension of several kilometers, presumably a mineral-bearing hydrothermal alteration zone." The signals corresponding to the entries describing the differences in the ability of materials in the study area to impede electric current are defined as resistivity change signals, and parameters such as the range of resistivity values, the morphological characteristics of low-resistivity or high-resistivity bodies, and burial depth are recorded.

[0040] Step S12110: Analyze the attribute information of the remote sensing image data module. The attribute information is recorded in the form of image interpretation report entries. Extract the entries describing the area and location of rock outcrops in the study area. Define the signals corresponding to the entries describing the area and location of rock outcrops in the study area as rock exposure signals.

[0041] The attribute information of the remote sensing image data module is recorded in the form of image interpretation report entries. During analysis, the focus is on the interpretation results of surface rock outcrops. Entries describing the area and location of rock outcrops in the study area are extracted, such as "A large area of ​​granite outcrops has developed in the northwest of the study area, covering an area of ​​approximately tens of square kilometers, distributed in an irregular shape, mainly extending along both sides of the northwest-trending fault zone." The signals corresponding to these entries are defined as rock outcrop signals, and auxiliary information such as the lithological name of the rock, the boundary coordinates of the outcrop area, and vegetation cover are recorded.

[0042] Step S12111: Extract the entries describing the vegetation cover area and growth status of the study area from the attribute information of the remote sensing image data module, and define the signals corresponding to the entries describing the vegetation cover area and growth status of the study area as vegetation distribution signals.

[0043] Descriptive entries related to vegetation are extracted from the attribute information of remote sensing image data modules. These entries may involve vegetation type, coverage, growth status, etc., such as "the vegetation coverage in the mineralization anomaly area is low, only about 20%, mainly sparse shrubs, with poor growth status, which is in stark contrast to the vegetation coverage of more than 60% in the surrounding normal area." The signals corresponding to the entries describing the vegetation coverage area and growth status of the study area are defined as vegetation distribution signals, and parameters such as the variation range of vegetation indices (such as normalized difference vegetation index) and vegetation community type are recorded.

[0044] Step S12112: Extract the entries describing the location and length of linear geological structures from the attribute information of the remote sensing image data module, and define the signals corresponding to the entries describing the location and length of linear geological structures as linear structure signals.

[0045] In the attribute information of the remote sensing image data module, entries describing linear geological structures are selected. These entries, based on image interpretation results, include information such as the direction, length, and number of linear structures. For example, "A total of 68 linear structures were interpreted in the study area, of which 25 are NE-trending linear structures, with lengths mostly ranging from several kilometers to over ten kilometers, mainly surface reflections of fault structures." The signals corresponding to the entries describing the location and length of linear geological structures are defined as linear structure signals, and detailed characteristic parameters such as the endpoint coordinates, strike azimuth, and linearity of each linear structure are recorded.

[0046] Step S12113: Classify and record the extracted geological response signal types according to the data module type, forming a list of geological structural signals, a list of geochemical signals, a list of geophysical signals, and a list of remote sensing image signals. Each list contains the signal type name and the source of the corresponding attribute information entries.

[0047] The extracted geological response signals were categorized and organized according to data module type, forming four independent signal lists. The geological structure signal list includes three types: stratigraphic sequence variation signals, fault activity signals, and fold morphology signals. Each signal type is followed by the corresponding geological survey report entry number and specific page number. The geochemical signal list includes elemental content variation signals, elemental assemblage signals, and isotope ratio signals, recording the corresponding elemental detection report number and analysis batch. The geophysical signal list includes gravity anomaly signals, magnetic field variation signals, and resistivity variation signals, indicating the chapter number of the geophysical survey report and the data processing flow number. The remote sensing image signal list includes rock exposure signals, vegetation distribution signals, and linear structural signals, labeling the map number and interpretation unit number of the image interpretation report. Each list is stored in a structured document format for easy reading and subsequent processing by computer programs.

[0048] Step S122: Analyze the impact of geological processes during the pre-mineralization material accumulation stage on the geological response signals of each data module, determine the stratigraphic sequence variation signal characteristics of the geological structural data module and the element content variation signal characteristics of the geochemical data module corresponding to the material migration of magmatic activity, and determine the fold morphology signal characteristics of the geological structural data module and the element combination signal characteristics of the geochemical data module corresponding to the material accumulation of sedimentary environment.

[0049] In the pre-mineralization material accumulation stage of volcanic-type copper-polymetallic deposit prospective areas, the main geological processes include magmatic material migration and sedimentary material accumulation. Magmatic material migration manifests as the upwelling process of Yanshanian granodiorite magma. During its ascent, the magma underwent intense material exchange with the surrounding rocks, leading to contact metamorphism and assimilation / contamination. Sedimentary material accumulation occurred in the Early Jurassic. The study area, located in a shallow to semi-deep marine environment, received a set of clastic rocks rich in volcanic material.

[0050] Analysis of stratigraphic sequence variation signals from the geological structural data module revealed that magmatic material migration led to a significant intrusive contact relationship between the intrusive intrusive body and the surrounding rocks, resulting in discontinuous stratigraphic sequences. The surrounding rocks exhibited baking rim phenomena near the contact zone, and some strata were inverted. These characteristics constitute the stratigraphic sequence variation signal features corresponding to magmatic material migration, including indicators such as the type of stratigraphic contact relationship (intrusive contact, fault contact), the degree of baking rim development, and the degree of stratigraphic disorder. Elemental content variation signals from the geochemical data module showed a significant increase in the content of ore-forming elements such as copper and molybdenum in the magmatic activity-affected area, forming an elemental anomaly dominated by copper. The anomaly range largely coincided with the distribution range of the intrusive intrusive body. Therefore, the elemental content variation signal features corresponding to magmatic material migration include parameters such as the enrichment coefficient of ore-forming elements, anomaly area, and peak intensity.

[0051] The depositional environment and material accumulation influence the fold morphology signal in the geological structure data module. Due to the stability of the depositional environment and variations in sediment supply rates, the resulting sedimentary strata exhibit distinct bedding structures. Under subsequent tectonic movements, these strata fold and deform, forming broad and gentle synclines and anticlines. Fold morphology signal characteristics include fold symmetry, variations in limb strata thickness, and the preservation integrity of axial strata. The elemental assemblage signal in the geochemical data module shows that strata formed by depositional material accumulation have high contents of rock-forming elements such as aluminum, iron, and magnesium, forming specific elemental combinations that differ significantly from those formed by magmatic activity. The elemental assemblage signal characteristics corresponding to depositional material accumulation include the ratio relationships of elemental combinations, elemental correlation coefficients, and the stratigraphic distribution of assemblage anomalies.

[0052] Step S123: Analyze the impact of geological processes during the mid-stage of mineralization energy transformation on the geological response signals of each data module, determine the fault activity signal characteristics of the geological structure data module and the magnetic field change signal characteristics of the geophysical data module corresponding to the energy release of tectonic stress, and determine the isotope ratio signal characteristics of the geochemical data module and the resistivity change signal characteristics of the geophysical data module corresponding to the energy transfer of hydrothermal activity.

[0053] During the mid-stage of mineralization and energy transformation, the study area experienced intense tectonic movement and hydrothermal activity. The energy release from tectonic stress manifested as multiple phases of activity along two sets of northeast- and northwest-trending faults. The tectonic stress generated by these faults led to rock fracturing and deformation, while simultaneously providing pathways for the migration of ore-forming hydrothermal fluids. The energy transfer effect of hydrothermal activity was characterized by the migration of ore-forming fluids rich in ore-forming elements along fault zones under the drive of tectonic stress, resulting in water-rock reactions with the surrounding rocks. This transferred heat and matter to the surrounding rocks, forming alteration and mineralization zones.

[0054] The release of tectonic stress energy significantly impacts the fault activity signal in the geological structure data module, increasing fault activity frequency and expanding its range. The most recently active fault breccia zones contain abundant tectonic breccia and fault gouge, and the fracture rate of rocks within these zones is significantly increased. These characteristics constitute the fault activity signal features corresponding to the release of tectonic stress energy, including indicators such as the fault activity phase, displacement magnitude, mechanical properties of rocks in the breccia zone, and fracture density. The magnetic field variation signal in the geophysical data module shows that in areas with strong tectonic stress energy release, fault activity causes directional alignment and local enrichment of magnetic minerals, leading to localized anomalous changes in magnetic field strength and forming high magnetic anomaly zones. The magnetic field variation signal features include parameters such as anomalous amplitude, gradient changes, and morphological complexity.

[0055] Hydrothermal activity and energy transfer influence isotope ratio signals in geochemical data modules. The interaction between hydrothermal fluids and the surrounding rocks leads to isotope exchange, causing systematic changes in isotope ratios within the mineralized zone. For example, hydrogen and oxygen isotope ratios shift towards the magmatic water isotope composition, while lead isotope ratios reflect the multi-source nature of ore-forming materials. Characteristics of isotope ratio signals corresponding to hydrothermal energy transfer include the range of isotope ratio variations, their correspondence to mineralization stages, and differences in isotope ratios among different minerals. Resistivity variation signals in geophysical data modules show that altered mineralized zones formed by hydrothermal activity have lower resistivity, creating a significant resistivity difference compared to unaltered surrounding rocks. This difference manifests as low-resistivity anomalies on controlled-source audio-frequency magnetotelluric sounding profiles. Resistivity variation signal characteristics include the depth, thickness, lateral extent of the low-resistivity anomaly, and the relationship between resistivity values ​​and mineralization degree.

[0056] Step S124: Analyze the impact of geological processes during the stable stage of the ore body in the later stage of mineralization on the geological response signals of each data module, determine the resistivity change signal characteristics of the geophysical data module and the rock exposure signal characteristics of the remote sensing image data module corresponding to the wall rock alteration protection effect, and determine the linear structural signal characteristics of the remote sensing image data module and the stratigraphic sequence change signal characteristics of the geological structural data module corresponding to the ore body morphology solidification effect.

[0057] In the later stages of mineralization, during the stabilization phase of the ore body, the main geological processes include the protective effect of wall rock alteration and the solidification of the ore body's morphology. Wall rock alteration refers to the silicification and sericitization that occur in the surrounding rock after the ore body forms, which improves the mechanical strength and weathering resistance of the surrounding rock, thus protecting the ore body from later weathering and erosion. Ore body morphology solidification refers to the fact that after the ore body forms, it is less affected by later tectonic movements, and its morphology and occurrence remain relatively stable. At the same time, the contact relationship between the ore body and the surrounding rock becomes clear, facilitating identification.

[0058] The protective effect of alteration of the surrounding rock affects the resistivity change signal in the geophysical data module. Due to changes in mineral composition (such as increased quartz content), the resistivity of altered surrounding rock is higher than that of unaltered surrounding rock, forming a specific resistivity difference relationship with the ore body. The characteristics of this resistivity change signal include the resistivity range of the alteration zone, its relative position to the ore body, and the correlation between the degree of alteration and the resistivity value. The rock exposure signal in the remote sensing image data module shows that due to the strong weathering resistance of the altered surrounding rock, large areas of exposed rock are formed on the surface. The characteristics of the exposed rock signal include lithological assemblage, color differences, and topographic features, which are significantly different from the vegetation cover characteristics of the unaltered areas.

[0059] The solidification of orebody morphology affects the linear structural signals in remote sensing image data modules. The boundaries of orebodies often coincide with the distribution of linear structures (such as fault zones). Characteristics of linear structural signals include the continuity of linear structures, their strike stability, and the degree of agreement with orebody boundaries. The stratigraphic sequence variation signals in geological structural data modules show that the solidification of orebody morphology makes the stratigraphic sequence relationship between the orebody and the surrounding rock more explicit. Orebodies typically cut through or penetrate the surrounding rock strata, forming unconformities or fault contacts. Characteristics of stratigraphic sequence variation signals include the morphological characteristics of the contact zone, stratigraphic gaps, and the degree of alteration of the strata by the orebody.

[0060] Step S125: Establish an association entry between the geological response signal type of each data module and the geological processes of each mineralization stage. Each association entry includes the data module type, geological response signal type, geological process type, and mineralization stage.

[0061] Based on the above analysis of the influence of geological processes and geological response signals of data modules on each mineralization stage, correlation entries were established. Each correlation entry contains four elements: data module type, geological response signal type, geological process type, and mineralization stage. For example, for the migration of magmatic materials, in the pre-mineralization stage, the correlation entry affecting the stratigraphic sequence variation signal of the geological structure data module is: "Geological structure data module - stratigraphic sequence variation signal - magmatic material migration - pre-mineralization"; the correlation entry affecting the elemental content variation signal of the geochemical data module is: "Geochemical data module - elemental content variation signal - magmatic material migration - pre-mineralization". Similarly, the correlation entries corresponding to the deposition of sedimentary environment materials are: "Geological structure data module - fold morphology signal - deposition of sedimentary environment materials - pre-mineralization" and "Geochemical data module - elemental assemblage signal - deposition of sedimentary environment materials - pre-mineralization".

[0062] The related entries for tectonic stress energy release during the middle stage of mineralization include: "Geological Structure Data Module - Fault Activity Signal - Tectonic Stress Energy Release - Middle Stage of Mineralization" and "Geophysical Data Module - Magnetic Field Change Signal - Tectonic Stress Energy Release - Middle Stage of Mineralization". The related entries for hydrothermal energy transfer are: "Geochemical Data Module - Isotope Ratio Signal - Hydrothermal Energy Transfer - Middle Stage of Mineralization" and "Geophysical Data Module - Resistivity Change Signal - Hydrothermal Energy Transfer - Middle Stage of Mineralization".

[0063] The associated entries for the protective effect of wall rock alteration in the later stages of mineralization are: "Geophysical Data Module - Resistivity Change Signal - Wall Rock Alteration Protection - Late Stage of Mineralization" and "Remote Sensing Image Data Module - Rock Exposure Signal - Wall Rock Alteration Protection - Late Stage of Mineralization". The associated entries for the solidification of orebody morphology include: "Remote Sensing Image Data Module - Linear Tectonic Signal - Orebody Morphology Solidification - Late Stage of Mineralization" and "Geological Tectonic Data Module - Stratigraphic Sequence Change Signal - Orebody Morphology Solidification - Late Stage of Mineralization". All associated entries are recorded in a structured table format to ensure the completeness and accuracy of the information.

[0064] Step S126: Integrate all related entries to form a set of related rules, and construct a stage mapping sub-relationship between data modules and mineralization mechanisms based on the set of related rules. Each stage mapping sub-relationship corresponds to a pre-mineralization, middle-mineralization, and post-mineralization stage. Connect the three stage mapping sub-relationships in sequence according to the mineralization time, supplement the transition characteristics of geological response signals between different stage mapping sub-relationships, and generate a dynamic mapping relationship to reflect the evolution of data module attribute information throughout the mineralization process.

[0065] Step S1261: Collect the relevant entries for the three stages of mineralization: early, middle and late. Each relevant entry includes the data module type, geological response signal type, geological process type, and mineralization stage.

[0066] Step S1262: Group the associated items according to the mineralization stage to form the early mineralization associated group, the middle mineralization associated group, and the late mineralization associated group.

[0067] Based on the mineralization stage information in the associated entries, all associated entries are divided into three groups. The Pre-Mineralization associated group contains all associated entries for the "Pre-Mineralization" stage; the Intermediate Mineralization associated group contains associated entries for the "Intermediate Mineralization" stage; and the Late Mineralization associated group contains associated entries for the "Late Mineralization" stage. Each associated group is stored separately for easy processing later.

[0068] Step S1263: Process the entries of the pre-mineralization associated group, extract the geological response signal type and associated geological process type corresponding to each data module in the pre-mineralization stage, and generate the first correspondence table.

[0069] Each entry in the pre-mineralization associated group was analyzed individually, extracting three elements: data module type, geological response signal type, and geological process type. For example, from the associated entry "Geological structure data module - stratigraphic sequence change signal - magmatic activity material migration - pre-mineralization," the geological structure data module, stratigraphic sequence change signal, and magmatic activity material migration were extracted. The extracted information was organized into a first correspondence table, where rows represent data module types, columns represent geological response signal types, and cells are filled with the corresponding geological process type.

[0070] Step S1264: Based on the first correspondence table, construct a mapping sub-relationship for the pre-mineralization stage. This mapping sub-relationship determines the correspondence between the stratigraphic sequence change signal and fold morphology signal of the geological structure data module and the migration of magmatic activity materials and the accumulation of sedimentary environment materials, respectively. It also determines the correspondence between the element content change signal and element combination signal of the geochemical data module and the migration of magmatic activity materials and the accumulation of sedimentary environment materials, respectively.

[0071] Based on the contents of the first correspondence table, a mapping sub-relationship for the pre-mineralization stage is constructed. It is clarified that stratigraphic sequence variation signals in the geological structure data module correspond to magmatic activity and material migration, while fold morphology signals correspond to sedimentary environment and material accumulation; similarly, elemental content variation signals in the geochemical data module correspond to magmatic activity and material migration, while elemental assemblage signals correspond to sedimentary environment and material accumulation. These correspondences are defined through logical rules, such as, "If a stratigraphic sequence variation signal appears in the geological structure data module, then magmatic activity and material migration are determined to exist."

[0072] Step S1265: Process the entries of the mid-mineralization correlation group, extract the geological response signal type and associated geological process type corresponding to each data module in the mid-mineralization stage, and generate a second correspondence table.

[0073] Using the same processing method as the pre-mineralization correlation group, the entries of the mid-mineralization correlation group were analyzed to extract data module types, geological response signal types, and geological process types, generating a second correspondence table. The structure of the second correspondence table is consistent with the first correspondence table, with rows representing data module types, columns representing geological response signal types, and cells containing the corresponding geological process types.

[0074] Step S1266: Based on the second correspondence table, construct a mapping sub-relationship for the mid-stage of mineralization. This sub-relationship determines the correspondence between the fault activity signal and the tectonic stress energy release effect of the geological structure data module, the correspondence between the isotope ratio signal and the hydrothermal activity energy transfer effect of the geochemical data module, and the correspondence between the magnetic field change signal and the resistivity change signal of the geophysical data module and the tectonic stress energy release effect and the hydrothermal activity energy transfer effect, respectively.

[0075] Based on the second correspondence table, a mapping sub-relationship for the mid-stage of mineralization is constructed. The fault activity signals in the geological structural data module correspond to tectonic stress energy release; the isotope ratio signals in the geochemical data module correspond to hydrothermal activity energy transfer; and the magnetic field variation signals in the geophysical data module correspond to tectonic stress energy release, while the resistivity variation signals correspond to hydrothermal activity energy transfer. These correspondences are also clearly defined in the form of logical rules.

[0076] Step S1267: Process the entries of the late mineralization associated group, extract the geological response signal type and associated geological process type corresponding to each data module in the late mineralization stage, and generate a third correspondence table.

[0077] The entries of the late mineralization associated groups are processed, relevant elements are extracted, and a third correspondence table is generated, with the same structure as the first two correspondence tables.

[0078] Step S1268: Based on the third correspondence table, construct a mapping sub-relationship for the later stages of mineralization. This sub-relationship determines the correspondence between the resistivity change signal of the geophysical data module and the surrounding rock alteration protection effect, determines the correspondence between the rock exposure signal and the linear structure signal of the remote sensing image data module and the surrounding rock alteration protection effect and the ore body morphology solidification effect, respectively, and determines the correspondence between the stratigraphic sequence change signal of the geological structure data module and the ore body morphology solidification effect.

[0079] Based on the third correspondence table, a mapping sub-relationship for the later stages of mineralization is constructed. The resistivity change signal of the geophysical data module corresponds to the alteration and protection of the surrounding rock; the rock exposure signal of the remote sensing image data module corresponds to the alteration and protection of the surrounding rock, and the linear tectonic signal corresponds to the ore body morphology solidification; the stratigraphic sequence change signal of the geological structure data module corresponds to the ore body morphology solidification, and these are defined in the form of logical rules.

[0080] Step S1269: Compare the correspondence between data modules, geological response signals, and geological processes in the mapping sub-relationships of each stage, and adjust them so that the same geological response signal of the same data module corresponds to only one geological process type in the mapping sub-relationships of different stages.

[0081] Because the same geological response signal from the same data module may be influenced by different geological processes at different mineralization stages, comparison and adjustment are necessary. For example, the stratigraphic sequence variation signal from the geological structure data module might correspond to magmatic activity and material migration in the early mineralization stage, and to ore body morphology consolidation in the later mineralization stage. This is reasonable, as it represents different geological processes at different mineralization stages. However, if the same geological response signal within the same mineralization stage corresponds to multiple geological processes, the influence results need to be re-analyzed, and the correlation entries adjusted to ensure that the same geological response signal from the same data module corresponds to only one geological process type in the mapping sub-relationships at different stages, thus avoiding logical conflicts.

[0082] Step S12610: Arrange the sub-relationships of each stage according to the mineralization time to form a sequence of stage sub-relationships, which serves as a component of the dynamic mapping relationship.

[0083] The mapping sub-relationships for the pre-mineralization, middle-mineralization, and post-mineralization stages are arranged chronologically to form a sequence of stage mapping sub-relationships. This sequence constitutes the core of the dynamic mapping relationship, reflecting the dynamic correspondence between data modules and mineralization mechanisms at different mineralization stages. The dynamic mapping relationship also includes transition rules between the mapping sub-relationships of each stage, used to describe the evolution of geological response signals and the transformation mechanism of geological processes from one stage to another.

[0084] Step S130: Generate mineralization association chains among multiple data modules based on dynamic mapping relationships. The mineralization association chains take data modules as nodes and the interaction relationships of different data modules in various mineralization stages as connection paths. Each connection path contains the collaborative change law of data module attribute information. The collaborative change law reflects the synchronous evolution characteristics of attribute information of different data modules within the same mineralization stage.

[0085] In the application of volcanic rock-type copper polymetallic deposit prospective areas, based on the dynamic mapping relationship constructed above, a metallogenic correlation chain is generated between data modules. The metallogenic correlation chain uses four data modules (geological structure data module, geochemical data module, geophysical data module, and remote sensing image data module) as nodes. The connection path between nodes is determined based on the interaction relationship between different data modules at various stages of metallogenesis. Each connection path contains the coordinated change law of the attribute information of the data modules, that is, how the attribute information of different data modules evolves synchronously within the same metallogenic stage.

[0086] Step S131: Extract the correlation patterns of the pre-mineralization stage from the dynamic mapping relationship, determine the first interaction relationship between the stratigraphic sequence change signal of the geological structure data module and the element content change signal of the geochemical data module. The first interaction relationship reflects the driving characteristics of the evolution process of the stratigraphic sequence change signal on the evolution process of the element content change signal.

[0087] By extracting correlation patterns from the mapping sub-relationships of the pre-mineralization stage in the dynamic mapping relationship, a close interaction was found between the stratigraphic sequence variation signal in the geological structural data module and the elemental content variation signal in the geochemical data module. Changes in stratigraphic sequence (such as the intrusion of intrusive bodies) lead to contact metamorphism of the surrounding strata, simultaneously promoting the migration of ore-forming elements from magma to the surrounding rocks, causing changes in elemental content. This interaction, where the evolution of the stratigraphic sequence variation signal drives the evolution of the elemental content variation signal, is defined as the first interaction.

[0088] Step S132: Extract the correlation rules of the mid-stage of mineralization from the dynamic mapping relationship, and determine the second interaction relationship between the isotope ratio signal of the geochemical data module and the resistivity change signal of the geophysical data module. The second interaction relationship reflects the driving characteristics of the evolution process of the isotope ratio signal on the evolution process of the resistivity change signal.

[0089] In the mapping relationship of the middle stage of mineralization, there is an interaction between the isotope ratio signal of the geochemical data module and the resistivity change signal of the geophysical data module. Hydrothermal activity causes changes in isotope ratios, and simultaneously, hydrothermal fluids react with the surrounding rocks, altering the mineral composition of the surrounding rocks and thus causing changes in resistivity. The evolution of the isotope ratio signal reflects the changes in the intensity and extent of hydrothermal activity, which in turn drives the evolution of the resistivity change signal, defined as the second interaction relationship.

[0090] Step S133: Extract the correlation rules of the late mineralization stage from the dynamic mapping relationship, and determine the third interaction relationship between the magnetic field change signal of the geophysical data module and the linear tectonic signal of the remote sensing image data module. The third interaction relationship reflects the driving characteristics of the evolution process of the magnetic field change signal on the evolution process of the linear tectonic signal.

[0091] The mapping relationship in the later stages of mineralization shows an interaction between the magnetic field variation signal from the geophysical data module and the linear tectonic signal from the remote sensing image data module. After the ore body morphology solidifies, the distribution of magnetic minerals within the ore body stabilizes, leading to stable magnetic field variation signal characteristics. Linear structures (such as fault zones) serve as the boundaries of the ore body, and their linear tectonic signal characteristics correspond to those of the magnetic field variation signal. The evolution of the magnetic field variation signal reflects the distribution characteristics of the ore body and drives the evolution of the linear tectonic signal, defined as the third interaction relationship.

[0092] Step S134: Set the geological structure data module as the starting node of the mineralization correlation chain. The starting node contains the stratigraphic sequence change signal, fault activity signal, fold morphology signal and corresponding spatial distribution information of the geological structure data module.

[0093] The construction of the mineralization correlation chain begins with the geological structure data module, which is designated as the starting node. The starting node contains all geological response signal types (sequence change signals, fault activity signals, and fold morphology signals) from the geological structure data module, along with their corresponding spatial distribution information. This spatial distribution information is stored as a sequence of geographic coordinates, corresponding one-to-one with each geological response signal type. For example, the sequence change signal corresponds to the coordinate sequence of the contact zone between the intrusive rock mass and the surrounding rock; the fault activity signal corresponds to the coordinate sequence of the fault fracture zone; and the fold morphology signal corresponds to the coordinate sequence of the fold axis trace.

[0094] Step S135: Connect the starting node and the geochemical data module node through the first interaction relationship, and record the coordinated change law of stratigraphic sequence change signal and element content change signal on the connection path. The coordinated change law includes the correspondence between stratigraphic sequence evolution level and element content change. The geochemical data module node includes the element content change signal, element combination signal, isotope ratio signal and corresponding spatial distribution information of the geochemical data module. The spatial distribution information of the geochemical data module node overlaps with the spatial distribution information of the starting node in terms of geographic coordinates.

[0095] Step S1351: Extract the relationship description of the first interaction relationship from the mapping sub-relationship of the pre-mineralization stage of the dynamic mapping relationship. This relationship description includes the evolutionary hierarchical division of the stratigraphic sequence change signal and the corresponding elemental content change characteristics.

[0096] A thorough analysis of the dynamic mapping relationships in the pre-mineralization stage yields a detailed description of the first interaction relationship. This description indicates that stratigraphic sequence variation signals can be divided into multiple evolutionary levels based on intrusive contact relationships, such as hyperdynamic contact levels, pulsating contact levels, and gradual contact levels. Each level corresponds to different elemental content variation characteristics; for example, hyperdynamic contact levels correspond to a sharp increase in ore-forming elements, pulsating contact levels correspond to fluctuating changes in ore-forming elements, and gradual contact levels correspond to a slow increase in ore-forming elements.

[0097] Step S1352: Divide the stratigraphic sequence change signal into multiple evolutionary levels according to the formation age, with each evolutionary level corresponding to a geological time interval.

[0098] Based on the attribute information of stratigraphic sequence change signals and combined with the regional geological timescale, the stratigraphic sequence change signals are divided into multiple evolutionary levels according to their formation age. For example, the stratigraphic sequence of the study area is divided into the Precambrian basement level, the Early Paleozoic sedimentary level, the Late Paleozoic volcanic rock level, and the Mesozoic intrusive rock level, etc. Each level corresponds to a specific geological time interval, such as the Mesozoic intrusive rock level corresponding to the Jurassic to the Cretaceous.

[0099] Step S1353: For each evolution level, extract the feature description of the element content change signal corresponding to that evolution level, and determine the correspondence between the evolution level and the element content change feature.

[0100] For each stratigraphic sequence evolution level, corresponding characteristic descriptions were extracted from the elemental content variation signals in the geochemical data module. For example, the elemental content variation signal characteristic corresponding to the Mesozoic intrusive rock level is a significantly increased copper content, with an enrichment coefficient greater than 10, and an anomalous peak appearing in the center of the intrusive body; the elemental content variation signal characteristic corresponding to the Early Paleozoic sedimentary level is a lower copper content, close to the background value, with an enrichment coefficient less than 2. Through comparative analysis, a one-to-one correspondence between each stratigraphic sequence evolution level and the elemental content variation characteristics was determined.

[0101] Step S1354: Record the correspondence between each stratigraphic sequence evolution level and the corresponding element content variation characteristics to form a synergistic variation table.

[0102] The correspondence between stratigraphic sequence evolution levels and element content variation characteristics is compiled into a co-variation table. The rows of the co-variation table represent stratigraphic sequence evolution levels, and the columns represent element content variation characteristic parameters (such as enrichment coefficient, anomalous area, peak intensity). The specific characteristic descriptions are filled in the cells.

[0103] Step S1355: Convert the collaborative change table into collaborative change pattern text that can be labeled on the connection path.

[0104] The content of the co-variation table is converted into a text describing the co-variation patterns in natural language. The text content must accurately reflect the correspondence between the stratigraphic sequence evolution level and the characteristics of element content changes. For example, "The copper enrichment coefficient of the Mesozoic intrusive rock level is greater than 10, the anomalous area covers the distribution range of the intrusive rock body, and the peak intensity appears in the center of the rock body; the copper enrichment coefficient of the Early Paleozoic sedimentary level is less than 2, and there is no obvious anomalous area."

[0105] Step S1356: Set a regularity annotation node on the connection path corresponding to the first interaction relationship, and embed the text of the cooperative change regularity into the annotation node.

[0106] A regularity annotation node is set on the connection path between the geological structure data module node (starting node) and the geochemical data module node. The main function of this node is to store the text of the coordinated change patterns, using a structured data format for easy reading and parsing by computer programs.

[0107] Step S1357: Position the annotation node in the middle of the connection path between the starting node and the geochemical data module node, and maintain a visual connection between the annotation node and the starting node and the geochemical data module node.

[0108] In the visualization of mineralization association chains, the regularity-labeled nodes are positioned in the middle of the connection path between the starting node and the geochemical data module node. They are connected to the two nodes by directed lines, with the arrows indicating the driving direction of the interaction (from the geological structure data module to the geochemical data module). The labeled nodes are rectangular in shape to distinguish them from the circular shapes of the data module nodes, facilitating visual identification.

[0109] Step S1358: Compare the stratigraphic division, element content variation characteristics description and dynamic mapping relationship of the text on the coordinated change law with the pre-mineralization correlation law, and adjust the text content to conform to the pre-mineralization correlation law.

[0110] The text on the coordinated variation patterns is compared with the pre-mineralization correlation patterns in the dynamic mapping relationship to check whether the stratigraphic division is consistent and whether the description of elemental content variation characteristics matches the results of magmatic material migration. If inconsistencies are found, such as the stratigraphic division omitting a certain intrusive contact type, or the description of elemental content variation characteristics not matching the isotopic analysis results, the text on the coordinated variation patterns is adjusted until it fully matches the pre-mineralization correlation patterns.

[0111] Step S1359: After completing the annotation node settings, check the connection status of the starting node, the first connection path, and the geochemical data module nodes, so that the interaction relationship between the data module nodes is fully reflected through the connection path and the coordinated change law of the annotation.

[0112] A comprehensive check was conducted on the connections of the starting node, the first connection path (including regularly labeled nodes), and the geochemical data module nodes. This ensured that the connection path lines were clear, the arrow directions were correct, the text content of the regularly labeled nodes was complete and accurate, and the geological response signal types and spatial distribution information contained in the data module nodes were correct. This check ensured that the first interaction relationship and the laws governing coordinated change were fully reflected.

[0113] The geochemical data module nodes contain elemental abundance variation signals, elemental assemblage signals, isotope ratio signals, and corresponding spatial distribution information. The spatial distribution information overlaps with the spatial distribution information of the starting node in terms of geographic coordinates. For example, the coordinate range of the anomalous area of ​​the elemental abundance variation signal overlaps with the coordinate range of the intrusive contact zone of the stratigraphic sequence variation signal, indicating a spatial correlation between the two.

[0114] Step S136: Connect the geochemical data module node and the geophysical data module node through the second interaction relationship, and record the coordinated change law of isotope ratio signal and resistivity change signal on the connection path. The coordinated change law includes the correspondence between isotope ratio range and resistivity change. The geophysical data module node includes the gravity anomaly signal, magnetic field change signal, resistivity change signal and corresponding spatial distribution information of the geophysical data module, and the spatial distribution information of the geophysical data module node and the spatial distribution information of the geochemical data module node have overlapping geographic coordinates.

[0115] The second interaction relationship description is extracted from the mid-stage mapping relationship of the dynamic mapping relationship. This description includes the interval division of the isotope ratio signal and the corresponding resistivity change characteristics. The isotope ratio signal is divided into multiple intervals according to its numerical range, such as low ratio interval, medium ratio interval, and high ratio interval. Each interval corresponds to different resistivity change characteristics; for example, the low ratio interval corresponds to high resistivity values, the medium ratio interval corresponds to medium resistivity values, and the high ratio interval corresponds to low resistivity values. The correspondence between the isotope ratio intervals and resistivity change characteristics is recorded to form a coordinated change table, which is then converted into coordinated change law text. Law annotation nodes are set on the connection paths corresponding to the second interaction relationship, and the coordinated change law text is embedded. The geophysical data module node contains gravity anomaly signals, magnetic field change signals, resistivity change signals, and their corresponding spatial distribution information. The spatial distribution information of the geophysical data module node overlaps with the spatial distribution information of the geochemical data module node in terms of geographic coordinates. For example, the coordinate range of the low resistivity anomaly area of ​​the resistivity change signal overlaps with the coordinate range of the high ratio interval of the isotope ratio signal.

[0116] Step S137: Connect the geophysical data module node and the remote sensing image data module node through the third interaction relationship, and record the coordinated change law of magnetic field change signal and linear structure signal on the connection path. The coordinated change law includes the correspondence between the intensity of magnetic field change and the number of linear structures. The remote sensing image data module node includes the rock exposure signal, vegetation distribution signal, linear structure signal and corresponding spatial distribution information of the remote sensing image data module, and the spatial distribution information of the remote sensing image data module node and the spatial distribution information of the geophysical data module node have overlapping geographic coordinates.

[0117] The relationship description of the third interaction relationship is extracted from the mapping sub-relationship of the late mineralization stage in the dynamic mapping relationship, including the intensity level classification of the magnetic field change signal and the corresponding linear structure quantity change characteristics. The magnetic field change signal is divided into weak anomaly level, moderate anomaly level, and strong anomaly level according to intensity. Each level corresponds to a different number of linear structures. For example, the strong anomaly level corresponds to a large number of linear structures, the moderate anomaly level corresponds to a moderate number of linear structures, and the weak anomaly level corresponds to a small number of linear structures. The correspondence between the magnetic field change intensity and the change in the number of linear structures is recorded to form a coordinated change table, which is converted into coordinated change law text. Law annotation nodes are set on the connection path corresponding to the third interaction relationship, and the coordinated change law text is embedded. The remote sensing image data module node contains rock exposure signal, vegetation distribution signal, linear structure signal and corresponding spatial distribution information. Its spatial distribution information overlaps with the spatial distribution information of the geophysical data module node in terms of geographic coordinates. For example, the coordinate range of the dense area of ​​linear structure signal overlaps with the coordinate range of the strong anomaly level of magnetic field change signal.

[0118] Step S138: Integrate the following nodes in the order of starting node, first connection path, geochemical data module node, second connection path, geophysical data module node, third connection path, and remote sensing image data module node to form the mineralization association chain.

[0119] The aforementioned nodes and connection paths are integrated sequentially to form a complete mineralization correlation chain. During the integration process, it is ensured that the connection paths between nodes are correct, the textual descriptions of the collaborative changes in regularly labeled nodes are accurate, and the geographic coordinate overlap of spatially distributed information is reasonable. The mineralization correlation chain is represented in the form of a directed graph, with nodes represented by circular or rectangular symbols, connection paths by arrowed lines, and regularly labeled nodes embedded in the center of the lines. The entire mineralization correlation chain clearly demonstrates the interaction relationships between data modules and the collaborative changes in attribute information.

[0120] Step S140: Filter the target area feature set that matches the mineralization association chain. The target area feature set consists of attribute information and spatial distribution information from multiple data modules that match the connection path of the mineralization association chain.

[0121] In prospective areas of volcanic rock-type copper-polymetallic deposits, target area feature sets that meet certain criteria are selected based on the constructed metallogenic correlation chains. These target area feature sets must contain attribute information and spatial distribution information from multiple data modules that match the connection paths of the metallogenic correlation chains. Specifically, the attribute information must conform to the collaborative change patterns along the connection paths, and the spatial distribution information must exhibit overlapping geographic coordinates.

[0122] Step S141: Extract the synergistic variation patterns corresponding to the three connection paths in the mineralization correlation chain, and generate a mineralization matching standard set. The mineralization matching standard set includes a first matching standard, a second matching standard, and a third matching standard. The first matching standard corresponds to the synergistic variation pattern of stratigraphic sequence variation signal and element content variation signal. The second matching standard corresponds to the synergistic variation pattern of isotope ratio signal and resistivity variation signal. The third matching standard corresponds to the synergistic variation pattern of magnetic field variation signal and linear tectonic signal.

[0123] Cooperative variation patterns are extracted from the regularly labeled nodes of the three connection paths of the mineralization correlation chain and transformed into mineralization matching standards. The first matching standard is based on the cooperative variation patterns of the first connection path, including the classification standards for stratigraphic sequence evolution levels and corresponding elemental content variation characteristics. For example, the standard for Mesozoic intrusive rock levels is that the stratigraphic contact relationship is intrusive contact with a baking edge phenomenon, and the corresponding copper enrichment coefficient standard is greater than 10. The second matching standard is based on the cooperative variation patterns of the second connection path, including the classification standards for isotope ratio ranges and corresponding resistivity variation characteristics. For example, the standard for high isotope ratio ranges is that a certain isotope ratio is greater than a certain value, and the corresponding resistivity value standard is less than a certain value. The third matching standard is based on the cooperative variation patterns of the third connection path, including the classification standards for magnetic field intensity levels and corresponding linear structure quantity standards. For example, the standard for strong magnetic field anomaly levels is that the magnetic field intensity anomaly value is greater than a certain value, and the corresponding linear structure quantity standard is greater than a certain number per square kilometer.

[0124] Step S142: Extract all stratigraphic sequence change signals and their corresponding spatial distribution information from the geological structure data module. Compare each stratigraphic sequence change signal with the stratigraphic sequence change features in the first matching criterion. Retain the stratigraphic sequence change signals and their corresponding spatial distribution information that conform to the stratigraphic sequence change features to form a geological structure candidate dataset.

[0125] All stratigraphic sequence variation signals in the geological structure data module are traversed, and the attribute information (such as stratigraphic contact relationships and baked rim development) and corresponding spatial distribution information (geographic coordinate sequence) of each signal are extracted. The attribute information of each stratigraphic sequence variation signal is compared with the stratigraphic sequence variation features in the first matching criterion to check whether it meets the criteria such as intrusive contact relationships and baked rim phenomena. Stratigraphic sequence variation signals that meet the criteria and their corresponding spatial distribution information are retained to form a geological structure candidate dataset. The geological structure candidate dataset is deduplicated to remove duplicate signal entries, ensuring that each entry in the dataset is unique.

[0126] Step S143: Extract all element content variation signals, isotope ratio signals, and corresponding spatial distribution information from the geochemical data module. Compare each element content variation signal with the element content variation characteristics in the first matching standard, and retain the element content variation signals and corresponding spatial distribution information that conform to the element content variation characteristics to form a first candidate geochemical dataset. Compare each isotope ratio signal with the isotope ratio variation characteristics in the second matching standard, and retain the isotope ratio signals and corresponding spatial distribution information that conform to the isotope ratio variation characteristics to form a second candidate geochemical dataset.

[0127] All elemental abundance variation signals and isotope ratio signals, along with their corresponding spatial distribution information, were extracted from the geochemical data module. For elemental abundance variation signals, their attribute information (such as the copper enrichment coefficient) was compared with the elemental abundance variation characteristics in the first matching criterion. Signals with enrichment coefficients greater than 10 and their corresponding spatial distribution information were retained to form the first candidate geochemical dataset. For isotope ratio signals, their attribute information (such as the isotope ratio value) was compared with the isotope ratio variation characteristics in the second matching criterion. Signals with ratios greater than a certain value and their corresponding spatial distribution information were retained to form the second candidate geochemical dataset. Deduplication was performed on both candidate datasets.

[0128] Step S144: Extract all resistivity change signals, magnetic field change signals, and corresponding spatial distribution information from the geophysical data module. Compare each resistivity change signal with the resistivity change characteristics in the second matching criterion, and retain the resistivity change signals and corresponding spatial distribution information that conform to the resistivity change characteristics to form the first candidate geophysical dataset. Compare each magnetic field change signal with the magnetic field change characteristics in the third matching criterion, and retain the magnetic field change signals and corresponding spatial distribution information that conform to the magnetic field change characteristics to form the second candidate geophysical dataset.

[0129] Resistivity and magnetic field variation signals, along with their spatial distribution information, are extracted from the geophysical data module. The resistivity variation signal attributes (e.g., resistivity values) are compared with resistivity variation features in the second matching criterion. Signals with resistivity values ​​below a certain threshold and their corresponding spatial distribution information are retained, forming the first candidate geophysical dataset. Similarly, the magnetic field variation signal attributes (e.g., magnetic field strength anomalies) are compared with magnetic field variation features in the third matching criterion. Signals with anomalies above a certain threshold and their corresponding spatial distribution information are retained, forming the second candidate geophysical dataset. Deduplication is then performed on both candidate datasets.

[0130] Step S145: Extract all linear structural signals and their corresponding spatial distribution information from the remote sensing image data module, compare each linear structural signal with the linear structural change features in the third matching criterion, retain the linear structural signals and their corresponding spatial distribution information that conform to the linear structural change features, and form a remote sensing image candidate dataset.

[0131] All linear structure signals and their spatial distribution information are extracted from the remote sensing image data module. The attribute information of the linear structure signals (such as the number of linear structures) is compared with the linear structure change features in the third matching criterion. Signals with a number of linear structures per square kilometer greater than a certain number and their corresponding spatial distribution information are retained to form a candidate dataset of remote sensing images, and deduplication is performed.

[0132] Step S146: Compare the spatial distribution information of the geological structure candidate dataset with the spatial distribution information of the geochemical first candidate dataset using geographic coordinates. Combine the geological structure data and geochemical data whose geographic coordinates overlap and whose attribute information meets the matching criteria to form the first cross dataset.

[0133] Step S1461: Extract the spatial distribution information corresponding to each data entry in the candidate dataset of geological structures. The spatial distribution information is stored in the form of a sequence of vertex coordinates of geographic coordinate polygons, with each data entry corresponding to a coordinate polygon.

[0134] Each data entry in the geological structure candidate dataset contains stratigraphic sequence variation signals and corresponding spatial distribution information. The spatial distribution information is represented in the form of geographic coordinate polygons. For example, the spatial distribution information of the contact zone of an intrusive rock mass is described by a polygon composed of multiple vertex coordinates. These vertex coordinates are arranged in clockwise or counterclockwise order to form a closed polygonal region.

[0135] Step S1462: Extract the spatial distribution information corresponding to each data entry in the first candidate geochemical dataset, and store it in the form of a sequence of vertex coordinates of geographic coordinate polygons, with each data entry corresponding to a coordinate polygon.

[0136] The data entries in the first candidate geochemical dataset contain signals of elemental content changes and corresponding spatial distribution information. The spatial distribution information is also stored in the form of vertex coordinate sequences of geographic coordinate polygons. For example, the spatial distribution information of the copper element anomaly area consists of a polygon composed of multiple vertex coordinates, representing the distribution range of the element anomaly.

[0137] Step S1463: Select the first data entry in the candidate dataset of geological structures, obtain the vertex coordinate sequence of its coordinate polygon, and determine the geographical coordinate range covered by the coordinate polygon.

[0138] For the first data entry in the candidate dataset of geological structures, read the coordinates of all vertices of its coordinate polygon, and calculate the minimum bounding rectangle of the polygon to obtain the geographic coordinate range it covers, including minimum longitude, maximum longitude, minimum latitude, and maximum latitude.

[0139] Step S1464: Traverse all data entries in the first candidate geochemical dataset and obtain the geographic coordinate range covered by the coordinate polygon of each entry.

[0140] Using the same method as in step S1463, traverse each data entry in the first candidate geochemical dataset, calculate the minimum bounding rectangle of each coordinate polygon, and determine the geographic coordinate range it covers.

[0141] Step S1465: Determine whether there is an overlap between the coordinate range of the first candidate geochemical data entry and the coordinate range of the geological structure data entry.

[0142] For the first data entry in the geological structure candidate dataset, coordinate range overlap is determined by sequentially comparing it with each data entry in the geochemical first candidate dataset. The method involves comparing the intersection of the minimum bounding rectangles of the two data entries; specifically, whether the minimum longitude of the geological structure data entry is less than the maximum longitude of the geochemical data entry, and whether the maximum longitude of the geological structure data entry is greater than the minimum longitude of the geochemical data entry; and simultaneously, whether the minimum latitude of the geological structure data entry is less than the maximum latitude of the geochemical data entry, and whether the maximum latitude of the geological structure data entry is greater than the minimum latitude of the geochemical data entry. If these conditions are met, coordinate range overlap is determined.

[0143] Step S1466: If there are overlapping areas, further check whether the stratigraphic sequence change signal of the geological structural data entry meets the first matching standard, and whether the elemental content change signal of the geochemical data entry meets the first matching standard.

[0144] For two data entries with overlapping coordinate ranges, re-examine whether the stratigraphic sequence variation signal of the geological structural data entry conforms to the stratigraphic sequence variation characteristics in the first matching criterion, such as whether the stratigraphic contact relationship is intrusive contact or whether there is a baked edge. At the same time, check whether the elemental content variation signal of the geochemical data entry conforms to the elemental content variation characteristics in the first matching criterion, such as whether the copper enrichment coefficient is greater than 10.

[0145] Step S1467: If both attribute information meets the first matching criterion, combine the two data entries into a cross data pair.

[0146] If the attribute information of both the geological structure data entry and the geochemical data entry meets the first matching criterion, then the two data entries are combined into a cross data pair. The cross data pair contains all the information of the geological structure data entry (stratigraphic sequence variation signal, spatial distribution information, attribute information) and all the information of the geochemical data entry (elemental content variation signal, spatial distribution information, attribute information).

[0147] Step S1468: Select the next data entry in the geological structure candidate dataset and repeat the above steps of determining the coordinate range, comparing the coordinate range, checking the attribute information, and filtering the cross data pairs.

[0148] After processing the first data entry in the geological structure candidate dataset, select the next data entry and repeat steps S1463 to S1467 until all data entries in the geological structure candidate dataset are compared with all data entries in the geochemical first candidate dataset.

[0149] Step S1469: Collect all selected cross data pairs. Each cross data pair contains the stratigraphic sequence variation signal and coordinate polygon of the geological structural data entry and the elemental content variation signal and coordinate polygon of the geochemical data entry.

[0150] Collect all eligible cross data pairs, each containing complete information on two data entries, to ensure the completeness and accuracy of the information.

[0151] Step S14610: Deduplicate the collected cross data pairs. If different cross data pairs contain the same geological structure data entries and the same geochemical data entries, retain only one cross data pair.

[0152] Examine the collected cross-data pairs to determine if there are any duplicates, i.e., different cross-data pairs contain the same geological structural data entries and the same geochemical data entries. If duplicates exist, retain only one cross-data pair to avoid data redundancy.

[0153] Step S14611: Integrate the deduplicated cross data pairs to form the first cross dataset. The dataset is organized in tabular form and includes fields such as geological structure data ID, geochemical data ID, coordinates of overlapping areas, stratigraphic sequence change signal, and element content change signal.

[0154] The deduplicated cross-referenced data pairs are integrated into a single dataset and organized in a table format. The table fields include geological structure data ID (a unique identifier for geological structure data entries), geochemical data ID (a unique identifier for geochemical data entries), coordinates of overlapping areas (the vertex coordinate sequence of the overlapping part of the coordinate polygon of the two data entries), stratigraphic sequence variation signal (the signal content of the geological structure data entries), and elemental content variation signal (the signal content of the geochemical data entries).

[0155] Step S147: Compare the spatial distribution information of the first cross dataset with the spatial distribution information of the second candidate geochemical dataset using geographic coordinates. Retain datasets whose geographic coordinates overlap and whose attribute information meets the matching criteria to form the second cross dataset.

[0156] Using a method similar to step S146, the geographic coordinates of the first cross dataset and the second candidate geochemical dataset are compared. The data entries in the first cross dataset include combinations of geological structural data and geochemical data, as well as coordinate polygons representing overlapping areas. The second candidate geochemical dataset includes isotope ratio signals and corresponding coordinate polygons. By comparing the geographic coordinate ranges of the overlapping area coordinate polygons with the isotope ratio signal coordinate polygons, it is determined whether overlap exists. Simultaneously, it is checked whether the isotope ratio signals meet the second matching criterion. Data combinations that meet the criteria are retained to form the second cross dataset. The second cross dataset includes fields such as geological structural data ID, geochemical data ID (elemental content variation signal and isotope ratio signal), overlapping area coordinates, stratigraphic sequence variation signal, elemental content variation signal, and isotope ratio signal.

[0157] Step S148: Compare the spatial distribution information of the second cross dataset with the spatial distribution information of the first geophysical candidate dataset using geographic coordinates. Retain datasets whose geographic coordinates overlap and whose attribute information meets the matching criteria to form the third cross dataset.

[0158] The second cross-dataset contains geological structural data, geochemical data (elemental abundance and isotope ratios), and coordinate polygons of overlapping areas. The first candidate geophysical dataset contains resistivity variation signals and corresponding coordinate polygons. The coordinate ranges of the two datasets are compared to determine overlap, and the resistivity variation signals are checked to see if they meet the second matching criterion. Data combinations that meet the criteria are retained to form the third cross-dataset, which includes fields such as geological structural data ID, geochemical data ID, geophysical data ID (resistivity variation signal), coordinates of overlapping areas, and various signals.

[0159] Step S149: Compare the spatial distribution information of the third cross dataset with the spatial distribution information of the second geophysical candidate dataset using geographic coordinates. Retain datasets whose geographic coordinates overlap and whose attribute information meets the matching criteria to form the fourth cross dataset.

[0160] Each entry in the third cross-tabulation dataset contains geological structural data, geochemical data (elemental abundance variation signals, isotope ratio signals), geophysical data (resistivity variation signals), and corresponding coordinate polygons of the overlapping regions. The second candidate geophysical dataset contains magnetic field variation signals and corresponding coordinate polygons, with each coordinate polygon defining the spatial extent of the magnetic field anomaly through a sequence of vertex coordinates.

[0161] First, the coordinate polygon of the overlapping region for each data entry in the third cross dataset is extracted. This polygon consists of at least four vertices arranged in a clockwise order, representing the spatial range where geological structures, elemental content, isotope ratios, and resistivity change signals overlap. Simultaneously, the coordinate polygon corresponding to each magnetic field change signal in the second geophysical candidate dataset is extracted, with the number of vertices varying between 4 and 20 depending on the complexity of the magnetic field anomaly morphology.

[0162] For the first data entry in the third cross dataset, the minimum longitude, maximum longitude, minimum latitude, and maximum latitude of the bounding rectangle of its overlapping region coordinate polygon are calculated. This process is repeated for all data entries in the second geophysical candidate dataset, similarly calculating the minimum bounding rectangle parameters for each magnetic field change signal coordinate polygon. By comparing the longitude and latitude ranges of the two rectangles, spatial overlap is determined—a potential spatial overlap exists when the minimum longitude of the third cross dataset entry is less than the maximum longitude of the geophysical data entry, and its maximum longitude is greater than the minimum longitude of the geophysical data entry; simultaneously, its minimum latitude is less than the maximum latitude of the geophysical data entry, and its maximum latitude is greater than the minimum latitude of the geophysical data entry.

[0163] For data entry combinations identified as potentially overlapping, a polygon intersection algorithm is further used to calculate the precise overlapping region. If the area of ​​the overlapping region accounts for more than 30% of the area of ​​the overlapping region of the entries in the third cross dataset, it is considered that there is a valid overlap in geographic coordinates. Subsequently, the attribute information of the magnetic field change signal is checked to see if it meets the magnetic field change intensity level in the third matching criterion—for example, the strong magnetic field anomaly level requires that the total magnetic field intensity anomaly value is higher than 5 times the standard deviation of the regional background value, and the anomaly morphology is strip-shaped or elliptical.

[0164] Data combinations with valid geographic coordinate overlap and magnetic field change signals conforming to the third matching criterion are retained to form a preliminary fourth cross dataset. This dataset undergoes deduplication; when two data combinations contain the same geological structural data ID, geochemical data ID, and geophysical data ID (resistivity and magnetic field), only the entry with the largest overlapping area is retained. The final fourth cross dataset is organized in tabular form, with added fields for geophysical magnetic field data ID and magnetic field change signal, recording the intensity level, morphological characteristics, and corresponding coordinate polygon parameters of the magnetic field anomalies.

[0165] Step S1410: Compare the spatial distribution information of the fourth cross dataset with the spatial distribution information of the remote sensing image candidate dataset using geographic coordinates, and retain the dataset combinations where the geographic coordinates overlap and the attribute information meets the matching criteria.

[0166] The fourth cross-dataset contains a combination of geological structure, geochemical (elemental abundance, isotope ratios), and geophysical (resistivity, magnetic field) data, along with coordinate polygons that overlap. The remote sensing image candidate dataset contains linear structural signals and their corresponding coordinate polygons. These polygons are formed by connecting the endpoint coordinates of the linear structures obtained through remote sensing interpretation. Each linear structural signal corresponds to at least two endpoint coordinates, and complex linear structural networks consist of multiple line segment coordinate sequences.

[0167] Extract the coordinate polygon of the overlapping region for each entry in the fourth cross dataset, and calculate its minimum bounding rectangle as a spatial extent reference. Traverse the linear structure signal entries in the remote sensing image candidate dataset, and extract the coordinate polygon for each entry—for a single linear structure, the coordinate polygon is simplified to the buffer region containing the line segment (the buffer distance is set to 50 meters to 500 meters according to the length of the linear structure); for dense linear structure regions, the coordinate polygon is the minimum convex polygon containing all relevant line segments.

[0168] By comparing the minimum bounding rectangles of entries in the fourth cross dataset with those in the remote sensing image data, combinations with potential spatial overlap are identified. Precise polygon intersection calculations are performed on these potential overlapping combinations. When the length of the overlapping region exceeds 40% of the total length of the linear structures, it is considered a valid geographic coordinate overlap. Simultaneously, the attribute information of the linear structure signals is checked to ensure it meets the linear structure quantity requirements in the third matching criterion—for example, the linear structure quantity standard for areas with strong magnetic field anomalies is at least 15 linear structures longer than 1 kilometer per 100 square kilometers, and the ratio of the number of northeast-trending to northwest-trending linear structures is between 1.5 and 2.5.

[0169] Retain the data combinations that meet the above conditions to complete the initial screening of the target region feature set.

[0170] Step S1411: Extract all attribute information from the retained dataset combination, including stratigraphic sequence variation signals, element content variation signals, isotope ratio signals, resistivity variation signals, magnetic field variation signals, linear tectonic signals, and corresponding spatial distribution information, and integrate them to form a target area feature set.

[0171] Information was integrated from datasets retained after multiple rounds of cross-screening. Each dataset contains six core geological response signals: stratigraphic sequence variation signals from the geological structural data module (recording stratigraphic contact relationship types, baked edge development width, and intrusive rock isotopic ages); elemental content variation signals from the geochemical data module (including enrichment coefficients and anomalous duration lengths of copper, molybdenum, and gold) and isotopic ratio signals (recording the interval distribution characteristics of lead and sulfur isotope ratios); resistivity variation signals from the geophysical data module (including the burial depth range, thickness variation, and apparent resistivity gradient of low-resistivity bodies) and magnetic field variation signals (recording the peak intensity, strike azimuth, and estimated depth of magnetic anomalies); and linear structural signals from the remote sensing image data module (including the density of linear structures, number of intersections, and angles with the magnetic anomaly axis).

[0172] Spatial distribution information is integrated into a unified coordinate reference system (using the 2000 National Geodetic Coordinate System, Gauss-Kruger 3-degree zonal projection). The coordinate polygon corresponding to each signal is checked for topological relationships to ensure there are no hanging nodes or self-intersections. The integrated target area feature set is stored in a structured data format. Each feature entry contains a unique feature ID, data source module identifier, signal type code, attribute parameter list, and a WKT (Well-Known Text) string representation of the spatial coordinate polygon, facilitating subsequent spatial analysis and fit calculation.

[0173] Step S150: Based on the synergistic change law in the mineralization correlation chain, determine the degree of fit between the spatial units of the target area feature set and the mineralization conditions. Adjust the spatial boundary range of the target area feature set according to the degree of fit. Repeat the adjustment process until no new spatial units that meet the degree of fit requirements can be included, and generate the delineation result of the mineral target area. The degree of fit reflects the degree of matching between the attribute information in the spatial unit and the synergistic change law of the mineralization correlation chain.

[0174] In the prospective copper-polymetallic deposit area of ​​volcanic rock type, the target area feature set covers an area of ​​approximately 500 square kilometers. Precise delineation of the target area boundary is required through spatial unit division and fit calculation. The spatial units are divided using square grids, with the grid side length set to 500 meters based on the regional geological complexity. The entire target area feature set is divided into approximately 2000 spatial units. Each unit is uniquely identified by its row and column numbers, and its center point's geographic coordinates and the coordinates of its four corner vertices are recorded.

[0175] Step S151: Extract the synergistic change patterns of the three connection paths in the mineralization association chain, and determine the mineralization association priority corresponding to each synergistic change pattern. The synergistic change pattern of the first connection path corresponds to the first association priority, the synergistic change pattern of the second connection path corresponds to the second association priority, and the synergistic change pattern of the third connection path corresponds to the third association priority.

[0176] The textual patterns of coordinated changes in three connection paths were extracted from the regularity-annotated nodes of the ore-forming association chain. The ore-forming association priority of each pattern was determined using an expert scoring method. The coordinated change pattern of the first connection path (geological structure-geochemical elements) directly reflects the initial accumulation process of ore-forming materials and was assigned the highest priority (weight coefficient set to 0.4). The second connection path (geochemical isotopes-geophysical resistivity) reflects the migration channels of ore-forming fluids and was assigned a medium priority (weight coefficient 0.35). The third connection path (geophysical magnetic field-remote sensing linear structure) reflects the surface markers of the ore body and was assigned a low priority (weight coefficient 0.25). The priority weight coefficients were determined using the Analytic Hierarchy Process (AHP). Five geological experts with over 20 years of experience in ore-forming regularity research were invited to conduct pairwise comparisons of the importance of each path, constructing a judgment matrix and passing a consistency test (CR value less than 0.1).

[0177] Step S152: Divide the spatial distribution information of the target area feature set into multiple spatial units of equal area, each spatial unit having a unique geographic coordinate identifier.

[0178] A regular grid division method was adopted, using the smallest bounding rectangle of the coordinate polygon of the overlapping area of ​​the target feature set as the boundary, and dividing the grid with 500-meter intervals along both the east-west and north-south directions. Each spatial unit is a square with an area of ​​0.25 square kilometers, and the unit number adopts the format of "row number-column number" (e.g., R012-C034), where the row number increases from north to south and the column number increases from west to east. The geographic coordinates of each unit include the latitude and longitude of the center point (accurate to 0.0001 degrees) and the latitude and longitude of the four corner vertices, stored as decimal coordinate values ​​in the WGS84 coordinate system. For spatial units that cross the boundary of the target feature set, the proportion of their area within the boundary is recorded. When this proportion is less than 30%, it is marked as an edge unit.

[0179] Step S153: For each spatial unit, extract the stratigraphic sequence variation signal and element content variation signal within the spatial unit, determine the matching status of the two based on the cooperative variation law of the first connection path, and determine the matching degree sub-item of the corresponding dimension in combination with the first association priority.

[0180] For each spatial unit, spatial overlay analysis is used to extract stratigraphic sequence variation signals and elemental content variation signals falling within that unit. The extraction indices for stratigraphic sequence variation signals include the presence of intrusive contact relationships (Boolean value), the width of baked rim development (continuous value), and stratigraphic inversion phenomena (Boolean value). The extraction indices for elemental content variation signals include the copper enrichment coefficient (continuous value), molybdenum anomaly contrast (continuous value), and the copper-molybdenum ratio (continuous value).

[0181] Based on the synergistic change patterns of the first connection path (the correspondence between stratigraphic sequence evolution levels and elemental content changes), a matching degree scoring model is established. For example, when Mesozoic intrusive rock level signals are present (intrusive contact + baking edge width > 2 meters) and the copper enrichment coefficient > 15, the matching degree score is 100 points; when Mesozoic intrusive rock level signals are present but the copper enrichment coefficient is between 10 and 15, the score is 80 points; when only sedimentary stratigraphic contact relationships exist and the copper enrichment coefficient < 5, the score is 0 points. After normalizing the matching degree score to the 0-1 interval, it is multiplied by the first association priority weight (0.4) to obtain the first dimension fit degree sub-item (F1).

[0182] Step S154: Extract the isotope ratio signal and resistivity change signal within the space cell, determine the matching status of the two based on the cooperative change law of the second connection path, and determine the matching degree sub-item of the corresponding dimension in combination with the second association priority.

[0183] Isotope ratio signals (e.g., lead-206 / lead-204 ratio, sulfur-34 / sulfur-32 ratio) and resistivity change signals (apparent resistivity value, resistivity gradient value) are extracted within the spatial unit. The cooperative change law of the second connection path requires that the high isotope ratio range (lead-206 / lead-204>18.5) corresponds to the low resistivity value (<50 ohm-meter). A two-dimensional matching matrix is ​​established. When the isotope ratio falls into the high range and the resistivity value is below the threshold, the matching degree score is 100 points; when the isotope ratio is in the middle range (18.0-18.5) and the resistivity value is between 50-100 ohm-meter, the score is 60 points; when the isotope ratio and resistivity value change in opposite directions, the score is 0 points. The normalized score is multiplied by the second association priority weight (0.35) to obtain the second dimension fit sub-item (F2).

[0184] Step S155: Extract the magnetic field change signal and linear construction signal within the space unit, determine the matching status of the two based on the cooperative change law of the third connection path, and determine the matching degree sub-item of the corresponding dimension in combination with the third association priority.

[0185] Magnetic field variation signals (anomaly amplitude, gradient value) and linear structure signals (number of linear structures, average length, directional rose diagram) are extracted within spatial cells. The cooperative variation law of the third connectivity path requires strong magnetic field anomalies (amplitude > 300 nanoteslas) to correspond to high-density linear structures (number of structures > 5 / km²). When the magnetic field anomaly level is strong and the linear structure density is above the threshold, the matching score is 100; when the magnetic field anomaly is moderate (100-300 nanoteslas) and the linear structure density is moderate (3-5 structures / km²), the score is 50; when there is no magnetic field anomaly or the linear structure is sparse, the score is 0. The normalized score is multiplied by the third association priority weight (0.25) to obtain the third-dimensional fit sub-item (F3).

[0186] Step S156: Combine the fit sub-items of each dimension to determine the overall fit of the spatial unit. The overall fit satisfies that all dimension sub-items are consistent with the description of the cooperative change law.

[0187] The overall fit (F) of a spatial unit is calculated using a weighted summation: F = F1 + F2 + F3, with a result ranging from 0 to 1. Simultaneously, a dimensional constraint is set—if any dimensional sub-item (F1, F2, F3) is below 0.3, even if the weighted sum exceeds the threshold, the overall fit is still considered substandard. This constraint ensures that each stage of the mineralization process has corresponding supporting evidence, preventing a single strong signal from masking the absence of other key stages. For example, a spatial unit may have an extremely high elemental anomaly (F1 = 0.4) but lack a corresponding resistivity anomaly (F2 = 0.2); in this case, the overall fit is considered substandard.

[0188] Step S157: Calculate the overall fit of all spatial units, determine the spatial unit clusters that meet the overall fit requirements, and generate the initial target area boundary based on the outer geographic coordinates of the spatial unit clusters.

[0189] The overall fit threshold was set to 0.65 (this threshold was determined through ROC curve analysis to ensure that the accuracy and recall of target region prediction both reached over 85%). All spatial units were traversed, and units with an overall fit F ≥ 0.65 were marked as qualified units. A region growing algorithm was used to identify qualified unit clusters—using any qualified unit as a seed, qualified units within its 8 neighborhoods (East, South, West, North, Northeast, Southeast, Northwest, Southwest) were merged into the same cluster. This process was repeated until all qualified units were assigned to a unique cluster.

[0190] For large clusters containing more than 20 qualified units, the boundary coordinates of their outer spatial units are extracted. The Convex Hull algorithm is used to generate the minimum bounding polygon of the cluster, which serves as the initial target area boundary. The vertex coordinates of this polygon are determined by connecting the outer edge vertices of the cluster's outer units; the number of vertices ranges from 8 to 30 depending on the cluster's shape complexity. For separate small clusters (5-20 qualified units), if their distance from the main cluster (the distance between the nearest unit centers) is less than 2 kilometers, they are merged into the initial target area boundary; otherwise, they are marked as isolated anomalies and not included in the target area.

[0191] Step S158: Extract the adjacent spatial units outside the initial target area boundary, determine whether the overall fit of the adjacent spatial units meets the requirements, and if the overall fit of the adjacent spatial units meets the requirements, include the adjacent spatial units in the target area and adjust the initial target area boundary.

[0192] After the initial target area boundary is generated, buffer analysis is used to extract adjacent spatial cells within a 500-meter radius outside the boundary. For each adjacent cell, its overall fit is recalculated (the result of the already calculated cell is directly used, and the uncalculated cell is calculated according to steps S153-S156). When the overall fit of the adjacent cell F ≥ 0.65, it is included in the target area, and the spatial cell cluster is updated.

[0193] When adjusting the initial target area boundary, a dynamic convex hull algorithm is used—based on the original boundary polygon, the outer vertices of the newly added units are added, and the minimum bounding polygon is recalculated. During boundary adjustment, the closure of the polygon and the consistency of the vertex order (using a clockwise direction) must be maintained. For example, if the initial target area boundary is a polygon with 12 vertices, adding 3 adjacent units may increase the number of vertices in the boundary polygon to 15-18 by adding the outer vertices of these 3 units.

[0194] Step S159: Repeat the steps of extracting adjacent spatial units outside the adjusted target area boundary, judging the overall fit, and determining whether to include them, until the overall fit of adjacent spatial units outside the boundary does not meet the requirements. Use the final adjusted target area boundary as the spatial range of the mineral target area, integrate the attribute information and geographic coordinate information of all spatial units within this spatial range, and generate the delineation result of the mineral target area.

[0195] After each round of boundary adjustment, adjacent spatial units one unit away from the new boundary are re-extracted, and the fit determination and boundary adjustment process is repeated. A maximum of 5 expansion rounds are set to prevent the target area from expanding indefinitely. Boundary expansion stops when the overall fit of all adjacent outer units is <0.65 in a given round of boundary adjustment, or when the maximum expansion round has been reached.

[0196] The final mineral target area delineation results include the following: the vertex coordinate sequence of the target area boundary polygon (WGS84 coordinate system, accurate to 0.0001 degrees), a list of the number and number of spatial units within the target area, statistical information on the attributes of each data module (such as average element enrichment coefficient, major isotope ratio range, and typical geophysical parameter range), and a heat map of the distribution of evidence for the mineralization stages (displaying the distribution density of qualified units according to the three mineralization stages). The results are output in GIS-compatible formats (Shapefile and GeoJSON) and accompanied by a detailed delineation report explaining the mineralization geological characteristics of the target area, key evidence chains, and recommendations for further work.

Claims

1. A method for intelligent delineation of mineral target areas based on multi-source heterogeneous geoscientific data, characterized in that, The method includes: The multi-source heterogeneous geoscientific dataset is divided into multiple data modules according to the scope of geological influence. The multi-source heterogeneous geoscientific dataset includes geological structural data, geochemical data, geophysical data and remote sensing image data. Each data module corresponds to a geoscientific data type, and each data module contains spatial distribution information and attribute information of the geoscientific data type. The spatial distribution information is recorded in the form of geographic coordinate sequence, and the attribute information is recorded in the form of geological feature description entries. A dynamic mapping relationship between multiple data modules and mineralization mechanisms is constructed. The dynamic mapping relationship is generated based on the correlation between the attribute information of different data modules and the geological processes in the mineralization process. The mineralization process includes three stages: material accumulation in the early stage of mineralization, energy transformation in the middle stage of mineralization, and ore body stabilization in the later stage of mineralization. The correlation relationship is obtained by analyzing the impact of geological processes in each stage on different geoscientific data types. Based on dynamic mapping relationships, a mineralization correlation chain is generated between multiple data modules. The mineralization correlation chain takes data modules as nodes and the interaction relationship between different data modules in each mineralization stage as the connection path. Each connection path contains the coordinated change law of data module attribute information. The coordinated change law reflects the synchronous evolution characteristics of attribute information of different data modules within the same mineralization stage. Filter the target area feature set that matches the mineralization association chain. The target area feature set consists of attribute information and spatial distribution information that match the connection path of the mineralization association chain in multiple data modules. Based on the synergistic change patterns in the mineralization correlation chain, the spatial unit of the target area feature set is determined to match the mineralization conditions. The spatial boundary range of the target area feature set is adjusted according to the matching degree. The adjustment process is repeated until no new spatial unit that meets the matching degree requirements can be included, thus generating the delineation result of the mineral target area. The matching degree reflects the degree of matching between the attribute information within the spatial unit and the synergistic change patterns in the mineralization correlation chain.

2. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 1, characterized in that, The construction of a dynamic mapping relationship between multiple data modules and mineralization mechanisms includes: Geological response signal types are extracted from the attribute information of each data module. The geological response signal types of the geological structure data module include stratigraphic sequence change signals, fault activity signals, and fold morphology signals. The geological response signal types of the geochemical data module include element content change signals, element combination signals, and isotope ratio signals. The geological response signal types of the geophysical data module include gravity anomaly signals, magnetic field change signals, and resistivity change signals. The geological response signal types of the remote sensing image data module include rock exposure signals, vegetation distribution signals, and linear structure signals. The study analyzed the impact of geological processes during the pre-mineralization material accumulation stage on the geological response signals of each data module. It determined the stratigraphic sequence variation signal characteristics of the geological structural data module and the element content variation signal characteristics of the geochemical data module corresponding to the material migration of magmatic activity. It also determined the fold morphology signal characteristics of the geological structural data module and the element combination signal characteristics of the geochemical data module corresponding to the material accumulation of sedimentary environment. The influence of geological processes during the mid-stage of mineralization energy transformation on the geological response signals of each data module was analyzed. The fault activity signal characteristics of the geological structure data module and the magnetic field change signal characteristics of the geophysical data module were determined to correspond to the energy release effect of tectonic stress. The isotope ratio signal characteristics of the geochemical data module and the resistivity change signal characteristics of the geophysical data module were determined to correspond to the energy transfer effect of hydrothermal activity. The study analyzed the impact of geological processes during the later stages of mineralization on the geological response signals of each data module. It determined the resistivity change signal characteristics of the geophysical data module and the rock exposure signal characteristics of the remote sensing image data module corresponding to the wall rock alteration protection effect. It also determined the linear structural signal characteristics of the remote sensing image data module and the stratigraphic sequence change signal characteristics of the geological structure data module corresponding to the ore body morphology solidification effect. Establish an association entry between the geological response signal type of each data module and the geological processes at each stage of mineralization. Each association entry records the characteristics of the geological response signal, the corresponding geological process type, and the mineralization stage. All related entries are integrated to form a set of related rules. Based on the set of related rules, a stage mapping sub-relationship between data modules and mineralization mechanism is constructed, with each of the early, middle and late mineralization stages corresponding to a stage mapping sub-relationship. The three-stage mapping sub-relationships are connected in sequence according to the mineralization time, and the transition characteristics of geological response signals between different stage mapping sub-relationships are supplemented to generate a dynamic mapping relationship that reflects the evolution of data module attribute information throughout the mineralization process.

3. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 1, characterized in that, The generation of mineralization association chains between multiple data modules based on dynamic mapping relationships includes: The correlation patterns of the pre-mineralization stage are extracted from the dynamic mapping relationship, and the first interaction relationship between the stratigraphic sequence change signal of the geological structure data module and the element content change signal of the geochemical data module is determined. The first interaction relationship reflects the driving characteristics of the evolution process of the stratigraphic sequence change signal on the evolution process of the element content change signal. The correlation patterns of the mid-stage of mineralization are extracted from the dynamic mapping relationship, and the second interaction relationship between the isotope ratio signal of the geochemical data module and the resistivity change signal of the geophysical data module is determined. The second interaction relationship reflects the driving characteristics of the evolution process of the isotope ratio signal on the evolution process of the resistivity change signal. The correlation patterns of the late mineralization stage are extracted from the dynamic mapping relationship, and the third interaction relationship between the magnetic field change signal of the geophysical data module and the linear tectonic signal of the remote sensing image data module is determined. The third interaction relationship reflects the driving characteristics of the evolution process of the magnetic field change signal on the evolution process of the linear tectonic signal. The geological structure data module is set as the starting node of the metallogenic correlation chain. This starting node contains the stratigraphic sequence change signal, fault activity signal, fold morphology signal and corresponding spatial distribution information of the geological structure data module. The starting node and the geochemical data module node are connected through a first interaction relationship. The coordinated change pattern of stratigraphic sequence change signal and element content change signal is recorded on the connection path. The coordinated change pattern includes the correspondence between stratigraphic sequence evolution level and element content change. The geochemical data module node contains the element content change signal, element combination signal, isotope ratio signal and corresponding spatial distribution information of the geochemical data module. The spatial distribution information of the geochemical data module node overlaps with the spatial distribution information of the starting node in terms of geographic coordinates. The geochemical data module node and the geophysical data module node are connected through a second interaction relationship. The coordinated variation law of isotope ratio signal and resistivity change signal is recorded on the connection path. The coordinated variation law includes the correspondence between isotope ratio range and resistivity change. The geophysical data module node contains the gravity anomaly signal, magnetic field change signal, resistivity change signal and corresponding spatial distribution information of the geophysical data module. The spatial distribution information of the geophysical data module node and the spatial distribution information of the geochemical data module node have overlapping geographic coordinates. The geophysical data module node and the remote sensing image data module node are connected through a third interaction relationship. The coordinated change pattern of magnetic field change signal and linear tectonic signal is recorded on the connection path. The coordinated change pattern includes the correspondence between the intensity of magnetic field change and the number of linear structures. The remote sensing image data module node contains the rock exposure signal, vegetation distribution signal, linear tectonic signal and corresponding spatial distribution information of the remote sensing image data module. The spatial distribution information of the remote sensing image data module node and the spatial distribution information of the geophysical data module node have overlapping geographic coordinates. The mineralization association chain is formed by integrating the following nodes in the order of starting node, first connection path, geochemical data module node, second connection path, geophysical data module node, third connection path, and remote sensing image data module node.

4. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 1, characterized in that, The set of target area features that conform to the mineralization association chain includes: The synergistic variation patterns of the three connection paths in the mineralization correlation chain are extracted to generate a mineralization matching standard set. The mineralization matching standard set includes a first matching standard, a second matching standard, and a third matching standard. The first matching standard corresponds to the synergistic variation pattern of stratigraphic sequence variation signal and element content variation signal. The second matching standard corresponds to the synergistic variation pattern of isotope ratio signal and resistivity variation signal. The third matching standard corresponds to the synergistic variation pattern of magnetic field variation signal and linear tectonic signal. Extract all stratigraphic sequence change signals and their corresponding spatial distribution information from the geological structure data module. Compare each stratigraphic sequence change signal with the stratigraphic sequence change features in the first matching criterion. Retain stratigraphic sequence change signals and their corresponding spatial distribution information that conform to the stratigraphic sequence change features to form a geological structure candidate dataset. Extract all elemental content variation signals, isotope ratio signals, and corresponding spatial distribution information from the geochemical data module. Compare each elemental content variation signal with the elemental content variation characteristics in the first matching standard, and retain the elemental content variation signals and corresponding spatial distribution information that conform to the elemental content variation characteristics to form the first candidate geochemical dataset. Compare each isotope ratio signal with the isotope ratio variation characteristics in the second matching standard, and retain the isotope ratio signals and corresponding spatial distribution information that conform to the isotope ratio variation characteristics to form the second candidate geochemical dataset. All resistivity change signals, magnetic field change signals, and corresponding spatial distribution information are extracted from the geophysical data module. Each resistivity change signal is compared with the resistivity change characteristics in the second matching criterion, and the resistivity change signals that conform to the resistivity change characteristics and their corresponding spatial distribution information are retained to form the first candidate geophysical dataset. Each magnetic field change signal is compared with the magnetic field change characteristics in the third matching criterion, and the magnetic field change signals that conform to the magnetic field change characteristics and their corresponding spatial distribution information are retained to form the second candidate geophysical dataset. Extract all linear structural signals and their corresponding spatial distribution information from the remote sensing image data module. Compare each linear structural signal with the linear structural change features in the third matching criterion. Retain the linear structural signals and their corresponding spatial distribution information that conform to the linear structural change features to form a remote sensing image candidate dataset. The spatial distribution information of the geological structure candidate dataset is compared with the spatial distribution information of the geochemical first candidate dataset by geographic coordinates. The geological structure data and geochemical data with overlapping geographic coordinates and matching attribute information are retained to form the first cross dataset. The spatial distribution information of the first cross dataset is compared with the spatial distribution information of the second candidate geochemical dataset by geographic coordinates. The datasets with overlapping geographic coordinates and whose attribute information all meet the matching criteria are retained to form the second cross dataset. The spatial distribution information of the second cross dataset is compared with the spatial distribution information of the first geophysical candidate dataset using geographic coordinates. Data sets with overlapping geographic coordinates and whose attribute information all meet the matching criteria are retained to form the third cross dataset. The spatial distribution information of the third cross dataset is compared with the spatial distribution information of the second geophysical candidate dataset using geographic coordinates. Data sets with overlapping geographic coordinates and matching attribute information are retained to form the fourth cross dataset. The spatial distribution information of the fourth cross dataset is compared with the spatial distribution information of the remote sensing image candidate dataset by geographic coordinates, and the dataset combination with overlapping geographic coordinates and attribute information that meets the matching criteria is retained. Extract all attribute information from the preserved dataset combination, including stratigraphic sequence variation signals, element content variation signals, isotope ratio signals, resistivity variation signals, magnetic field variation signals, linear tectonic signals, and corresponding spatial distribution information, and integrate them to form a target area feature set.

5. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 1, characterized in that, The process involves determining the degree of fit between the spatial units of the target area feature set and the mineralization conditions based on the synergistic change patterns in the mineralization correlation chain, adjusting the spatial boundary range of the target area feature set according to the degree of fit, and repeating the adjustment process until no new spatial units meeting the degree of fit requirements can be included, thereby generating the delineation results of the mineral target area, including: The synergistic change patterns of the three connection paths in the mineralization association chain are extracted, and the mineralization association priority corresponding to each synergistic change pattern is determined. The synergistic change pattern of the first connection path corresponds to the first association priority, the synergistic change pattern of the second connection path corresponds to the second association priority, and the synergistic change pattern of the third connection path corresponds to the third association priority. The spatial distribution information of the target area feature set is divided into multiple spatial units of equal area, and each spatial unit has a unique geographic coordinate identifier. For each spatial unit, the stratigraphic sequence variation signal and element content variation signal within that spatial unit are extracted. The matching status of the two is determined based on the coordinated variation law of the first connection path, and the degree of fit sub-item of the corresponding dimension is determined in combination with the first association priority. Extract the isotope ratio signal and resistivity change signal within the space cell, determine the matching status of the two based on the cooperative change law of the second connection path, and determine the matching degree sub-item of the corresponding dimension in combination with the second association priority. Extract the magnetic field change signal and linear structure signal within the space unit, determine the matching status of the two based on the cooperative change law of the third connection path, and determine the degree of fit sub-item of the corresponding dimension in combination with the third association priority. By combining the fit sub-items of each dimension, the overall fit of the spatial unit is determined. The overall fit satisfies that all sub-items of the dimension are consistent with the description of the cooperative change law. The overall fit of all spatial units is statistically analyzed, and spatial unit clusters that meet the overall fit requirements are identified. The initial target area boundary is generated based on the outer geographic coordinates of the spatial unit cluster. Extract adjacent spatial units outside the initial target area boundary, determine whether the overall fit of the adjacent spatial units meets the requirements, and if the overall fit of the adjacent spatial units meets the requirements, include the adjacent spatial units in the target area and adjust the initial target area boundary. The process of repeatedly extracting adjacent spatial units outside the adjusted target area boundary, judging the overall fit, and determining whether to include them is repeated until the overall fit of adjacent spatial units outside the boundary does not meet the requirements. The final adjusted target area boundary is used as the spatial range of the mineral target area. The attribute information and geographic coordinate information of all spatial units within this spatial range are integrated to generate the delineation result of the mineral target area.

6. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 2, characterized in that, The extraction of geological response signal types from the attribute information of each data module includes: The attribute information of the geological structure data module is analyzed. The attribute information is recorded in the form of geological exploration report entries. Entries describing the chronological order of strata formation are extracted from them, and the signals corresponding to the entries describing the chronological order of strata formation are defined as stratum sequence change signals. Extract the entries describing the frequency and range of fault occurrence from the attribute information of the geological structure data module, and define the signals corresponding to the entries describing the frequency and range of fault occurrence as fault activity signals; Extract the entries describing the fold bending morphology and extension direction from the attribute information of the geological structure data module, and define the signals corresponding to the entries describing the fold bending morphology and extension direction as fold morphology signals. The attribute information of the geochemical data module is analyzed. The attribute information is recorded in the form of element detection report entries. Entries describing the differences in the content of target mineral-related elements in different regions are extracted from them. The signals corresponding to the entries describing the differences in the content of target mineral-related elements in different regions are defined as element content change signals. Extract the entries from the geochemical data module attribute information that describe the types and proportions of different elements that appear together, and define the signals corresponding to the entries that describe the types and proportions of different elements that appear together as element combination signals. Extract the entries describing the changes in the atomic ratio of the target isotope from the attribute information of the geochemical data module, and define the signals corresponding to the entries describing the changes in the atomic ratio of the target isotope as isotope ratio signals; The attribute information of the geophysical data module is analyzed. The attribute information is recorded in the form of geophysical survey report entries. Entries describing the difference between the gravity value of the study area and the standard gravity field are extracted from it. The signals corresponding to the entries describing the difference between the gravity value of the study area and the standard gravity field are defined as gravity anomaly signals. Extract the entries describing the changes in the magnetic field induction intensity of the geomagnetic field in the study area from the attribute information of the geophysical data module, and define the signals corresponding to the entries describing the changes in the magnetic field induction intensity of the geomagnetic field in the study area as magnetic field change signals. Extract the entries from the geophysical data module attribute information that describe the differences in the ability of materials in the study area to impede current, and define the signals corresponding to the entries that describe the differences in the ability of materials in the study area to impede current as resistivity change signals. The attribute information of the remote sensing image data module is analyzed. The attribute information is recorded in the form of image interpretation report entries. Entries describing the area and location of rock outcrops in the study area are extracted from them. The signals corresponding to the entries describing the area and location of rock outcrops in the study area are defined as rock exposure signals. Extract the items describing the vegetation cover area and growth status of the study area from the attribute information of the remote sensing image data module, and define the signals corresponding to the items describing the vegetation cover area and growth status of the study area as vegetation distribution signals. Extract the entries describing the location and length of linear geological structures from the attribute information of the remote sensing image data module, and define the signals corresponding to the entries describing the location and length of linear geological structures as linear structure signals; The extracted geological response signal types are categorized and recorded according to data module type, forming lists of geological structural signals, geochemical signals, geophysical signals, and remote sensing image signals. Each list includes the signal type name and the source of the corresponding attribute information entries.

7. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 2, characterized in that, The process involves integrating all related entries to form a set of related patterns, and then constructing a stage mapping sub-relationship between the data module and the mineralization mechanism based on this set of related patterns, including: Collect relevant entries for the three stages of mineralization: pre-mineralization, middle-mineralization, and late-mineralization. Each relevant entry includes data module type, geological response signal type, geological process type, and mineralization stage. The related items are grouped according to the mineralization stage, forming the pre-mineralization related group, the mid-mineralization related group, and the post-mineralization related group. The entries of the pre-mineralization associated group are processed to extract the geological response signal type and associated geological process type of each data module in the pre-mineralization stage, and a first correspondence table is generated. Based on the first correspondence table, a mapping sub-relationship for the pre-mineralization stage is constructed. This mapping sub-relationship determines the correspondence between the stratigraphic sequence change signal and fold morphology signal of the geological structure data module and the migration of magmatic activity materials and the accumulation of sedimentary environment materials, respectively. It also determines the correspondence between the element content change signal and element combination signal of the geochemical data module and the migration of magmatic activity materials and the accumulation of sedimentary environment materials, respectively. The entries of the mid-mineralization correlation group are processed to extract the geological response signal type and associated geological process type corresponding to each data module in the mid-mineralization period, and a second correspondence table is generated. Based on the second correspondence table, a mapping sub-relationship for the mid-stage of mineralization is constructed. This sub-relationship determines the correspondence between the fault activity signal and the tectonic stress energy release effect of the geological structure data module, the correspondence between the isotope ratio signal and the hydrothermal activity energy transfer effect of the geochemical data module, and the correspondence between the magnetic field change signal and the resistivity change signal of the geophysical data module and the tectonic stress energy release effect and the hydrothermal activity energy transfer effect, respectively. The entries of the late mineralization associated group are processed to extract the geological response signal type and associated geological process type corresponding to each data module in the late mineralization stage, and a third correspondence table is generated. Based on the third correspondence table, a mapping sub-relationship for the later stages of mineralization is constructed. This sub-relationship determines the correspondence between the resistivity change signal of the geophysical data module and the protective effect of wall rock alteration, determines the correspondence between the rock exposure signal and the linear structure signal of the remote sensing image data module and the protective effect of wall rock alteration and the solidification effect of ore body morphology, respectively, and determines the correspondence between the stratigraphic sequence change signal of the geological structure data module and the solidification effect of ore body morphology. By comparing the correspondence between data modules, geological response signals, and geological processes in the mapping sub-relationships of each stage, adjustments are made to ensure that the same geological response signal of the same data module corresponds to only one geological process type in the mapping sub-relationships of different stages. Arrange the sub-relationships of each stage according to the ore-forming time sequence to form a sequence of stage sub-relationships, which serves as a component of the dynamic mapping relationship.

8. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 3, characterized in that, The process of connecting the starting node and the geochemical data module node through a first interaction relationship, and recording the coordinated variation patterns of stratigraphic sequence variation signals and elemental abundance variation signals along the connection path, includes: The relationship description of the first interaction relationship is extracted from the mapping sub-relationship of the pre-mineralization stage of the dynamic mapping relationship. This relationship description includes the evolutionary hierarchical division of the stratigraphic sequence change signal and the corresponding elemental content change characteristics. The stratigraphic sequence change signal is divided into multiple evolutionary levels according to the formation age, and each evolutionary level corresponds to a geological time interval. For each evolution level, feature descriptions of the element content change signals corresponding to that evolution level are extracted to determine the correspondence between the evolution level and the element content change features. Record the correspondence between each stratigraphic sequence evolution level and the corresponding element content variation characteristics to form a synergistic variation table; The collaborative change table is converted into collaborative change pattern text that can be labeled on the connection path; Set up pattern annotation nodes on the connection path corresponding to the first interaction relationship, and embed the text of the cooperative change pattern into the annotation nodes; The annotation node is positioned in the middle of the connection path between the starting node and the geochemical data module node, and the annotation node maintains a visual connection with the starting node and the geochemical data module node. By comparing the stratigraphic division, element content variation characteristics description and dynamic mapping relationship in the text of the coordinated change law, the pre-mineralization correlation law was obtained by adjusting the text content to conform to the pre-mineralization correlation law. After completing the annotation node settings, check the connection status of the starting node, the first connection path, and the geochemical data module nodes to ensure that the interaction between data module nodes is fully reflected through the connection paths and the coordinated change patterns of the annotations.

9. The intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscientific data according to claim 4, characterized in that, The spatial distribution information of the geological structure candidate dataset is compared with the spatial distribution information of the geochemical first candidate dataset using geographic coordinates. Geological structure data and geochemical data with overlapping geographic coordinates and matching attribute information are retained and combined to form the first cross-dataset, including: Extract the spatial distribution information corresponding to each data entry in the candidate dataset of geological structures. The spatial distribution information is stored in the form of vertex coordinate sequence of geographic coordinate polygons, with each data entry corresponding to a coordinate polygon. The spatial distribution information corresponding to each data entry in the first candidate geochemical dataset is extracted and stored in the form of vertex coordinate sequence of geographic coordinate polygons, with each data entry corresponding to a coordinate polygon. Select the first data entry in the candidate dataset of geological structures, obtain the vertex coordinate sequence of its coordinate polygon, and determine the geographic coordinate range covered by the coordinate polygon. Traverse all data entries in the first candidate geochemical dataset and obtain the geographic coordinate range covered by the coordinate polygon of each entry; Determine whether there is any overlap between the coordinate range of the first candidate geochemical data entry and the coordinate range of the geological structure data entry; If overlapping areas exist, further examine whether the stratigraphic sequence variation signal of the geological structural data entry meets the first matching standard, and whether the elemental content variation signal of the geochemical data entry meets the first matching standard; If both attribute information meets the first matching criterion, the two data entries are combined into a cross data pair. Select the next data entry from the geological structure candidate dataset and repeat the above steps of determining the coordinate range, comparing the coordinate range, checking the attribute information, and filtering the cross data pairs. This process continues until all data entries in the geological structure candidate dataset have been compared with the first geochemical candidate dataset. Collect all selected cross data pairs. Each cross data pair contains stratigraphic sequence variation signals and coordinate polygons for geological structural data entries and elemental content variation signals and coordinate polygons for geochemical data entries. The collected cross data pairs are deduplicated. If different cross data pairs contain the same geological structure data entries and the same geochemical data entries, only one cross data pair is retained. The deduplicated cross data pairs are integrated to form the first cross dataset. The dataset is organized in tabular form and includes fields such as geological structure data ID, geochemical data ID, coordinates of overlapping areas, stratigraphic sequence variation signal, and elemental content variation signal.

10. A smart delineation system for mineral target areas based on multi-source heterogeneous geoscientific data, characterized in that, The method includes a processor and a readable storage medium storing a program that, when executed by the processor, implements the intelligent delineation method for mineral target areas based on multi-source heterogeneous geoscience data as described in any one of claims 1-9.

Images