Copper mine target area prediction method and system based on multi-source information data analysis

Abstract

The application provides a copper mine target area prediction method and system based on multi-source information data analysis, and relates to the technical field of computers. First, multi-source copper mine related basic information such as surface rock outcrop records, soil element content data, regional gravity observation data, remote sensing image feature data and geological structure surveying and mapping data of a target area is collected. Then, clue tracing mapping processing is performed on the multi-source basic information to generate a plurality of sets of clue tracing sets. Then, the plurality of sets of clue tracing sets are subjected to spatio-temporal coupling networking processing to construct a dynamic coupling clue network. Then, signal resonance enhancement processing is performed on the dynamic coupling clue network to generate a resonance enhancement network. Finally, target area convergence definition processing is performed based on the resonance enhancement network to generate a copper mine target area prediction result, gradually narrowing the range of mineralization potential areas, and the generated target area copper mine target area prediction result has higher accuracy and reliability, can effectively guide copper mine exploration work, improve exploration efficiency and success rate, and reduce exploration cost.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method and system for predicting copper mine target areas based on multi-source information data analysis. Background Technology

[0002] In the field of copper exploration, accurate prediction of copper target areas is crucial for improving exploration efficiency, reducing exploration costs, and discovering new copper resources. Currently, traditional methods for predicting copper target areas mainly rely on the analysis of a single information source or a few relevant pieces of information. For example, some methods rely solely on geological structural mapping data and human experience to determine the relationship between geological structures and mineralization. However, these methods are limited by the subjective experience and knowledge of geologists, making it difficult to comprehensively and accurately grasp the mineralization patterns. Other methods utilize soil element content data and use simple statistical analysis to delineate potential mineralization areas. However, soil element content is influenced by various factors, and relying solely on this data is insufficient to accurately reflect the mineralization of deep copper deposits. Furthermore, while remote sensing imagery can provide extensive surface information, its ability to predict deep copper deposits is limited when used alone. These existing methods, lacking comprehensive utilization and in-depth analysis of multi-source information, fail to fully consider the inherent connections and spatiotemporal evolution patterns between various information sources, resulting in low accuracy and reliability in copper target area prediction, and thus failing to meet the needs of modern copper exploration. Summary of the Invention

[0003] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for predicting copper ore target areas based on multi-source information data analysis, the method comprising:

[0004] Collect readily available basic information on multi-source copper deposits in the target area. This basic information includes surface rock outcrop records, soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data.

[0005] Perform source tracing mapping processing on the multi-source copper ore related basic information to trace the original source of the copper ore mineralization in each type of basic information and generate multiple sets of source tracing clues.

[0006] The multiple sets of tracing clues are subjected to spatiotemporal coupling networking processing, and a dynamic coupled clue network is constructed by combining the spatial location of the tracing clues with the mineralization time series.

[0007] The dynamic coupling clue network is subjected to signal resonance enhancement processing. Through the ore-forming logic resonance effect between the source clues, the expression of ore-forming related signals is enhanced, and a resonance enhancement network is generated.

[0008] Based on the signal distribution and coupling relationship in the resonant enhancement network, target area convergence and delineation processing is performed to gradually narrow down the range of mineralization potential areas and generate copper ore target area prediction results for the target area.

[0009] Furthermore, embodiments of the present invention also provide a copper ore target area prediction system based on multi-source information data analysis, comprising:

[0010] A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the aforementioned copper ore target area prediction method based on multi-source information data analysis by executing the machine-executable instructions.

[0011] In another aspect, embodiments of the present invention also provide a computer program product, the computer program product including machine-executable instructions, the machine-executable instructions being stored in a computer-readable storage medium, a processor of a computer device reading the machine-executable instructions from the computer-readable storage medium, the processor executing the machine-executable instructions, causing the computer device to execute the aforementioned copper ore target area prediction method based on multi-source information data analysis.

[0012] Based on the above, by collecting readily available multi-source copper deposit-related basic information from the target area, including surface rock outcrop records, soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data, various types of information related to copper mineralization are integrated. This multi-source basic information undergoes source tracing mapping processing to trace the original source of copper mineralization in each type of information, generating multiple sets of source tracing clues. This allows for in-depth exploration of the mineralization essence behind the information. Furthermore, the multiple sets of source tracing clues are spatiotemporally coupled and networked, constructing a dynamic coupling line by combining spatial location and mineralization time series. The ore-forming network fully considers the dynamic changes of the mineralization process in time and space. It performs signal resonance enhancement processing on the dynamically coupled clue network, and strengthens the expression of mineralization-related signals by utilizing the mineralization logic resonance effect between the trace clues. This generates a resonance enhancement network, which further highlights the key information of mineralization. Finally, based on the signal distribution and coupling relationship in the resonance enhancement network, it performs target area convergence and delineation processing to gradually narrow down the range of mineralization potential areas. The generated target area copper ore target area prediction results have higher accuracy and reliability, which can effectively guide copper ore exploration work, improve exploration efficiency and success rate, and reduce exploration costs. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the execution flow of the copper mine target area prediction method based on multi-source information data analysis provided in the embodiments of the present invention.

[0014] Figure 2This is a schematic diagram of exemplary hardware and software components of a copper mine target area prediction system based on multi-source information data analysis provided in an embodiment of the present invention. Detailed Implementation

[0015] Figure 1 This is a flowchart illustrating a copper mine target area prediction method based on multi-source information data analysis provided in one embodiment of the present invention, which will be described in detail below.

[0016] Step S110: Collect readily available basic information related to multi-source copper deposits in the target area. The basic information related to multi-source copper deposits includes surface rock outcrop records, soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data.

[0017] In this embodiment, taking the prediction of a copper ore target area in a certain target region as an example, the collection of basic information related to multi-source copper ore is initiated. For surface rock outcrop records, information on rock outcrops at different locations in the region is collected through field geological surveys, including detailed descriptions of rock type, color, structure, texture, and occurrence status. The specific geographical location information of each outcrop, such as latitude and longitude coordinates, is also recorded. Soil element content data is obtained by sampling soil in the region according to a set grid layout. The sampling depth is determined based on the regional geological conditions. Laboratory chemical analysis is performed on the collected soil samples to obtain the content data of various elements, including copper and other associated elements related to copper mineralization. The spatial coordinates and sampling depth of each sampling point are recorded. Regional gravity observation data is obtained by systematically measuring gravity in the region using a gravimeter. The gravity values ​​at different observation points, observation time, and environmental conditions during observation, such as temperature and humidity, are recorded, along with the precise coordinates of each observation point. Remote sensing image feature data was acquired using high-resolution satellite remote sensing technology to obtain images of the region. Preliminary interpretation of the images was performed to extract tonal, textural, and spatial distribution features, while also marking anomalous areas such as tonal and textural anomalies. Geological structural mapping data was obtained through geological mapping and other methods, recording the types of geological structures in the region, such as folds, faults, and joints. The data describes the scale, occurrence, spatial distribution, and relationships between these structures, and also collects information on the tectonic evolution of the region.

[0018] Step S120: Perform source tracing mapping processing on the multi-source copper ore related basic information, trace the original source of the copper ore mineralization in each type of basic information, and generate multiple sets of source tracing clues.

[0019] After obtaining the aforementioned basic information related to multiple copper deposits, the next step is to perform source tracing and mapping processing on this information. Taking surface rock outcrop records as an example, it is necessary to trace the original sources of clues related to copper mineralization from these records. First, the rock type is analyzed to determine whether it belongs to a rock type related to copper mineralization, such as porphyry and volcanic rocks in igneous rocks, or copper-bearing shale in sedimentary rocks. For mineral composition records, it is necessary to identify whether they contain copper minerals and indicator minerals related to copper mineralization, such as pyrite and chalcopyrite, and analyze the formation environment and genesis of these minerals. In terms of structural features, it is necessary to observe whether the rocks have mineralization-related structures, such as fracture zones and fissures, which may provide space and channels for copper mineralization. Through comprehensive analysis of the above information, the original sources of clues related to copper mineralization in each type of basic information are traced.

[0020] Step S121: Decompose the surface rock outcrop record into rock type description, mineral composition record, structural features and outcrop spatial location information to generate a basic rock outcrop dataset, which is a structured representation of the surface rock outcrop record.

[0021] When performing source mapping on surface rock outcrop records, the first step is decomposition. The collected surface rock outcrop records are broken down according to rock type description, mineral composition record, structural features, and outcrop spatial location information. For example, for a particular rock outcrop, the rock type description might be "gray medium-grained diorite," the mineral composition record might include "approximately 50% plagioclase, approximately 30% amphibole, and a small amount of pyrite," the structural features might be "massive structure, medium-grained subhedral granular texture," and the outcrop spatial location information would be its latitude and longitude coordinates. These pieces of information are extracted and organized according to a predefined format to form a structured basic dataset of rock outcrops, enabling subsequent processing to be more organized and efficient.

[0022] Step S122: For the basic dataset of rock outcrops, define the clue tracing dimensions, which include mineral genesis tracing, rock formation environment tracing, and tectonic influence tracing.

[0023] After generating the basic dataset of rock outcrops, it is necessary to define clue tracing dimensions. The mineralogical tracing dimension focuses on the formation causes and processes of minerals in rocks. By analyzing the types, combinations, and structures of minerals, it traces the geological conditions and evolutionary processes of their formation to determine whether they are related to copper mineralization. The rock formation environment tracing dimension focuses on studying the physicochemical conditions and geological environment during rock formation, such as temperature, pressure, and medium composition. These environmental factors have a significant impact on copper mineralization. The tectonic influence tracing dimension mainly considers the impact of tectonic movements on rock outcrops, including rock deformation and fracturing caused by tectonic activity, as well as providing channels for ore-forming fluids and ore-bearing space. By defining these three clue tracing dimensions, it is possible to comprehensively mine clues related to copper mineralization from the basic dataset of rock outcrops.

[0024] Step S123: Based on the mineral evolution records related to copper mineralization, construct a mineral genesis tracing path. Along the mineral genesis tracing path, extract mineral genesis tracing clues related to copper mineralization from the rock outcrop basic dataset, and label the relevant content of the formation of each mineral and the associated path of copper mineralization.

[0025] From the mineral evolution records related to copper mineralization, mineral assemblages and evolutionary sequences at different mineralization stages are obtained. For example, in the early stages of copper mineralization, some high-temperature mineral assemblages may form, while as the mineralization process progresses and the temperature gradually decreases, some low-temperature mineral assemblages will form. Based on the above mineral evolution records, a mineral genesis tracing path from early to late stages is constructed. Then, along this path, records related to these mineral assemblages are searched in the basic dataset of rock outcrops. For example, when mineral assemblages such as chalcopyrite and pyrite are found in a rock outcrop, based on the mineral genesis tracing path, it is determined that these minerals may have formed at a certain stage of copper mineralization, and the correlation path between the formation of these minerals and copper mineralization is marked, such as these minerals being formed under the action of ore-forming fluids and specific temperature and pressure conditions, which is related to the main mineralization stage of copper ore.

[0026] For example, step S1231: Separate the primary mineral assemblage record and the secondary mineral assemblage record from the mineral evolution record of copper ore formation. Based on the primary mineral assemblage record, arrange the crystallization sequence of primary minerals from the early high temperature stage to the late low temperature stage to generate the primary mineral crystallization sequence. Based on the secondary mineral assemblage record, arrange the alteration and superposition sequence of secondary minerals under surface conditions to generate the secondary mineral alteration sequence.

[0027] When constructing the mineral genesis tracing path, the first step is to process the mineral evolution records related to copper mineralization. This involves separating the primary mineral assemblages from the secondary mineral assemblages. For the primary mineral assemblages, the types of minerals formed under different temperature conditions are analyzed. The crystallization sequence of these primary minerals is arranged from the early high-temperature stage to the late low-temperature stage. For example, in the early high-temperature stage, olivine may crystallize first, followed by pyroxene. As the temperature decreases, plagioclase and other minerals may crystallize sequentially, thus generating a primary mineral crystallization sequence. For the secondary mineral assemblages, the process of primary minerals undergoing alteration to form secondary minerals under surface conditions is studied. The sequence of secondary minerals is arranged according to the order and superposition of alteration. For example, primary pyrite may first alter to limonite, and then further alter to hematite, generating a secondary mineral alteration sequence.

[0028] Step S1232: Extract all mineral names from the mineral composition record of the rock outcrop basic dataset, compare the extracted mineral names with the minerals in the primary mineral crystallization sequence, and identify the minerals belonging to the primary mineral crystallization sequence; compare the extracted mineral names with the minerals in the secondary mineral alteration sequence, and identify the minerals belonging to the secondary mineral alteration sequence.

[0029] From the mineral composition record portion of the rock outcrop's basic dataset, all mineral names are extracted. For example, the mineral composition record of a rock outcrop might contain names such as pyrite, chalcopyrite, plagioclase, and amphibole. These mineral names are then compared one by one with the minerals in the previously generated primary mineral crystallization sequence and secondary mineral alteration sequence. If a mineral name appears in the primary mineral crystallization sequence, it is identified as a mineral belonging to the primary mineral crystallization sequence; if it appears in the secondary mineral alteration sequence, it is identified as a mineral belonging to the secondary mineral alteration sequence. Through this method, mineral types related to copper mineralization can be preliminarily screened.

[0030] Step S1233: For the minerals identified as belonging to the primary mineral crystallization sequence, locate the position of the mineral in the primary mineral crystallization sequence and record the preceding and succeeding minerals at that position; for the minerals identified as belonging to the secondary mineral alteration sequence, locate the specific position of the mineral in the secondary mineral alteration sequence and record the alteration stage indicated by that position and the original parent mineral.

[0031] For minerals identified as belonging to the primary mineral crystallization sequence, their corresponding positions are located within that sequence. For example, if the primary mineral crystallization sequence is olivine-pyroxene-platinum-quartz, and the identified mineral is pyroxene, then its position is after olivine and before plagioclase; its preceding mineral is recorded as olivine, and its succeeding mineral as plagioclase. For minerals belonging to the secondary mineral alteration sequence, such as limonite, their positions are located within the secondary mineral alteration sequence to determine their alteration stage, such as the early alteration stage, and their original parent mineral is recorded as pyrite. This information is crucial for tracing the genesis and evolution of minerals.

[0032] Step S1234: Combining the specific positions of primary minerals in the primary mineral crystallization sequence and secondary minerals in the secondary mineral alteration sequence, arrange the complete generation order of all minerals in the rock outcrop basic dataset. Based on the complete generation order, identify the symbiotic and repulsive relationships between mineral assemblages, generate mineral symbiotic assemblage rules, and use the mineral symbiotic assemblage rules to check the rationality of the mineral composition in the rock outcrop basic dataset and mark mineral anomalies that do not conform to the mineral symbiotic assemblage rules.

[0033] Based on the positions of primary minerals in their crystallization sequence and secondary minerals in their alteration sequence, all minerals in the rock outcrop dataset are arranged in chronological order of formation, resulting in a complete generation sequence. For example, olivine, a primary mineral, forms first, followed by pyroxene, and then limonite, a secondary mineral. Based on this complete generation sequence, the symbiotic and repulsive relationships between different minerals are analyzed. Symbiotic relationships refer to mineral assemblages that can form simultaneously under the same geological conditions, while repulsive relationships refer to minerals that cannot coexist under the same conditions. Mineral symbiotic assemblage rules are generated based on these relationships; for example, olivine and quartz typically do not coexist. These rules are then used to check the rationality of the mineral composition in the rock outcrop dataset. If mineral assemblages that do not conform to the symbiotic assemblage rules are found, such as the simultaneous occurrence of olivine and quartz, they are marked as mineral anomalies.

[0034] Step S1235: Referring to the specific spatial zoning patterns of minerals during the copper ore formation process, the complete generation sequence is mapped to the spatial distribution prediction of minerals, thereby generating a mineral spatial zoning pattern.

[0035] During copper mineralization, different minerals often exhibit certain spatial zoning patterns. For example, the central part of an ore body may be dominated by chalcopyrite, gradually transitioning to pyrite towards the outside, and further outwards, other alteration minerals may appear. Referring to these specific mineral spatial zoning patterns, and combining previously obtained complete mineral formation sequence information with spatial location information, the spatial distribution of different minerals can be predicted. For example, early-formed high-temperature minerals may be distributed in the deeper parts of the ore body, while later-formed low-temperature minerals may be distributed in the shallower parts or edges of the ore body, thus generating a mineral spatial zoning pattern.

[0036] Step S1236: Integrate the primary mineral crystallization sequence, secondary mineral alteration sequence, complete formation sequence, mineral symbiotic assemblage rules, and mineral spatial zoning patterns to construct a mineral genesis tracing path. Along the mineral genesis tracing path, extract mineral assemblages that conform to the mineral symbiotic assemblage rules from the rock outcrop basic dataset as mineral genesis tracing clues. Mark the complete formation sequence stage, the position of the primary mineral crystallization sequence or the position of the secondary mineral alteration sequence to which each mineral belongs, and the spatial position of the mineral in the metallogenic system inferred from the mineral spatial zoning pattern. Complete the annotation of the relevant content of the association path between the formation of each mineral and copper mineralization.

[0037] By integrating primary mineral crystallization sequences, secondary mineral alteration sequences, complete formation sequences, mineral assemblages, and mineral spatial zoning patterns, a complete mineralogical genetic tracing path is formed. Along this path, mineral assemblages conforming to the mineral assemblages rules are selected from the rock outcrop dataset; these assemblages constitute the mineralogical genetic tracing clues. For each mineral in each mineralogical genetic tracing clue, its stage in the complete formation sequence (e.g., early, middle, or late); its position in the primary mineral crystallization sequence or secondary mineral alteration sequence; and its spatial position in the metallogenic system inferred from the mineral spatial zoning pattern (e.g., ore body center, edge, or transition zone) are labeled. These labels demonstrate the correlation between the formation of each mineral and copper mineralization.

[0038] Step S124: Combine regional geological evolution records to construct a rock formation environment tracing path. Based on the rock formation environment tracing path, select rock formation environment tracing clues that reflect favorable mineralization environments from the rock outcrop basic dataset, and label the geological evolution stage related content corresponding to each tracing clue.

[0039] Collect relevant records of regional geological evolution in the target area, including information on the region's geological history, tectonic movements, sedimentation, and magmatic activity. Analyze these records to understand the environmental characteristics of different geological periods, such as paleogeography, paleoclimate, and paleotectonics. Based on the above information, construct a source path for rock formation environments, reflecting the evolution of these environments. Then, based on this path, select rock records from the basic rock outcrop dataset that reflect favorable mineralization environments. For example, the formation environments of certain sedimentary rocks may have provided favorable conditions for the sedimentary mineralization of copper deposits, or the formation environments of certain igneous rocks may be closely related to the magmatic-hydrothermal mineralization of copper deposits. For these selected source path clues for rock formation environments, label their corresponding geological evolution stages, such as a specific geological age or tectonic movement period.

[0040] For example, step S1241: Extract sedimentary formation sequence records, magmatic activity sequence records, and metamorphic sequence records from the relevant records of regional geological evolution. Based on the sedimentary formation sequence records, arrange the lithofacies assemblages and sedimentary facies types of sedimentary rocks in different periods to generate a sedimentary environment evolution sequence. Based on the magmatic activity sequence records, arrange the rock type assemblages and intrusion or eruption modes of magmatic rocks in different periods to generate a magmatic activity environment sequence. Based on the metamorphic sequence records, arrange the mineral assemblages and metamorphic facies types of different metamorphic zones to generate a metamorphic environment sequence.

[0041] When constructing a path for tracing the origins of rock formation environments, the first step is to process relevant records of regional geological evolution. Separate the sedimentary formation sequence records, magmatic activity sequence records, and metamorphic sequence records. For the sedimentary formation sequence records, the lithofacies assemblages and sedimentary facies types of sedimentary rocks formed in different geological periods are analyzed, such as fluvial, lacustrine, and deep-sea facies, and arranged chronologically to generate a sedimentary environment evolution sequence. Based on the magmatic activity sequence records, the lithofacies assemblages of magmatic rocks from different periods are determined, such as basalt and granite, as well as their intrusion or eruption modes, such as central eruptions and fissure eruptions, and this information is arranged to generate a magmatic activity environment sequence. For the metamorphic sequence records, the mineral assemblages and metamorphic facies types of different metamorphic zones are studied, such as greenschist and amphibolite facies, and arranged according to the degree of metamorphism to generate a metamorphic environment sequence.

[0042] Step S1242: From the rock type descriptions and structural features of the rock outcrop basic dataset, determine the major category and specific lithology of the rocks; match the determined sedimentary rock lithology with the sedimentary environment evolution sequence to determine the specific sedimentary facies type and period position of the sedimentary rock formation in the sedimentary environment evolution sequence; match the determined igneous rock lithology with the magmatic activity environment sequence to determine the specific magmatic activity environment of the igneous rock formation and the period position in the magmatic activity environment sequence; match the determined metamorphic rock lithology with the metamorphic environment sequence to determine the specific metamorphic zone of the metamorphic rock formation and the stage position in the metamorphic environment sequence.

[0043] From the rock type descriptions and structural features in the basic dataset of rock outcrops, we determine whether a rock belongs to a major category such as sedimentary, igneous, or metamorphic rocks, and then identify its specific lithology. For example, based on the rock's structural features and mineral composition, we identify a rock as sandstone, belonging to the sedimentary rock category. Then, we compare the identified sedimentary rock lithology with the sedimentary environment evolution sequence to find the matching sedimentary facies type; for example, the sandstone may belong to fluvial facies deposits. We then determine its chronological position in the sedimentary environment evolution sequence, such as the fluvial depositional stage in a certain geological era. A similar method is used for igneous and metamorphic rocks, matching them with magmatic activity environment sequences and metamorphic environment sequences, respectively, to determine their specific formation environments and positions within the corresponding sequences.

[0044] Step S1243: Based on the time locations determined in the sedimentary environment evolution sequence, the phase locations determined in the magmatic activity environment sequence, and the stage locations determined in the metamorphic environment sequence, outline the paleogeographic pattern changes of the target area within the time frame of the relevant records of regional geological evolution, and analyze the tectonic sedimentary basin boundaries, syn-sedimentary fault locations, and volcanic activity centers related to copper mineralization in the paleogeographic pattern changes.

[0045] By integrating the chronological locations identified in the sedimentary environment evolution sequence, the phase locations identified in the magmatic activity environment sequence, and the stage locations identified in the metamorphic environment sequence, and combining this with the time frame of regional geological evolution, the paleogeographic pattern of the target region in different geological periods can be depicted. For example, at a certain period, the region may have been a vast ocean, gradually rising to form land with geological evolution, during which it underwent multiple sedimentary, magmatic, and metamorphic processes. In the process of paleogeographic pattern changes, the boundaries of tectonic sedimentary basins related to copper mineralization can be analyzed; these basins may have provided sites for copper deposition; syn-sedimentary fault locations may have provided channels for the migration of ore-forming fluids; and volcanic activity centers may have brought ore-forming materials and heat.

[0046] Step S1244: Based on the boundaries of tectonic sedimentary basins, the location of syn-sedimentary faults, and the center of volcanic activity, delineate the spatial range of favorable mineralization environments in the changes of paleogeographic patterns. Spatially overlay the delineated favorable mineralization environment spatial range with the outcrop spatial location information of the basic dataset of rock outcrops, identify rock outcrop records whose outcrop spatial location information falls within the favorable mineralization environment spatial range, and extract the rock type description and structural features corresponding to the identified rock outcrop records as clues to the origin of the rock formation environment reflecting the favorable mineralization environment.

[0047] Based on the established boundaries of tectonic-sedimentary basins, the locations of syn-sedimentary faults, and centers of volcanic activity, the spatial extent of favorable mineralization environments is delineated on paleogeographic maps. For example, the areas within tectonic-sedimentary basins, near syn-sedimentary faults, and around centers of volcanic activity are defined as favorable mineralization environments. Then, spatial overlay analysis is performed between these spatial extents and the outcrop spatial location information in the basic rock outcrop dataset to identify rock outcrop records whose spatial locations fall within the favorable mineralization environment range. The rock type descriptions and structural features of these rock outcrop records, such as lithofacies characteristics of sedimentary rocks and intrusive characteristics of igneous rocks, are extracted as clues to the provenance of the rock formation environment reflecting the favorable mineralization environment.

[0048] Step S1245: Mark the specific sedimentary facies type and period location, or the specific magmatic activity environment and period location, or the specific metamorphic zone and stage location corresponding to each rock formation environment tracing clue, as well as the specific mineralization favorable environment type in the paleogeographic pattern change indicated by the rock formation environment tracing clue, and complete the marking of the relevant content of the geological evolution stage corresponding to each tracing clue.

[0049] For each lithological origin clue, based on previous matching results, the specific sedimentary facies type and its position in the sedimentary environment evolution sequence are labeled, such as fluvial sedimentary deposits belonging to a certain geological age; or the specific magmatic activity environment and its position in the magmatic activity environment sequence, such as a central eruptive environment belonging to a certain period of magmatic activity; or the specific metamorphic zone and its stage position in the metamorphic environment sequence, such as a greenschist metamorphic zone belonging to an early metamorphic stage. Simultaneously, the specific mineralization-favorable environment type in the paleogeographic pattern changes indicated by the origin clue is labeled, such as tectonic sedimentary basin environment, volcanic activity center environment, etc., thus completing the labeling of the relevant content of the geological evolution stage corresponding to each origin clue.

[0050] Step S125: Referring to the relevant data on the impact of tectonic movement on copper mineralization, construct a tectonic influence tracing path. Through the tectonic influence tracing path, extract the tectonic association tracing clues formed by the tectonic movement from the basic dataset of rock outcrops, and mark the corresponding content of the tectonic movement and the formation of the tracing clues.

[0051] Data on the impact of tectonic movements on copper mineralization were collected, including information on the type, intensity, timing, and alteration of rocks and ore bodies. Based on this data, a tectonic influence tracing path was constructed, reflecting how tectonic movements influenced the formation and distribution of copper deposits. Then, using this path, tectonic features such as folds, faults, and joints, formed by tectonic movements, were identified from the basic rock outcrop dataset. These features may have provided space, pathways, or alteration conditions for copper mineralization and were therefore used as tectonic correlation tracing clues. For each tectonic correlation tracing clue, the type, timing, and intensity of the corresponding tectonic movement were labeled to clarify the correspondence between the tectonic movement and the tracing clue.

[0052] For example, step S1251: Extract the records of tectonic deformation patterns, tectonic stress field directions, and tectonic activity periods from the data related to the influence of tectonic movements on copper mineralization. Based on the records of tectonic deformation patterns, summarize the development characteristics of fold types, fracture properties, and joint systems in different tectonic stages to generate a sequence of tectonic pattern evolution. Based on the records of tectonic stress field directions, restore the orientation changes of principal stress axes in different tectonic stages to generate a sequence of tectonic stress field direction evolution. Based on the records of tectonic activity periods, divide the chronological order and superimposed transformation relationship of tectonic events to generate a sequence of tectonic activity periods.

[0053] When constructing the tectonic influence tracing path, the first step is to extract tectonic deformation pattern records, tectonic stress field direction records, and tectonic activity period records from data related to the impact of tectonic movements on copper mineralization. For the tectonic deformation pattern records, the types of folds appearing in different tectonic stages, such as anticlines and synclines, the nature of faults, such as normal faults and reverse faults, and the development characteristics of joint systems, such as joint strike and density, are analyzed. The changes of these characteristics over time are summarized to generate a tectonic pattern evolution sequence. Based on the tectonic stress field direction records, geomechanical analysis methods are used to reconstruct the orientation changes of principal stress axes in different tectonic stages, such as the direction of maximum and minimum principal stress, generating a tectonic stress field direction evolution sequence. Based on the tectonic activity period records, the chronological order of different tectonic events and their superimposed and altering relationships are determined, such as early folds being cut by later faults, generating a tectonic activity period sequence.

[0054] Step S1252: From the structural features of the rock outcrop basic dataset, identify structural traces at the microscopic and outcrop scales. Compare the identified structural traces with the structural style evolution sequence to determine the structural style type to which the structural trace belongs and its stage in the structural style evolution sequence. Compare the geometric shape of the identified structural trace with the evolution sequence of the structural stress field direction to invert the paleostress direction of the structural trace and determine the stage to which the paleostress direction belongs in the evolution sequence of the structural stress field direction.

[0055] From the structural and tectonic feature descriptions in the basic dataset of rock outcrops, microscopic structural features are identified, such as the orientation of minerals and crystal deformation, as well as outcrop-scale structural features, such as the morphology of folds and the attitude of faults. These structural features are compared with the structural style evolution sequence to determine their structural style type. For example, if a fold belongs to a box-shaped anticline, its stage in the structural style evolution sequence is determined, such as belonging to the early tectonic stage. Simultaneously, based on the geometric morphology of the structural features, such as the axial plane strike of folds and the strike and dip angle of faults, combined with the evolution sequence of tectonic stress field directions, the paleostress direction at the time of the structural feature's formation can be inverted. For example, based on the attitude and movement direction of reverse faults, the principal compressive stress direction at that time can be inverted, and the stage to which this paleostress direction belongs in the evolution sequence of tectonic stress field directions can be determined.

[0056] Step S1253: Compare the stage of the tectonic trace in the tectonic style evolution sequence with the stage it belongs to in the tectonic stress field direction evolution sequence to confirm the consistency of the stages, thereby anchoring the tectonic trace to a specific tectonic event in the tectonic activity period sequence.

[0057] By comparing the stage of a tectonic feature in the tectonic style evolution sequence with its corresponding stage in the tectonic stress field direction evolution sequence, if the two stages are consistent, it indicates that the formation of the tectonic feature is consistent with the tectonic movement and stress field conditions of that stage. Based on this, the tectonic feature is anchored to a specific tectonic event in the tectonic activity period sequence. For example, if a tectonic feature belongs to the middle stage in both the tectonic style evolution sequence and the tectonic stress field direction evolution sequence, then it can be anchored to a middle-stage tectonic event in the tectonic activity period sequence.

[0058] Step S1254: Based on the sequence of tectonic activity periods, arrange the intensity and superposition of the alteration effect of different tectonic events on early existing rocks or ore bodies, analyze the intensity and superposition of the alteration effect of tectonic events on early existing rocks or ore bodies, and classify the types of tectonic expansion space that are conducive to the placement of copper deposits and the types of tectonic destruction that are unfavorable to the preservation of copper deposits.

[0059] Based on the sequence of tectonic activity periods, we understand the order and characteristics of different tectonic events. We analyze the intensity of each tectonic event's alteration of pre-existing rocks or ore bodies; for example, strong compression may lead to rock fracturing, while tension may create fractures. Simultaneously, we study the superposition of tectonic events on early rocks or ore bodies, such as later fractures cutting through earlier folds. Based on the above analysis, we classify tectonic expansion spaces favorable for copper ore placement, such as fracture zones formed by extensional fractures and delamination spaces formed by folds, which provide sites for copper precipitation and enrichment; and tectonic destructive processes unfavorable for copper ore preservation, such as strong shearing that may lead to ore body fragmentation and dispersion.

[0060] Step S1255: From the rock type description, mineral composition record and structural features of the rock outcrop basic dataset, look for evidence indicating the existence of tectonic expansion space and evidence indicating the occurrence of tectonic destruction. Correlate the evidence indicating the existence of tectonic expansion space with tectonic events in the tectonic activity sequence that are conducive to the placement of copper deposits, and correlate the evidence indicating the occurrence of tectonic destruction with tectonic events in the tectonic activity sequence that are unfavorable to the preservation of copper deposits.

[0061] In the basic dataset of rock outcrops, we carefully searched for evidence indicating the existence of tectonic expansion spaces in rock type descriptions, mineral composition records, and structural features, such as well-developed fractures in rocks and breccias in breccia zones; and evidence indicating tectonic destruction, such as mineral fracturing and rock folding. We correlated the found evidence indicating the existence of tectonic expansion spaces with tectonic events in the sequence of tectonic activity that favored copper deposit placement, indicating that these expansion spaces were formed under the influence of these tectonic events. Similarly, we correlated the evidence indicating tectonic destruction with tectonic events that were detrimental to copper deposit preservation, indicating that these tectonic events damaged earlier rocks or ore bodies.

[0062] Step S1256: Extract rock type descriptions, mineral composition records, or structural features associated with tectonic events that facilitated the placement of copper deposits, as clues for tracing tectonic associations formed under the influence of tectonic movements.

[0063] From the rock outcrop records associated with tectonic events that facilitated copper deposit placement, we can extract rock type descriptions, such as breccia in fracture zones; mineral composition records, such as copper minerals filling fractures; and structural features, such as the distribution and density of fractures. This information can reflect the positive impact of tectonic movements on copper mineralization, and therefore serves as a clue for tracing the tectonic associations formed under the influence of tectonic movements.

[0064] Step S1257: Label the specific structural style type, the paleostress direction derived from the inversion, the name of the specific structural event to which each structural correlation trace clue corresponds, as well as the specific type of structural expansion space or structural damage indicated by the structural correlation trace clue, and complete the labeling of the relevant content on the correspondence between structural movement and the formation of trace clue.

[0065] For each tectonic correlation traceability clue, the specific tectonic style type is labeled, such as extensional fracture, fold collapse, etc.; the inverted paleostress direction is indicated, such as the direction of the maximum principal stress being north-south; the name of the specific tectonic event anchored is indicated, such as the Yanshanian tectonic movement; and the specific type of tectonic expansion space indicated by the traceability clue is indicated, such as fracture-type expansion space, or the specific type of tectonic destruction is indicated, such as shear destruction. These labels demonstrate the correspondence between tectonic movements and the formation of traceability clues.

[0066] Step S126: Integrate the mineral genesis traceability clues, rock formation environment traceability clues, and tectonic correlation traceability clues to generate a rock outcrop traceability clue group, which includes mineralization-related original clues in the surface rock outcrop record.

[0067] The previously extracted clues regarding mineral genesis, rock formation environment, and tectonic correlation were integrated. These clues were then categorized and organized, removing duplicate or redundant information to ensure each clue had a clear direction and relevance. The integrated clues were then combined to form a rock outcrop source clue group. This group contains original clues related to copper mineralization traced from surface rock outcrop records.

[0068] Step S127: Using the same clue tracing dimension definition, tracing path construction, and tracing clue extraction and integration method, perform clue tracing processing on the soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data respectively, to form soil element tracing clue group, gravity observation tracing clue group, remote sensing image tracing clue group, and geological structure tracing clue group in sequence.

[0069] For soil element content data, the following tracing dimensions are first defined: in addition to tracing mineral genesis, rock formation environment, and tectonic influences, an element migration tracing dimension is added. Then, corresponding tracing paths are constructed, extracting tracing clues related to copper mineralization in terms of element genesis, environment, tectonic influences, and migration from the soil element content data, and integrating them into a soil element tracing clue group. For regional gravity observation data, a similar tracing dimension and path construction method is used, focusing on extracting tracing clues related to the causes of gravity anomalies and environmental influences, forming a gravity observation tracing clue group. For remote sensing image feature data, an image feature evolution tracing dimension is added to the original dimensions, constructing a complete tracing path, extracting mineralization-related tracing clues in terms of tone, texture, spatial distribution, and feature evolution, and integrating them into a remote sensing image tracing clue group. For geological structural mapping data, the same tracing dimension definition principle is used to construct a set of structural tracing paths, extracting various structural tracing clues related to mineralization, generating a set of original geological structural tracing clues, which are then integrated and optimized to form a geological structural tracing clue group.

[0070] Step S1271: Decompose the soil element content data into element type records, element content value records, sampling point spatial coordinates and sampling depth information to generate a basic soil element dataset, which is a structured presentation of the soil element content data.

[0071] The collected soil element content data is broken down into the following parts: element type records (e.g., names of elements like copper, lead, and zinc); element content values ​​(the numerical content of each element in the soil sample); spatial coordinates of the sampling points (latitude and longitude of each soil sample collection point); and sampling depth information (the depth at which the soil sample was collected). This information is then organized according to a specific structure to form a basic soil element dataset, making the data more organized and facilitating subsequent traceability processing.

[0072] Step S1272: For the aforementioned soil element basic dataset, using the existing traceability dimensions of mineral genesis, rock formation environment, and tectonic influence, supplement the traceability dimension of element migration to generate a soil element traceability dimension set.

[0073] When tracing the origins of elements in the basic soil element dataset, in addition to the previously defined dimensions of mineral genesis, rock formation environment, and tectonic influence, a new dimension of element migration is added. This dimension focuses on the migration processes and mechanisms of elements in the soil, such as migration with groundwater and migration after absorption by plants. This is crucial for understanding the enrichment and dispersion of elements during copper mineralization. Combining these four dimensions generates a set of soil element origination dimensions.

[0074] Step S1273: Based on the element migration records related to copper ore formation, construct element migration source tracing paths, and combine existing mineral genesis source tracing paths, rock formation environment source tracing paths, and tectonic influence source tracing paths to generate a complete set of soil element source tracing paths.

[0075] Records of element migration during copper mineralization were collected to understand the migration patterns, directions, and influencing factors of copper and other associated elements under different geological conditions. Based on these records, source tracing pathways for element migration were constructed. Simultaneously, the mineralogical, lithogenetic, and tectonic influence source tracing pathways previously constructed for rock outcrop records were appropriately adjusted and expanded to suit the characteristics of soil element content data. Finally, these source tracing pathways were integrated to generate a complete set of soil element source tracing pathways.

[0076] Step S1274: Along the complete source tracing path set of soil elements, extract the source tracing clues of element genesis, element environmental source tracing clues, element structural influence source tracing clues, and element migration source tracing clues related to copper mineralization from the basic soil element dataset, and generate the original source tracing clue set of soil elements.

[0077] Clues are extracted from the basic soil element dataset according to each path in the complete set of soil element source tracing paths. Genetic source tracing clues focus on the origin of elements, such as weathering and decomposition of primary minerals or introduction by magmatic hydrothermal fluids; environmental source tracing clues reflect the environmental conditions during element formation, such as redox environments and pH levels; tectonic influence source tracing clues demonstrate the impact of tectonic movements on element distribution, such as the control of element migration by fault zones; and migration source tracing clues indicate the migration processes and patterns of elements in the soil. These extracted clues are combined to generate a set of original source tracing clues for soil elements.

[0078] Step S1275: Integrate the original source traceability clue set of soil elements to generate a soil element source traceability clue group.

[0079] The original source clues for soil elements were integrated and processed, removing duplicate information and merging similar clues to ensure accuracy and completeness. The integrated clues were then arranged in a logical order to form a soil element source clue group, which contains various original clues related to copper mineralization traced from soil element content data.

[0080] Step S1276: Decompose the regional gravity observation data into gravity numerical records, observation point coordinates, observation time information and observation environment records to generate a gravity observation basic dataset. Using the corresponding clue tracing dimensions and path construction method, extract the clues for tracing the causes of gravity anomalies and the clues for tracing the influence of gravity environment, and integrate them to form a gravity observation tracing clue group.

[0081] Regional gravity observation data is broken down into gravity numerical records (gravity measurements at different observation points), observation point coordinates (recording the location of each observation point), observation time information (describing the time of gravity measurement), and observation environment records (such as terrain and vegetation cover at the time of measurement). This data is then compiled into a basic gravity observation dataset. Next, following previous tracing dimensions such as rock formation environment and tectonic influence, corresponding tracing paths are constructed. Tracing clues for the causes of gravity anomalies are extracted from the basic gravity observation dataset, analyzing the reasons for gravity anomalies, such as the existence of underground ore bodies and differences in rock density. Tracing clues for the environmental influences of gravity are also extracted, considering the impact of environmental factors such as terrain and surface cover on gravity measurement results. These clues are then integrated to form a gravity observation tracing clue group.

[0082] Step S1277: Decompose the remote sensing image feature data into image tone features, texture features, spatial distribution features and anomaly area markers to generate a remote sensing image basic dataset. Based on the principle of defining the source tracing dimension, supplement the source tracing dimension of image feature evolution, construct a complete source tracing path, extract mineralization-related source tracing clues from remote sensing images, and integrate them to form a remote sensing image source tracing clue group.

[0083] Remote sensing image feature data is decomposed to extract tonal features, such as color depth and tonal uniformity in different areas; texture features, such as texture coarseness and direction of ground features in the image; spatial distribution features, such as shape, size, and arrangement of ground features; and anomaly area markers, such as areas with tonal or texture anomalies. These feature data are then organized into a basic remote sensing image dataset. Based on the definition principles of clue tracing dimensions, an image feature evolution tracing dimension is added. This dimension is used to trace the evolution of image features over time, such as changes in image features of mineral deposits at different periods. A complete tracing path is constructed, including dimensions such as mineral genesis tracing, rock formation environment tracing, tectonic influence tracing, and image feature evolution tracing. Along these paths, tracing clues related to copper mineralization are extracted from the basic remote sensing image dataset, such as tonal anomalies indicating the presence of ore bodies, and texture features reflecting rock type and structure. The extracted clues are then integrated to form a remote sensing image tracing clue group.

[0084] For example, step S12771: Obtain the original image file and corresponding interpretation report from the remote sensing image feature data, extract the image tone uniformity description, the location information of tone anomaly areas, and the tone change trend record from them, and generate image tone feature data.

[0085] Information about image tone is extracted from the original image files and corresponding interpretation reports of remote sensing image feature data. The description of image tone uniformity includes whether the tone is uniform across the entire image area and whether there are local tone differences. The location information of tone anomalies is obtained through markers and coordinate data in the interpretation report, clarifying the specific location of the anomalies in the image. The tone change trend record reflects the changes in tone over time or space in different areas, such as the gradual change in tone from the center to the edge of the image. The above information is then organized to generate image tone feature data.

[0086] Step S12772: Extract texture coarseness-related descriptions, texture distribution-related records, and texture difference descriptions from the surrounding area from the original image file to generate image texture feature data.

[0087] In the original image files, descriptions related to texture coarseness are extracted through visual interpretation and computer image analysis, such as whether the texture is fine or coarse; records related to texture distribution, including the distribution range and density of the texture in the image; and descriptions of the differences between the texture and surrounding areas, such as the differences in type and density between the texture of a certain area and the texture of adjacent areas. These descriptive information are then organized to generate image texture feature data.

[0088] Step S12773: Extract the spatial arrangement, relative positional relationship and coverage description of various features in the image from the interpretation report to generate image spatial distribution feature data.

[0089] The interpretation report details the spatial arrangement of various land cover features in the image, such as linear or circular arrangements; relative positional relationships, such as whether a feature is above, below, to the left, or to the right of another feature; and coverage descriptions, including the size and shape of the features. This information is extracted from the interpretation report to generate spatial distribution feature data for the image.

[0090] Step S12774: Collect detailed descriptions and location coordinates of the abnormal tone regions, abnormal texture regions, and abnormal spatial distribution regions marked in the interpretation report, and generate image abnormal region marking data.

[0091] The interpretation report will mark anomalous regions in the image, including anomalous tonal regions, anomalous texture regions, and anomalous spatial distribution regions. Detailed descriptions of these anomalous regions are collected, such as anomalous color features, texture features, spatial distribution features, and their location coordinates. This information is then compiled to generate image anomalous region marking data.

[0092] Step S12775: Integrate the image tone feature data, image texture feature data, image spatial distribution feature data, and image anomaly area marker data to generate a remote sensing image basic dataset.

[0093] The image tonal feature data, image texture feature data, image spatial distribution feature data, and image anomaly area marker data are integrated and organized according to a certain structure and format to form a basic dataset of remote sensing images.

[0094] Step S12776: Referring to the definition principles of the clue tracing dimension, and combining the correlation records between remote sensing image features and copper mineralization, supplement the image feature evolution tracing dimension. This image feature evolution tracing dimension is used to trace the evolution and changes of image features with the mineralization process.

[0095] Referring to the principles previously defined for tracing the origins of mineralization clues, and combining this with the correlation between remote sensing image features and copper mineralization records, it is recognized that image features evolve and change during copper mineralization. For example, the image hue, texture, and other characteristics of the deposit may differ at different stages of copper mineralization. Therefore, a new dimension for tracing the evolution of image features is added to track the changes in these image features throughout the mineralization process, such as image features in the early mineralization stage, the middle mineralization stage, and the later alteration stage.

[0096] Step S12777: Using the dimensions of mineral genesis, rock formation environment, and tectonic influence, together with the supplementary image feature evolution dimension, we form a set of remote sensing image source tracing dimensions.

[0097] By combining the previously defined dimensions of mineral genesis tracing, rock formation environment tracing, and tectonic influence tracing with the newly added dimension of image feature evolution tracing, a set of remote sensing image tracing dimensions is formed. These four dimensions trace the origins of remote sensing image features from different perspectives, enabling a comprehensive uncovering of clues related to copper mineralization.

[0098] Step S12778: Based on the image feature response related records of copper ore formation, construct the corresponding tracing path for each tracing dimension, determine the specific steps and directions for extracting relevant tracing clues from the image feature data, and generate a complete set of tracing paths for remote sensing images.

[0099] Based on relevant records of image feature responses during copper mineralization, this study aims to understand the characteristics of remote sensing images under different mineralization stages and geological conditions. A corresponding source tracing path is constructed for each dimension in the remote sensing image source tracing dimension set. For example, for the mineral genesis source tracing dimension, the steps and directions for extracting clues related to specific minerals from image tone and texture features are determined; for the image feature evolution source tracing dimension, specific methods and paths for tracing the evolution of image features over time are determined. These source tracing paths are then integrated to generate a complete set of remote sensing image source tracing paths.

[0100] Step S12779: Along the complete source tracing path set of the remote sensing image, extract the source tracing clues of color tone formation, texture environment, spatial distribution structure, and feature evolution related to copper mineralization from the basic dataset of the remote sensing image, and generate the original source tracing clue set of the remote sensing image.

[0101] Following each path in the complete source tracing path set of remote sensing images, clues are extracted from the basic remote sensing image dataset. Tonal origination clues analyze the causes of tonal anomalies in the images, such as whether they are caused by ore bodies; texture environment clues study the rock formation environment reflected by texture features; spatial distribution and tectonic origin clues explore the relationship between the spatial distribution of ground features and tectonic structures; and feature evolution clues trace the evolution of image features during mineralization processes. These extracted clues are then combined to generate the original source tracing clue set for the remote sensing images.

[0102] Step S127710: Logically integrate the original source tracing clue set of the remote sensing image to generate a remote sensing image source tracing clue group. The remote sensing image source tracing clue group is used to completely trace the original mineralization-related clues in the remote sensing image feature data.

[0103] The original source tracing clues from remote sensing images are logically integrated, and the consistency and correlation between clues are checked. Contradictory or irrelevant clues are removed, and similar clues are merged and categorized. The integrated clues are arranged in a certain logical order to form a remote sensing image source tracing clue group. This remote sensing image source tracing clue group can completely trace the original mineralization-related clues in the remote sensing image feature data.

[0104] Step S1278: Decompose the geological structure mapping data into structure type records, structure scale related descriptions, structure spatial distribution and structure evolution information to generate a basic geological structure dataset. Following the principle of defining the source dimension of clues, construct a set of structure source paths, extract various source clues related to geological structures and mineralization, and generate a set of original source clues for geological structures.

[0105] Geological structural mapping data is broken down into structural type records, such as folds, faults, and joints; structural scale descriptions, including length, width, and depth; spatial distribution records of structural locations and extent within the target area; and structural evolution information, describing the formation time, evolution process, and interrelationships of the structures. This data is then compiled into a basic geological structural dataset. Following the principle of defining traceability dimensions, a set of structural traceability paths is constructed, including dimensions such as tectonic genesis, tectonic activity phases, and the relationship between structures and mineralization. Along these paths, various traceability clues related to mineralization are extracted from the basic geological structural dataset, such as structural types conducive to mineralization and the relationship between tectonic activity phases and mineralization, generating a set of original geological structural traceability clues.

[0106] Step S1279: Integrate and optimize the original source clue set of the geological structure to generate a geological structure source clue group.

[0107] The original set of geological structural origin clues was integrated and optimized, removing duplicate and redundant clues and supplementing missing key information to ensure the accuracy and completeness of the clues. The integrated and optimized clues were then classified and organized according to structural type, mineralization stage, etc., to form geological structural origin clue groups.

[0108] Step S12710: Compare the completeness and logical consistency of the content of the soil element source traceability clue group, gravity observation source traceability clue group, remote sensing image source traceability clue group and geological structure source traceability clue group. Through cross-matching verification of source traceability clues, complete the missing mineralization-related original clue tracing content in each source traceability clue group.

[0109] The source tracing clues from soil elements, gravity observations, remote sensing images, and geological structures were compared against each other. The completeness of each clue group was checked, and any important clues were examined. The logical consistency between clues was verified, and any contradictions or inconsistencies were investigated. The reliability of the clues was verified by cross-matching clues from different groups, such as whether anomalies in soil elements corresponded to anomalies in remote sensing image tones, and whether gravity anomalies were related to geological structures. For any missing or inconsistent information, further investigation and supplementation were conducted to complete the missing original mineralization-related traceability content in each source tracing clue group, ensuring that all clue groups accurately and comprehensively reflect information related to copper mineralization.

[0110] Step S128: For each traceability clue in each traceability clue group, add a description of its relevance to the original source of copper ore formation. Classify and organize the traceability clue groups after adding the relevance description according to the basic information type. Match each traceability clue group with the corresponding multi-source copper ore related basic information to generate a classified traceability clue set.

[0111] For each traceability clue in each traceability clue group, describe in detail its relevance to the original source of copper mineralization. For example, a mineral genesis traceability clue may be directly related to magmatic-hydrothermal mineralization of copper deposits, indicating that the mineral was crystallized during magmatic-hydrothermal activity, serving as a direct indicator of copper mineralization. After adding the relevance descriptions, classify and organize the traceability clue groups according to the types of basic information related to multi-source copper deposits, such as surface rock outcrop records and soil element content data. Match each classified traceability clue group with its corresponding basic information to clarify which basic information each clue originates from, generating a classified traceability clue set.

[0112] Step S129: Integrate all categorized traceability clue sets to generate multiple sets of traceability clues, which fully trace the original clue sources related to copper ore formation in each type of basic information.

[0113] The generated sets of various categorized traceability clues are integrated to summarize all original clues related to copper mineralization. During the integration process, the integrity and consistency of the clues are ensured, avoiding duplication and conflict of information. The resulting sets of multiple traceability clues comprehensively cover the original sources of copper mineralization traced from various multi-source copper mine-related basic information.

[0114] Step S130: Perform spatiotemporal coupling networking processing on the multiple sets of tracing clues, and construct a dynamic coupled clue network by combining the spatial location corresponding to the tracing clues with the mineralization time series.

[0115] After obtaining multiple sets of tracing clues, these clues need to be spatiotemporally coupled and networked. First, the spatial location information and mineralization-related temporal information corresponding to each tracing clue are collected. Spatial location information can include latitude and longitude coordinates, regional divisions, etc., while the mineralization time series reflects different stages of the copper mineralization process. Then, the spatial and temporal correlations of these clues are analyzed, connecting clues that are spatially close and related in the mineralization time series to construct a network structure. This dynamically coupled clue network can intuitively demonstrate the spatiotemporal relationships between different tracing clues and their connection to the copper mineralization process.

[0116] Step S131: Extract all traceability clues contained in each traceability clue group in the multiple traceability clue sets, obtain the spatial location information and mineralization time correlation information corresponding to each traceability clue, and generate a spatiotemporal basic traceability clue set.

[0117] From each set of multiple source tracing clues, all source tracing clues are extracted. For each clue, its corresponding spatial location information, such as the coordinates of the geological body or sampling point corresponding to the clue, is obtained by consulting its original records or relevant annotation information. Simultaneously, based on the content of the clue and related geological evolution records, its correlation with the mineralization time series is determined, such as whether the clue formed in the early, middle, or late stages of mineralization. The above spatial location information and mineralization time correlation information are then linked to each source tracing clue to generate a spatiotemporal basic source tracing clue set.

[0118] Step S132: Analyze the spatiotemporal evolution records of copper ore formation and define the criteria for determining the spatiotemporal coupling of tracing clues. The criteria include the interaction relationship between tracing clues in different spatiotemporal dimensions during the ore formation process.

[0119] A thorough analysis of the spatiotemporal evolution records related to copper mineralization is conducted to understand the formation and evolution of copper deposits in different geological periods and spatial locations. Based on these records, criteria for determining the spatiotemporal coupling of tracing clues are defined. These criteria should encompass the interaction relationships between tracing clues in different spatiotemporal dimensions. For example, in the same mineralization stage, spatially adjacent clues may have causal relationships or synergistic effects; clues with inheritance relationships in different mineralization stages may have evolutionary connections. This process is achieved by clarifying these criteria.

[0120] Step S133: Based on the judgment criteria, define the spatiotemporal coupling dimension, which includes the spatial location coupling dimension and the time series coupling dimension. Each coupling dimension corresponds to a specific coupling judgment criterion.

[0121] Based on the previously defined criteria for determining the spatiotemporal coupling of tracing clues, we further define spatiotemporal coupling dimensions. The spatial location coupling dimension primarily considers the spatial relationship between tracing clues, such as distance and whether they reside in the same tectonic unit. Its corresponding coupling criteria may include spatial distance thresholds and spatial distribution pattern matching. The temporal series coupling dimension focuses on the chronological order and correlation of tracing clues within the mineralization time series. Its corresponding criteria may include time interval thresholds and temporal evolution stage matching. By defining these two coupling dimensions, we can conduct coupling analysis of tracing clues from different perspectives.

[0122] Step S134: Construct a spatiotemporal coupling execution specification, which divides the coupling levels according to the spatial location coupling dimension and the time series coupling dimension, and determines the coupling mode and coupling range of different levels.

[0123] A spatiotemporal coupling execution specification is established, dividing the coupling process into different levels based on spatial location coupling and time series coupling dimensions. For example, spatial location coupling can be divided into levels such as short-range coupling, medium-range coupling, and long-range coupling; time series coupling can be divided into levels such as synchronous coupling, adjacent-period coupling, and interval-period coupling. For each coupling level, the specific coupling method is determined, such as direct connection or indirect connection, as well as the coupling range, such as the spatial range or time interval within which coupling occurs. By formulating the spatiotemporal coupling execution specification, the spatiotemporal coupling networking process becomes more standardized and regulated.

[0124] Step S135: Mark each traceability clue in the spatiotemporal basic traceability clue set with spatiotemporal attributes, supplement and improve the spatial location details and mineralization time correlation details of the traceability clues, and generate a traceability clue set marked with spatiotemporal attributes.

[0125] Detailed spatiotemporal attribute annotations are performed on each traceability clue in the spatiotemporal foundation clue set. Spatial location details include the specific region where the clue is located, topographic features, and its relative position with surrounding geographical landmarks; mineralization time correlation details include the specific geological age of the clue's formation, its specific stage in the mineralization sequence, and its chronological relationship with other clues. By supplementing these details, the spatiotemporal attributes of the traceability clues are enriched and made more accurate, generating a traceability clue set annotated with spatiotemporal attributes.

[0126] Step S1351: Extract each trace clue from the spatiotemporal basic trace clue set, obtain the basic information type and core content corresponding to the trace clue, and generate basic information for a single trace clue.

[0127] Tracing clues are extracted one by one from the spatiotemporal foundational tracing clue set. For each clue, its corresponding basic information type is determined, such as whether it belongs to surface rock outcrop records or soil element content data. At the same time, the core content of the clue is extracted, such as mineral name, element content, and structural type.

[0128] Step S1352: For each traceability clue, search the spatial location description in the original record of the traceability clue, and extract the key spatial location information, which includes the geographical identifier of the area, the location of the relative reference point, and the range description.

[0129] Based on the basic information of a single tracing clue, locate the original record of that clue. In the original record, search for descriptions of spatial location and extract key spatial information. Geographical identifiers of the area can include administrative division names, mountain range names, river names, etc.; relative reference points such as distance from a mountain peak, or location on which side of a river; and descriptions of the area involved in the clue, including its size and shape. This key information helps to accurately determine the spatial location of the tracing clue.

[0130] Step S1353: Based on the relevant requirements of geographic information standardization, the extracted key spatial location information is converted into a unified spatial coordinate representation, the accuracy-related description of the spatial location is supplemented, the spatial coverage corresponding to the tracing clue is obtained, and spatial attribute details are generated.

[0131] In accordance with the relevant requirements for geographic information standardization, the extracted key spatial location information is converted into a unified spatial coordinate representation, such as latitude and longitude coordinates. Simultaneously, relevant descriptions of spatial location accuracy are added, such as the coordinate error range and measurement method. Based on the spatial coordinates and accuracy information, the spatial coverage area corresponding to the tracing clue is determined, such as a polygonal region or a certain radius around a point, generating detailed spatial attributes.

[0132] Step S1354: Analyze the core content of the source tracing clue and its correlation with the copper mineralization stage. Combined with the regional geological evolution timeline, obtain the mineralization time interval corresponding to the source tracing clue and mark the time-related location of the source tracing clue in the mineralization process.

[0133] Analyze the core elements of the provenance clues, such as mineral assemblages and elemental anomalies, and their relationship to the copper mineralization stages. Combine this with the regional geological evolution timeline to determine the approximate time range of the provenance clue's formation, i.e., the mineralization time interval. For example, a certain mineral assemblage may have formed during the hydrothermal stage of copper mineralization, corresponding to a specific geological age. Mark the temporal location of this provenance clue within the mineralization process, such as the early mineralization stage, the main mineralization stage, or the late alteration stage.

[0134] Step S1355: Supplement the auxiliary information related to the formation time of the source clue, including the order of occurrence of the geological events corresponding to the source clue, the temporal relationship with other source clues, and generate time attribute details.

[0135] In addition to the mineralization time interval and time-related location, supplementary time-related auxiliary information is provided to support the formation of this tracing clue. For example, the sequence of geological events corresponding to this tracing clue, such as magma intrusion preceding tectonic deformation; and its temporal relationship with other tracing clues, such as whether this clue formed before or after another clue. This information is then integrated to generate detailed time attribute information.

[0136] Step S1356: Integrate the spatial attribute details with the temporal attribute details to generate the spatiotemporal attribute annotation content of the single tracing clue. The spatiotemporal attribute annotation content includes the spatial location details and mineralization time correlation details of the tracing clue.

[0137] Spatial and temporal attribute details are integrated to form the spatiotemporal attribute annotation content for a single tracing clue. This spatiotemporal attribute annotation content includes spatial location details of the tracing clue, such as coordinates, range, and precision, as well as mineralization time correlation details, such as time interval, time location, and sequence of related geological events.

[0138] Step S1357: Bind the spatiotemporal attribute annotation content with the corresponding source clue, establish a one-to-one correspondence between the annotation content and the source clue, and generate a single source clue.

[0139] The generated spatiotemporal attribute annotations are bound to the corresponding source tracing clues, ensuring that each source tracing clue has its corresponding spatiotemporal attribute annotation, establishing a one-to-one correspondence. Through this binding, individual source tracing clues are annotated, making the spatiotemporal attributes of the source tracing clues clearer and easier to manage.

[0140] Step S1358: Repeat the operations of extracting basic information of a single source traceability clue, obtaining spatial attribute details, obtaining temporal attribute details, forming annotation content and binding source traceability clues, until all source traceability clues in the spatiotemporal basic source traceability clue set have completed spatiotemporal attribute annotation.

[0141] Following the steps described above, each source clue in the spatiotemporal basic source clue set is processed sequentially, repeatedly extracting basic information, obtaining spatial and temporal attribute details, forming annotation content, and binding source clues, until all source clues have completed spatiotemporal attribute annotation.

[0142] Step S1359: Extract all the marked single traceability clues according to the basic information type, and fill in the missing spatial location details or mineralization time correlation details in each traceability clue through cross-comparison of spatiotemporal attribute details.

[0143] All individual source tracing clues with completed spatiotemporal attribute annotations are categorized and extracted according to their basic information types. Then, the spatiotemporal attribute details of annotated individual source tracing clues of the same or different types are cross-compared. For example, clues from soil element content data and remote sensing image feature data are compared to see if they are consistent in spatial location and correlated in time. Through cross-comparison, missing spatial location details or mineralization time correlation details in each source tracing clue are identified and supplemented, ensuring that the spatiotemporal attributes of all clues are complete and accurate.

[0144] Step S13510: Classify and sort the completed and labeled single traceability clues according to the basic information type to generate a set of traceability clues labeled with spatiotemporal attributes. The set of traceability clues labeled with spatiotemporal attributes contains complete spatiotemporal basic data for subsequent spatiotemporal coupling networking.

[0145] The completed and labeled traceability clues are classified according to the type of basic information, and then sorted in a certain order within each category, such as by spatial location or time order, to finally generate a set of traceability clues labeled with spatiotemporal attributes.

[0146] Step S136: Select any one source clue from the set of source clues with marked spatiotemporal attributes as the coupling start source clue, and obtain the spatiotemporal attribute parameters of the coupling start source clue.

[0147] From the set of source tracing clues labeled with spatiotemporal attributes, one source tracing clue is randomly selected or selected according to certain rules as the coupling starting source tracing clue. The spatiotemporal attribute parameters of this starting clue are obtained, including spatial location coordinates, spatial coverage, mineralization time interval, time location, etc. These parameters will serve as the benchmark for coupling with other clues.

[0148] Step S137: In the set of source clues with marked spatiotemporal attributes, filter the associated source clues whose spatiotemporal attribute parameters with the coupling start source clue meet the requirements of the spatiotemporal coupling execution specification. The associated source clues are source clues that may be coupled with the coupling start source clue in terms of spatial location or time series.

[0149] According to the spatiotemporal coupling execution specification, related tracing clues are screened from the set of tracing clues labeled with spatiotemporal attributes. Based on the spatiotemporal attribute parameters of the starting clue, it is checked whether the spatial location of other clues is within the specified coupling range and whether the time series meets the time requirements of coupling. For example, clues that are spatially close to the starting clue and are in the same or adjacent mineralization stage in time are screened as related tracing clues, as these clues may be coupled with the starting clue.

[0150] Step S138: Establish the spatiotemporal coupling relationship between the coupling initiation tracing clue and the associated tracing clue, mark the coupling dimension and coupling basis corresponding to the coupling relationship, generate a single coupling link, and the single coupling link records the spatiotemporal association related content between the two tracing clues.

[0151] For the selected related tracing clues, establish their spatiotemporal coupling relationship with the initial tracing clue. Clarify the coupling dimension corresponding to the coupling relationship, i.e., whether it is spatial location coupling, temporal series coupling, or both. Simultaneously, label the basis for coupling, such as spatial distance within a specified threshold, overlapping time intervals, etc. Record the above information to generate a single coupling link, which details the spatiotemporal correlation between the two tracing clues.

[0152] Step S139: Repeat the operations of selecting the initial tracing clue of coupling, filtering the associated tracing clues and establishing coupling relationships until all the tracing clues in the set of tracing clues with marked spatiotemporal attributes participate in the construction of at least one coupling link, and generate an initial set of coupling links.

[0153] The process of selecting initial coupling clues, filtering related clues, and establishing coupling relationships is repeated continuously. Each time a new initial clue is selected, related clues are filtered, and a new coupling link is established. This continues until all clues in the set of source clues labeled with spatiotemporal attributes have participated in the construction of at least one coupling link. All generated coupling links are then aggregated to form an initial set of coupling links.

[0154] Step S1310: Using the source clues in each set of source clues labeled with spatiotemporal attributes as network nodes, and the coupling links in the initial set of coupling links as connection channels between nodes, construct a dynamic coupling clue network, wherein the dynamic coupling clue network contains the spatiotemporal coupling relationship between source clues.

[0155] Each traceability clue in the set of traceability clues labeled with spatiotemporal attributes is used as a node in a dynamic coupled clue network. The coupling links in the initial set of coupling links are used as connection channels between nodes, connecting nodes with spatiotemporal coupling relationships, thereby constructing a dynamic coupled clue network. This dynamic coupled clue network shows the spatiotemporal coupling relationships between all traceability clues and can intuitively reflect the correlation between different clues in the copper mineralization process.

[0156] Step S140: Perform signal resonance enhancement processing on the dynamic coupling clue network. Through the ore-forming logic resonance effect between the source clues, enhance the expression of ore-forming related signals and generate a resonance enhancement network.

[0157] After the dynamic coupling clue network is constructed, it needs to undergo signal resonance enhancement processing. Analyzing the mineralization logic relationships among the various tracing clues in the network reveals a resonance effect when different clues corroborate and reinforce each other's mineralization logic. By identifying and utilizing this resonance effect, the expression of mineralization-related signals is strengthened, making the clues and relationships closely related to copper mineralization in the network more prominent, thus generating a resonance-enhanced network.

[0158] Step S141: Analyze the dynamic coupling clue network, extract all network nodes and coupling links between nodes, obtain the source clue content corresponding to each network node and the coupling attribute of each coupling link, and generate the basic set for resonance processing.

[0159] The dynamic coupling clue network is analyzed to extract all nodes, each corresponding to a source tracing clue. Simultaneously, the coupling links between nodes are extracted, and the coupling attributes of each link are obtained, such as coupling dimension, coupling basis, and coupling strength. The source tracing clue content corresponding to each network node and the coupling attributes of the coupling links are integrated to generate a basic set for resonance processing.

[0160] Step S142: Based on the resonance correlation data between different mineralization factors in the copper ore formation process, define the triggering conditions for the resonance of the source trace clues. The triggering conditions are the prerequisites for the mineralization logic resonance effect to be generated between the source trace clues.

[0161] Resonance-related correlation data among different mineralization factors during copper mineralization are collected, such as the synergistic relationships between different elemental anomalies and the matching relationships between tectonics and mineral assemblages. Based on the above data, the triggering conditions for resonance of source tracing clues are defined. For example, when two clues respectively indicate copper element anomalies and pyrite mineral assemblages, and they are spatially adjacent and temporally synchronous, the resonance triggering condition is met. The above triggering condition is a prerequisite for determining whether a mineralization logic resonance effect can occur between source tracing clues.

[0162] Step S143: Based on the triggering conditions, construct a set of resonance reinforcement rules, which specifies the reinforcement method when different types of source tracing clues combine to produce a resonance effect.

[0163] Based on the defined resonance triggering conditions, a set of resonance enhancement rules is constructed. For different types of source tracing clue combinations, corresponding enhancement methods are specified. For example, for the resonance of elemental anomaly clues and mineral assemblage clues, the enhancement method might be to increase the signal strength of the coupling link between them; for the resonance of tectonic clues and remote sensing image anomaly clues, it might be to expand their coupling range.

[0164] Step S144: Perform resonance trigger condition matching on each coupled link in the basic set of resonance processing, and determine whether the tracing clues corresponding to the two network nodes connected by the coupled link meet the resonance trigger condition.

[0165] Each coupled link in the basic set of resonance processing is traversed, and the tracing clues corresponding to the two network nodes connected by the link are checked to see if they meet the resonance triggering conditions. Specifically, the content, spatiotemporal attributes, etc., of the two clues are compared to see if they meet the requirements specified in the triggering conditions. If they do, it is considered that the two clues can generate a mineralization logic resonance effect; otherwise, no resonance effect can be generated.

[0166] Step S145: For the coupling link that satisfies the resonance triggering condition, strengthen the signal transmission strength of the coupling link according to the corresponding strengthening method in the resonance strengthening rule set, and at the same time supplement the resonance-related source clue association information to generate a strengthened coupling link.

[0167] For coupled links that meet the resonance triggering conditions, processing is performed according to the corresponding enhancement methods in the resonance enhancement rule set. For example, the signal transmission strength of the coupled link is increased to make the mineralization-related signals more prominent in the network. Simultaneously, information related to resonance-related tracing clues is supplemented, such as the specific mineralization logic basis of resonance between two clues and the significance of resonance for mineralization prediction. The coupled links processed in the above way are then generated as enhanced coupled links.

[0168] Step S1451: Determine the resonance enhancement rules applicable to the coupling link that satisfies the resonance triggering conditions, and extract the corresponding enhancement methods, enhancement-related parameters, and related information supplementary requirements from the resonance enhancement rule set.

[0169] For coupled links that meet the resonance triggering conditions, the applicable resonance enhancement rule is determined based on the type of tracing clues connected to them and the specific circumstances of the resonance triggering conditions. The enhancement method corresponding to this rule is extracted from the set of resonance enhancement rules, such as the percentage increase in signal strength; enhancement-related parameters, such as the increase value or multiple of signal strength; and supplementary information requirements, such as the resonance basis and significance that need to be supplemented.

[0170] Step S1452: Based on the extracted enhancement method, the signal transmission channel of the coupled link is extended to increase the signal carrying capacity of the signal transmission channel, improve the signal transmission efficiency in the coupled link, and initially enhance the signal transmission strength of the coupled link.

[0171] Based on the extracted enhancement methods, the signal transmission channel of the coupled link is expanded. For example, the bandwidth or capacity of the channel is increased, allowing more mineralization-related signals to be transmitted through it. Simultaneously, the signal transmission path is optimized to reduce signal loss during transmission and improve transmission efficiency. Through these processes, the signal transmission strength of the coupled link is initially enhanced.

[0172] Step S1453: According to the requirements of the relevant parameters, adjust the signal output strength of the network nodes at both ends of the coupling link so that the output signal of the network node can adapt to the conduction characteristics of the coupling link, and further enhance the signal conduction effect of the coupling link.

[0173] Based on the enhanced parameter requirements, adjust the signal output strength of the network nodes at both ends of the coupled link. For example, increase the amplitude or power of the node output signal to match the characteristics of the extended signal transmission channel, ensuring efficient signal transmission in the link and further enhancing the signal transmission effect of the coupled link.

[0174] Step S1454: Analyze the core content of the two tracing clues connected by the coupling link, explore the potential mineralization correlation points between the two tracing clues in addition to the existing coupling relationship, and generate potential correlation information.

[0175] The core content of the two tracing clues connected by the coupling link is analyzed in depth, such as mineral composition, elemental content, and structural features. In addition to the existing coupling relationship, other potential mineralization correlation points may exist between them. For example, the two clues may jointly indicate a specific ore-forming fluid channel or reflect a key stage in the mineralization process. These potential correlation points are then identified to generate potential correlation information.

[0176] Step S1455: Based on the potential correlation information, supplement the specific logical description of the relationship between the two tracing clues, mark the relevant basis of the mineralization logic that generates resonance effect between the two tracing clues, and improve the content of the correlation information.

[0177] Based on the potential correlation information, supplement the two tracing clues with a detailed logical description of their connection. Explain in detail the metallogenic logic underlying the resonance effect between them, such as a shared metallogenic geological background and similar metallogenic physicochemical conditions. These additions will refine the correlation information, making the resonance effect more logically sound.

[0178] Step S1456: Integrate the initially enhanced signal transmission channel, the adjusted node signal output strength, and the supplementary related information to generate the enhanced basic link.

[0179] The initially enhanced signal transmission channel, the adjusted node signal output strength, and the supplementary related information are integrated to form a reinforced basic link.

[0180] Step S1457: Perform signal stability processing on the enhanced basic link, optimize the signal transmission path of the enhanced basic link, reduce signal loss during the transmission process of the enhanced basic link, and maintain stable transmission of the enhanced signal.

[0181] Strengthening the basic link involves signal stability processing. By optimizing the transmission path and adding signal compensation mechanisms, signal loss and interference during transmission are reduced, ensuring that the strengthened signal can be transmitted stably in the link and avoiding signal attenuation or distortion.

[0182] Step S1458: Add resonance identification information to the enhanced basic link. The resonance identification information includes the resonance type and influence range of the enhanced basic link, and generate enhanced link attributes.

[0183] To strengthen the basic link, resonance identification information is added to clarify the resonance type of the link, such as element-mineral resonance, structure-image resonance, etc.; as well as the scope of the resonance's influence, such as which surrounding nodes or links may be affected. The above identification information constitutes the attributes of the strengthened link, which facilitates the identification and analysis of resonance effects in the network.

[0184] Step S1459: Bind the enhanced basic link to the complete enhanced link attributes, record the enhanced features and attribute information of the enhanced basic link, and generate the enhanced coupled link.

[0185] By binding the enhanced basic link with the complete enhanced link attributes, the enhanced characteristics and attribute information of the link can be recognized and utilized by the system. Through the above binding, the final enhanced coupled link is generated, which not only has enhanced signal transmission capability, but also contains rich resonance-related attribute information.

[0186] Step S14510: By testing the signal transmission strength and verifying the correlation information, complete the missing resonance-related source clue correlation information in the enhanced coupling link, and improve the content related to the ore-forming logic resonance effect.

[0187] The generated reinforced coupling links were subjected to signal transmission strength testing to ensure that their signal transmission strength met the expected requirements. Simultaneously, the associated information was matched and verified to check its accuracy and completeness. Missing resonance-related tracing clues discovered during testing and verification were supplemented to further refine the content related to the mineralization logic resonance effect.

[0188] Step S146: For coupled links that do not meet the resonance triggering conditions, maintain the original coupling relationship of the coupled links and incorporate them into the subsequent network construction in their original state to generate basic coupled links.

[0189] For coupled links that do not meet the resonance triggering condition, no enhancement processing is performed, and their original coupling relationship and signal transmission strength are maintained. These links are then incorporated into the subsequent network construction process in their original state to generate basic coupled links, which serve as the fundamental components of the network.

[0190] Step S147: Collect all the reinforced coupling links and the basic coupling links to construct an initial resonance network, which contains all the coupling links that have been reinforced and incorporated in their original state.

[0191] All generated enhanced coupling links and basic coupling links are collected together, and an initial resonance network is constructed according to their connection relationships. This initial resonance network includes links that have undergone signal resonance enhancement processing and the original basic links, reflecting the coupling relationships between the tracing clues.

[0192] Step S148: Extend the resonance range of the enhanced coupling link in the initial resonance network, and based on the resonance signal of the enhanced coupling link, associate other network nodes in the initial resonance network that may produce resonance effects to generate extended resonance links.

[0193] In the initial resonant network, focusing on the reinforced coupling links, we analyze the other network nodes that their resonant signals may affect. Based on the resonance triggering conditions, we search for other nodes associated with these reinforced coupling links and determine whether new resonant effects might occur between them. If so, we establish new coupling links, i.e., extended resonant links, to connect the aforementioned nodes.

[0194] Step S149: Integrate the extended resonant link into the initial resonant network, update the coupling relationship and signal strength between network nodes in the initial resonant network, and generate an intermediate resonant network.

[0195] The generated extended resonance links are added to the initial resonance network to update the coupling relationships between network nodes and add new connection channels. Simultaneously, based on the characteristics of the extended resonance links, the signal strength between relevant nodes is adjusted so that the network can more accurately reflect the distribution and correlation of ore-related signals, thus generating an intermediate resonance network.

[0196] Step S1410: Perform signal integration processing on the intermediate resonance network to unify the signal expression forms of all nodes and links in the intermediate resonance network and generate a resonance enhancement network.

[0197] Signal integration processing is performed on the intermediate resonance network to unify the signal representation formats of different nodes and links, such as using the same signal strength measurement unit and the same signal encoding method. Through integration, the signals in the network become more standardized and easier to analyze, ultimately generating a resonance enhancement network. This resonance enhancement network can display the enhanced mineralization-related signals and their correlations.

[0198] Step S150: Based on the signal distribution and coupling relationship in the resonant enhancement network, perform target area convergence and delineation processing to gradually narrow the range of the mineralization potential area and generate copper ore target area prediction results for the target area.

[0199] The enhanced signal distribution and node coupling relationships in the resonance enhancement network are used for target area convergence and delineation. First, regions with high signal intensity and dense coupling relationships in the network are identified; these regions often have greater mineralization potential. Then, through a series of convergence steps, the scope of these regions is gradually narrowed down, interference from non-mineralization factors is eliminated, and the predicted copper ore target area is finally determined.

[0200] Step S151: Extract the enhancement signal distribution data and node coupling relationship data in the resonance enhancement network, obtain the dense correlation data of the spatial concentration area of ​​enhancement signal and node coupling, and generate the basic data for target area delineation.

[0201] The enhanced signal distribution data is extracted from the resonant enhancement network, including the signal intensity distribution at different spatial locations; and node coupling relationship data, such as coupling density and coupling strength between nodes. Based on the above data, spatial concentration regions of the enhanced signal, i.e., regions with high signal intensity, are determined; and dense correlation data of node coupling, such as regions with dense coupling links, are also identified.

[0202] Step S152: Analyze the spatial distribution records of copper ore deposits and define the direction judgment criteria for target area convergence. The direction judgment criteria are determined based on the spatial distribution records of ore deposits.

[0203] By studying the spatial distribution records of copper mineralization, we can understand the spatial distribution patterns of copper deposits, such as the common distribution of ore bodies along fault zones and their enrichment in specific lithological regions. Based on these patterns, we can define criteria for determining the direction of convergence in target areas. For example, the convergence direction should point towards areas with well-developed fault structures, areas with specific lithological distributions, or areas with abnormally high elemental values, ensuring that the convergence process proceeds in the direction with greater mineralization potential.

[0204] Step S153: Construct target region convergence execution specifications. The target region convergence execution specifications are divided into convergence levels according to the enhanced signal strength and the densely coupled correlation data of nodes. Each convergence level corresponds to a different region reduction range.

[0205] A target region convergence execution specification was established, dividing the target region convergence process into different levels based on enhanced signal strength and dense node coupling data. For example, the first level of convergence targets regions with high signal strength and dense coupling, with a larger reduction margin; the second level of convergence targets regions with medium signal strength and relatively dense coupling, with a moderate reduction margin. Each convergence level specifies the specific region reduction margin and operation method, ensuring the convergence process proceeds in an orderly manner.

[0206] Step S154: Divide the spatial concentration region of the enhanced signal in the target area definition basic data into boundaries, determine the initial boundary range of each concentration region, and generate multiple initial potential regions.

[0207] Based on the spatial concentration of enhanced signals in the target area definition data, boundary delineation is performed. Using spatial analysis methods such as contour mapping and cluster analysis, the initial boundary range of each concentration area is determined. The area enclosed by these boundary ranges is the initial potential area, and each initial potential area possesses a certain mineralization potential.

[0208] Step S155: Based on the target region convergence execution specification, perform first-level convergence processing on each initial potential region, and reduce the initial boundary range of the initial potential region according to the enhancement signal intensity in the initial potential region to generate a first-level convergence region.

[0209] Following the target area convergence execution specifications, a first-level convergence process is performed on each initial potential region. Based on the intensity distribution of the enhanced signal within the region, core regions with higher signal intensity are retained, while edge regions with lower signal intensity are removed, thereby narrowing the initial boundary range. After the first-level convergence process, a first-level convergence region is generated, with a smaller area than the initial potential region, resulting in a more concentrated mineralization potential.

[0210] Step S156: Analyze the node coupling dense correlation data in each of the first-level convergence regions, and combine it with the corresponding convergence level in the target region convergence execution specification to perform second-level convergence processing on the first-level convergence regions, further narrowing the range of the first-level convergence regions and generating second-level convergence regions.

[0211] Analyze the node coupling density data within the first-level convergence region, such as the density of coupling links and the strength of association between nodes. Based on the convergence level corresponding to this data in the target region convergence execution specification, perform second-level convergence processing on the first-level convergence region. For example, for regions with high coupling density, further narrow the scope, retaining the core coupling region; for regions with low coupling density, appropriately adjust the boundaries. Through this second-level convergence processing, a smaller second-level convergence region is generated.

[0212] Step S157: Extract the spatial coordinates and regional feature information of each of the secondary convergence regions, associate them with the original spatial data in the basic information related to the multi-source copper mine, and perform the mineralization-related matching operation of the secondary convergence regions.

[0213] Extract the spatial coordinates of the secondary convergence region to determine its specific location within the target region. Simultaneously, collect regional characteristic information, such as rock type, structural features, and elemental content. Associate this information with the original spatial data from the multi-source copper deposit's related basic information, such as the spatial distribution of surface rock outcrops and the location of soil element sampling points. Perform mineralization-related matching operations to check whether the characteristics of the secondary convergence region match known mineralization models and mineralization indicators.

[0214] Step S158: Based on the results of the mineralization-related matching operation, perform third-level convergence processing on the secondary convergence region, retain the region in the secondary convergence region where the results of the mineralization-related matching operation meet the requirements, and remove the region in the secondary convergence region where the results of the mineralization-related matching operation do not meet the requirements, thereby generating a tertiary convergence region.

[0215] Based on the results of mineralization-related matching operations, a third-level convergence process is performed on the secondary convergence region. Regions meeting the matching requirements, such as those highly matching the mineralization model or containing multiple mineralization indicators, are retained. Regions failing to meet the matching requirements, such as those lacking mineralization indicators or contradicting the mineralization model, are discarded. This third-level convergence process generates a tertiary convergence region, further enhancing its mineralization potential.

[0216] Step S1581: Extract the results of the mineralization-related matching operations for each of the secondary convergence regions, obtain the specific distribution of the region segments whose matching results meet the requirements and the region segments whose matching results do not meet the requirements within the secondary convergence region, and generate reasonable distribution data.

[0217] From the results of mineralization-related matching operations, the specific distribution of matching segments within each secondary convergence region, identifying those that meet and do not, is extracted. For example, it identifies which segments meet mineralization requirements in terms of rock type, elemental content, and other characteristics, and which do not. This distribution information is then compiled into reasonable distribution data to demonstrate the mineralization matching status of different segments within the secondary convergence region.

[0218] Step S1582: Based on the rationality distribution data, obtain the spatial boundary coordinates of the area segments within the secondary convergence area whose mineralization-related matching operation results meet the requirements, and locate the range of the area segments within the secondary convergence area whose mineralization-related matching operation results meet the requirements.

[0219] Based on the reasonable distribution data, determine the spatial boundary coordinates of the region segments within the secondary convergence region that meet the matching requirements. Through coordinate positioning, clarify the specific range of these region segments, such as the coordinates of the upper left and lower right corners, or the vertex coordinates of the boundary polygons.

[0220] Step S1583: Analyze the spatial connectivity between the regions within the secondary convergence region whose mineralization-related matching operation results meet the requirements. Determine the regions within the secondary convergence region whose mineralization-related matching operation results meet the requirements by comparing spatial coordinates, and define the integration-related conditions for the regions.

[0221] Analyze the spatial connectivity between eligible region segments, such as whether they are adjacent, overlapping, or have gaps. Identify adjacent or nearby region segments through spatial coordinate comparison. Define integration criteria for these region segments, such as spatial distance being less than a certain threshold and smooth boundary connections.

[0222] Step S1584: For the regional segments whose mineralization-related matching operation results meet the requirements and the integration conditions are satisfied, perform spatial boundary fusion processing, eliminate the gaps between the regional segments through boundary coordinate connection calculation, and generate continuous regional blocks.

[0223] For region segments that meet the integration criteria, spatial boundary fusion processing is performed. By calculating the boundary coordinates of the region segments, adjusting the boundary shape, and eliminating gaps between them, multiple region segments are merged into a continuous region block. This avoids inaccurate target area ranges caused by the dispersion of region segments.

[0224] Step S1585: Extract the spatial boundary coordinates of the region segment whose mineralization-related matching operation results do not meet the requirements within the secondary convergence region, and obtain the position of the region segment within the secondary convergence region.

[0225] Extract the spatial boundary coordinates of the region fragments whose matching results do not meet the requirements from the reasonable distribution data, and determine the specific location of these region fragments within the secondary convergence region.

[0226] Step S1586: Based on the spatial boundary of the region segment whose mineralization-related matching operation results do not meet the requirements within the secondary convergence region, the region range that needs to be removed is divided within the secondary convergence region, and the region range is made to correspond completely with the region segment whose mineralization-related matching operation results do not meet the requirements within the secondary convergence region through coordinate mapping.

[0227] Based on the spatial boundaries of the non-compliant region fragments, the area to be removed is delineated within the secondary convergence region. Coordinate mapping technology is used to ensure a complete spatial correspondence between the relevant area and the non-compliant region fragment, accurately marking the parts to be removed.

[0228] Step S1587: Compare the coordinates of the continuous region block with the original boundary of the secondary convergence region, and adjust the boundary coordinates of the continuous region block so that the continuous region block is completely within the range of the secondary convergence region.

[0229] The coordinates of the fused contiguous region blocks are compared with the original boundaries of the secondary convergence region to check if the region blocks exceed the range of the secondary convergence region. If they do, the boundary coordinates of the region blocks are adjusted to ensure they are entirely within the secondary convergence region, thus ensuring the accuracy of the convergence process.

[0230] Step S1588: Based on the defined range of regions to be eliminated, the corresponding part of the secondary convergence region is eliminated through spatial region clipping operation, and the adjusted continuous region blocks are retained to generate the preliminary tertiary convergence region.

[0231] Based on the defined areas that need to be removed, a spatial region pruning operation is performed on the secondary convergence region to remove areas that do not meet the requirements. The adjusted continuous region blocks are retained to generate the initial tertiary convergence region.

[0232] Step S1589: Process the preliminary third-level convergence region using a spatial integrity detection algorithm to complete the missing mineralization-related matching operation results in the preliminary third-level convergence region and make the preliminary third-level convergence region as a whole coherent through boundary connection verification.

[0233] A spatial integrity detection algorithm is used to check the preliminary third-level convergence region to find any missing qualified region segments. If any are found, they are added to the preliminary third-level convergence region. At the same time, the boundaries of the regions are verified to ensure that the boundaries of the entire preliminary third-level convergence region are continuous and complete, without obvious breaks or overlaps.

[0234] Step S15810: Perform boundary processing on the preliminary three-level convergence region, adjust its boundary based on the spatial distribution coordinates of the mineralization-related tracing clues, and generate a three-level convergence region.

[0235] Based on the spatial distribution coordinates of mineralization-related prototyping clues, the boundaries of the preliminary tertiary convergence region are fine-tuned. For example, if an important prototyping clue is located near the boundary of the preliminary region, the boundary is adjusted appropriately to include the area where the clue is located. Through boundary processing, the final tertiary convergence region is generated, making it more accurately reflect the mineralization potential area.

[0236] Step S159: Integrate all the three-level convergence regions, eliminate the overlapping parts between the three-level convergence regions, and generate a unified convergence region set. Each region in the convergence region set carries the associated attributes that meet the requirements of the mineralization-related matching operation results.

[0237] All generated tertiary convergence regions are integrated, and the overlap between regions is checked. If overlap exists, the overlapping parts are eliminated based on factors such as the quality of the mineralization-related matching operation results or the importance of the regions, retaining the better regions. Finally, a unified set of convergence regions is generated, with each region carrying the required correlation attributes of the mineralization-related matching operation results, such as mineralization probability and main mineralization indicators.

[0238] Step S1510: Based on the set of convergent regions, obtain the final boundary range and spatial coordinates of each region in the set of convergent regions, and generate the copper ore target area prediction result of the target region. The copper ore target area prediction result defines the area where copper ore may be distributed.

[0239] From the convergence region set, the final boundary range and spatial coordinates of each region are obtained. This information is then organized into copper ore target area prediction results for the target region, defining the areas where copper ore may be distributed. These areas are those with the greatest mineralization potential, determined after multiple rounds of convergence processing.

[0240] Based on the same inventive concept, please refer to Figure 2 The diagram illustrates exemplary hardware and software components of a copper ore target area prediction system 100 based on multi-source information data analysis provided in an embodiment of the present invention. The copper ore target area prediction system 100 based on multi-source information data analysis may include a communication unit 110, a machine-readable storage medium 120, and a processor 130.

[0241] In this embodiment, the machine-readable storage medium 120 can also be integrated into the processor 130 and can communicate and interact with external systems through the communication unit 110. The machine-readable storage medium 120 stores machine-executable instructions for executing the scheme of this application, and the processor 130 executes the machine-executable instructions stored in the machine-readable storage medium 120 to implement the copper ore target area prediction method based on multi-source information data analysis provided in the aforementioned method embodiments.

[0242] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for predicting copper ore target areas based on multi-source information data analysis, characterized in that, The method includes: Collect readily available basic information on multi-source copper deposits in the target area. This basic information includes surface rock outcrop records, soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data. Perform source tracing mapping processing on the multi-source copper ore related basic information to trace the original source of the copper ore mineralization in each type of basic information and generate multiple sets of source tracing clues. The multiple sets of tracing clues are subjected to spatiotemporal coupling networking processing, and a dynamic coupled clue network is constructed by combining the spatial location of the tracing clues with the mineralization time series. The dynamic coupling clue network is subjected to signal resonance enhancement processing. Through the ore-forming logic resonance effect between the source clues, the expression of ore-forming related signals is enhanced, and a resonance enhancement network is generated. Based on the signal distribution and coupling relationship in the resonant enhancement network, target area convergence and delimitation processing is performed to gradually narrow the range of the mineralization potential area and generate copper ore target area prediction results for the target area. The step of performing signal resonance enhancement processing on the dynamically coupled clue network, through the ore-forming logic resonance effect between source clues, enhances the expression of ore-forming related signals and generates a resonance enhancement network, including: The dynamic coupling clue network is analyzed, all network nodes and coupling links between nodes are extracted, the source clue content corresponding to each network node and the coupling attribute of each coupling link are obtained, and a basic set for resonance processing is generated. Based on the resonance correlation data between different mineralization factors during the copper mineralization process, including the synergistic relationship between different elemental anomalies and the matching relationship between structure and mineral assemblages, the triggering conditions for the resonance of source traces are defined. The triggering conditions are the prerequisites for the mineralization logic resonance effect to be generated between source traces. Based on the triggering conditions, a set of resonance reinforcement rules is constructed, which specifies the reinforcement method when different types of tracing clues combine to produce a resonance effect; For each coupling link in the basic set of resonance processing, a resonance trigger condition matching is performed to determine whether the tracing clues corresponding to the two network nodes connected by the coupling link meet the resonance trigger condition. For the coupling link that meets the resonance triggering condition, the signal transmission strength of the coupling link is strengthened according to the corresponding strengthening method in the resonance strengthening rule set, and resonance-related source clue association information is supplemented to generate a strengthened coupling link. For coupled links that do not meet the resonance triggering conditions, the original coupling relationship of the coupled links is maintained, and they are incorporated into the subsequent network construction in their original state to generate basic coupled links; Collect all the enhanced coupling links and the basic coupling links to construct an initial resonant network, which includes all coupling links that have been enhanced and incorporated in their original state. The resonance range of the enhanced coupling link in the initial resonance network is extended, and based on the resonance signal of the enhanced coupling link, other network nodes in the initial resonance network that may produce resonance effects are associated to generate extended resonance links; The extended resonant link is integrated into the initial resonant network, and the coupling relationship and signal strength between network nodes in the initial resonant network are updated to generate an intermediate resonant network. The intermediate resonance network is subjected to signal integration processing to unify the signal expression forms of all nodes and links in the intermediate resonance network, thereby generating a resonance enhancement network. Based on the signal distribution and coupling relationship in the resonant enhancement network, the target area convergence and delineation process is performed to gradually narrow down the range of the mineralization potential area, generating copper ore target area prediction results for the target area, including: Extract the enhancement signal distribution data and node coupling relationship data from the resonant enhancement network, obtain the dense correlation data of the spatial concentration area of ​​the enhancement signal and the node coupling, and generate the basic data for target area delineation. Analyze the spatial distribution records of copper mineralization and define the direction judgment criteria for target area convergence. The direction judgment criteria are determined based on the spatial distribution records of mineralization. A target region convergence execution specification is constructed. The target region convergence execution specification divides the convergence level according to the enhanced signal strength and the densely coupled correlation data of nodes. Each convergence level corresponds to a different region reduction range. The spatial concentration region of the enhanced signal in the target area definition basic data is delineated to determine the initial boundary range of each concentration region, thereby generating multiple initial potential regions. Based on the target region convergence execution specification, a first-level convergence process is performed on each initial potential region. According to the enhancement signal intensity in the initial potential region, the initial boundary range of the initial potential region is narrowed to generate a first-level convergence region. Analyze the densely coupled related data of nodes in each of the first-level convergence regions, and combine it with the corresponding convergence level in the target region convergence execution specification to perform second-level convergence processing on the first-level convergence regions, further narrowing the range of the first-level convergence regions and generating second-level convergence regions. Extract the spatial coordinates and regional feature information of each of the secondary convergence regions, associate them with the original spatial data in the basic information related to the multi-source copper ore, and perform mineralization-related matching operations for the secondary convergence regions; Based on the results of the mineralization-related matching operations, a third-level convergence process is performed on the secondary convergence region. The region in the secondary convergence region whose mineralization-related matching operation results meet the requirements is retained, and the region in the secondary convergence region whose mineralization-related matching operation results do not meet the requirements is removed, thus generating a tertiary convergence region. Integrate all the three-level convergence regions, eliminate the overlapping parts between the three-level convergence regions, and generate a unified set of convergence regions. Each region in the set of convergence regions carries the associated attributes that meet the requirements of the mineralization-related matching operation results. Based on the set of convergent regions, the final boundary range and spatial coordinates of each region in the set of convergent regions are obtained, and the copper ore target area prediction result of the target region is generated. The copper ore target area prediction result defines the area where copper ore may be distributed.

2. The copper ore target area prediction method based on multi-source information data analysis according to claim 1, characterized in that, The process of performing source tracing mapping on the multi-source copper ore-related basic information traces the original source of clues related to copper mineralization in each type of basic information, generating multiple sets of source tracing clues, including: The surface rock outcrop record is decomposed into rock type description, mineral composition record, structural features and outcrop spatial location information to generate a basic rock outcrop dataset, which is a structured representation of the surface rock outcrop record. For the aforementioned rock outcrop dataset, a clue tracing dimension is defined, which includes mineral genesis tracing, rock formation environment tracing, and tectonic influence tracing. Based on the mineral evolution records related to copper mineralization, a mineral genesis tracing path is constructed. Along the mineral genesis tracing path, mineral genesis tracing clues related to copper mineralization are extracted from the basic dataset of rock outcrops, and the relevant content of the formation of each mineral and the associated path of copper mineralization is marked. Based on relevant records of regional geological evolution, a source path for rock formation environment is constructed. According to the source path, source clues reflecting favorable mineralization environments are selected from the basic dataset of rock outcrops, and the relevant content of the geological evolution stage corresponding to each source clue is marked. Based on data related to the impact of tectonic movements on copper mineralization, a tectonic influence tracing path is constructed. Through this tectonic influence tracing path, tectonic correlation tracing clues formed by tectonic movements are extracted from the basic dataset of rock outcrops, and the corresponding relationship between tectonic movements and the formation of tracing clues is marked. By integrating the aforementioned mineral genesis traceability clues, rock formation environment traceability clues, and tectonic correlation traceability clues, a rock outcrop traceability clue group is generated, which includes the original mineralization-related clues in the surface rock outcrop record; Using the same definition of source tracing dimensions, construction of source tracing paths, and extraction and integration of source tracing clues, source tracing processing was performed on the soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data, respectively, to form soil element source tracing clue group, gravity observation source tracing clue group, remote sensing image source tracing clue group, and geological structure source tracing clue group in sequence. For each traceability clue in each traceability clue group, add a description of its relevance to the original source of copper ore formation. Classify and organize the traceability clue groups after adding the relevance description according to the basic information type. Match each traceability clue group with the corresponding basic information of multi-source copper mines to generate a classified traceability clue set. Integrate all categorized traceability clue sets to generate multiple traceability clue sets. These multiple traceability clue sets can completely trace the original clue sources related to copper mineralization in each type of basic information.

3. The copper ore target area prediction method based on multi-source information data analysis according to claim 1, characterized in that, The process of performing spatiotemporal coupling networking on the multiple sets of tracing clues, combining the spatial location of the tracing clues with the mineralization time series, to construct a dynamically coupled clue network includes: Extract all traceability clues contained in each traceability clue group from the multiple sets of traceability clues, and obtain the spatial location information and mineralization time association information corresponding to each traceability clue to generate a spatiotemporal basic traceability clue set. Analyze the spatiotemporal evolution records of copper mineralization and define the criteria for determining the spatiotemporal coupling of traceability clues. The criteria include the interaction relationship of traceability clues in different spatiotemporal dimensions during the mineralization process. Based on the judgment criteria, a spatiotemporal coupling dimension is defined, which includes a spatial location coupling dimension and a time series coupling dimension. Each coupling dimension corresponds to a specific coupling judgment criterion. A spatiotemporal coupling execution specification is constructed, which divides the coupling levels according to the spatial location coupling dimension and the time series coupling dimension, and determines the coupling mode and coupling range of different levels; Each traceability clue in the spatiotemporal basic traceability clue set is labeled with spatiotemporal attributes, and the spatial location details and mineralization time correlation details of the traceability clues are supplemented and improved to generate a traceability clue set labeled with spatiotemporal attributes. Select any one source clue from the set of source clues with marked spatiotemporal attributes as the coupling start source clue, and obtain the spatiotemporal attribute parameters of the coupling start source clue; In the set of source clues with marked spatiotemporal attributes, filter the associated source clues whose spatiotemporal attribute parameters meet the requirements of the spatiotemporal coupling execution specification. The associated source clues are source clues that may be coupled with the coupled starting source clue in terms of spatial location or time series. Establish the spatiotemporal coupling relationship between the initial tracing clue and the associated tracing clue, label the coupling dimension and coupling basis corresponding to the coupling relationship, generate a single coupling link, and the single coupling link records the spatiotemporal correlation related content between the two tracing clues; Repeat the operations of selecting the initial tracing clue of coupling, filtering the associated tracing clues, and establishing coupling relationships until all the tracing clues in the set of tracing clues with marked spatiotemporal attributes participate in the construction of at least one coupling link, and generate an initial set of coupling links; Using the source clues in each set of source clues labeled with spatiotemporal attributes as network nodes, and the coupling links in the initial set of coupling links as connection channels between nodes, a dynamic coupling clue network is constructed, which includes the spatiotemporal coupling relationship between source clues.

4. The copper ore target area prediction method based on multi-source information data analysis according to claim 2, characterized in that, The same methods of defining source tracing dimensions, constructing source tracing paths, and extracting and integrating source tracing clues are used to perform source tracing processing on the soil element content data, regional gravity observation data, remote sensing image feature data, and geological structure mapping data, respectively forming soil element source tracing clue groups, gravity observation source tracing clue groups, remote sensing image source tracing clue groups, and geological structure source tracing clue groups, including: The soil element content data is decomposed into element type records, element content value records, sampling point spatial coordinates and sampling depth information to generate a basic soil element dataset, which is a structured presentation of the soil element content data. Based on the aforementioned basic soil element dataset, the existing traceability dimensions of mineral genesis, rock formation environment, and tectonic influence are used, and the element migration traceability dimension is added to generate a set of soil element traceability dimensions. Based on the element migration records of copper mineralization, we constructed element migration source tracing paths, and combined them with existing mineral genesis source tracing paths, rock formation environment source tracing paths, and tectonic influence source tracing paths to generate a complete set of soil element source tracing paths. Along the complete source path set of soil elements, extract source clues related to copper mineralization, including genetic source clues, environmental source clues, structural influence source clues, and migration source clues, from the basic soil element dataset to generate a set of original source clues for soil elements. Integrate the original source tracing clues of the soil elements to generate a soil element source tracing clue group; The regional gravity observation data is decomposed into gravity numerical records, observation point coordinates, observation time information, and observation environment records to generate a gravity observation basic dataset. Following the corresponding clue tracing dimensions and path construction method, clues for tracing the causes of gravity anomalies and clues for tracing the impact of gravity environment are extracted and integrated to form a gravity observation tracing clue group. The remote sensing image feature data is decomposed into image tone features, texture features, spatial distribution features and anomaly area markers to generate a basic remote sensing image dataset. Based on the principle of defining the source tracing dimension, the source tracing dimension of image feature evolution is supplemented to construct a complete source tracing path, extract mineralization-related source tracing clues from remote sensing images, and integrate them to form a remote sensing image source tracing clue group. The geological structure mapping data is decomposed into structure type records, structure scale related descriptions, structure spatial distribution and structure evolution information to generate a basic geological structure dataset. Following the principle of defining the source dimension of clues, a set of structure source tracing paths is constructed, and various source tracing clues related to geological structures and mineralization are extracted to generate a set of original source tracing clues for geological structures. The original source clues set of the geological structure are integrated and optimized to generate a geological structure source clue group; By comparing the completeness and logical consistency of the content of the soil element source tracing clue group, gravity observation source tracing clue group, remote sensing image source tracing clue group and geological structure source tracing clue group, and by cross-matching and verifying the source tracing clues, the missing mineralization-related original clue tracing content in each source tracing clue group is supplemented.

5. The copper ore target area prediction method based on multi-source information data analysis according to claim 3, characterized in that, The process involves labeling each trace in the spatiotemporal foundation traceability clue set with spatiotemporal attributes, supplementing and improving the spatial location details and mineralization time correlation details of the traceability clues, and generating a set of traceability clues labeled with spatiotemporal attributes, including: Extract each trace clue from the spatiotemporal basic trace clue set, obtain the basic information type and core content corresponding to the trace clue, and generate basic information for a single trace clue. For each tracing clue, the spatial location description in the original record of the tracing clue is searched, and key spatial location information is extracted. The key spatial location information includes the geographical identifier of the area, the location of relative reference points, and the range description. Based on the requirements of geographic information standardization, the extracted key spatial location information is converted into a unified spatial coordinate representation, the accuracy-related description of the spatial location is supplemented, the spatial coverage corresponding to the tracing clue is obtained, and spatial attribute details are generated. The core content of this tracing clue is analyzed and its relationship with the copper mineralization stage. Combined with the regional geological evolution timeline, the mineralization time interval corresponding to this tracing clue is obtained, and the time-related positioning of this tracing clue in the mineralization process is marked. Supplement the auxiliary information related to the formation time of this source clue, including the order of occurrence of the geological events corresponding to this source clue, the temporal relationship with other source clues, and generate time attribute details; The spatial attribute details are integrated with the temporal attribute details to generate the spatiotemporal attribute annotation content of the single tracing clue. The spatiotemporal attribute annotation content includes the spatial location details and mineralization time correlation details of the tracing clue. The spatiotemporal attribute annotations are bound to the corresponding source clues to establish a one-to-one correspondence between the annotation content and the source clue, thereby generating a single source clue with annotations. Repeat the process of extracting basic information of a single source trace, obtaining spatial attribute details, obtaining temporal attribute details, forming annotation content and binding the source trace until all source traces in the spatiotemporal basic source trace set have completed spatiotemporal attribute annotation; All the marked single traceability clues are extracted according to the basic information type. By cross-comparing the spatiotemporal attribute details, the missing spatial location details or mineralization time correlation details in each traceability clue are filled in. The completed and labeled traceability clues are classified and sorted according to the basic information type to generate a set of traceability clues labeled with spatiotemporal attributes. The set of traceability clues labeled with spatiotemporal attributes contains complete spatiotemporal basic data for subsequent spatiotemporal coupling network formation.

6. The copper ore target area prediction method based on multi-source information data analysis according to claim 1, characterized in that, For the coupling link that satisfies the resonance triggering condition, the signal transmission strength of the coupling link is strengthened according to the corresponding strengthening method in the resonance strengthening rule set. At the same time, resonance-related source tracing clue association information is supplemented to generate a strengthened coupling link, including: Determine the resonance enhancement rules applicable to the coupling links that meet the resonance triggering conditions, and extract the corresponding enhancement methods, enhancement-related parameters, and related information supplementary requirements from the set of resonance enhancement rules; Based on the extracted enhancement method, the signal transmission channel of the coupled link is extended to increase the signal carrying capacity of the signal transmission channel, improve the signal transmission efficiency in the coupled link, and initially enhance the signal transmission strength of the coupled link. According to the requirements of the relevant parameters, the signal output strength of the network nodes at both ends of the coupling link is adjusted so that the output signal of the network node can adapt to the conduction characteristics of the coupling link, thereby further enhancing the signal conduction effect of the coupling link; Analyze the core content of the two tracing clues connected by the coupling link, explore the potential mineralization correlation points between the two tracing clues in addition to the existing coupling relationship, and generate potential correlation information. Based on the potential correlation information, supplement the specific logical description of the relationship between the two tracing clues, mark the relevant basis of the mineralization logic that produces a resonance effect between the two tracing clues, and improve the content of the correlation information. By integrating the initially enhanced signal transmission channels, the adjusted node signal output strength, and the supplementary related information, a reinforced basic link is generated. The enhanced basic link is subjected to signal stability processing to optimize the signal propagation path of the enhanced basic link, reduce signal loss during the propagation process of the enhanced basic link, and maintain stable transmission of the enhanced signal. Add resonance identification information to the enhanced basic link, the resonance identification information including the resonance type and influence range of the enhanced basic link, and generate enhanced link attributes; The enhanced basic link is bound to the complete enhanced link attributes, and the enhanced features and attribute information of the enhanced basic link are recorded to generate the enhanced coupled link. By testing the signal transmission strength and verifying the correlation information, the missing resonance-related source clues in the enhanced coupling link are supplemented, and the content related to the resonance effect of mineralization logic is improved.

7. The copper ore target area prediction method based on multi-source information data analysis according to claim 4, characterized in that, Based on the results of the mineralization-related matching operations, a third-level convergence process is performed on the secondary convergence region. This process retains the portion of the secondary convergence region where the mineralization-related matching operation results meet the requirements, and removes the portion where the results do not meet the requirements, generating a tertiary convergence region, including: Extract the results of mineralization-related matching operations for each of the secondary convergence regions, obtain the specific distribution of regional segments within the secondary convergence region that meet the matching requirements and those that do not, and generate reasonable distribution data; Based on the aforementioned reasonable distribution data, the spatial boundary coordinates of the region segments within the secondary convergence region whose mineralization-related matching operation results meet the requirements are obtained, and the range of the region segments within the secondary convergence region whose mineralization-related matching operation results meet the requirements is located. Analyze the spatial connectivity between the regions within the secondary convergence region whose mineralization-related matching operation results meet the requirements, determine the adjacent or nearby regions within the secondary convergence region whose mineralization-related matching operation results meet the requirements through spatial coordinate comparison, and define the integration-related conditions for these regions. For the regional segments whose mineralization-related matching operation results meet the requirements and the integration conditions are satisfied, spatial boundary fusion processing is performed. The gaps between the regional segments are eliminated by boundary coordinate connection calculation to generate continuous regional blocks. Extract the spatial boundary coordinates of the region segment whose mineralization-related matching operation results do not meet the requirements within the secondary convergence region, and obtain the position of the region segment within the secondary convergence region; Based on the spatial boundary of the region segment whose mineralization-related matching operation results do not meet the requirements within the secondary convergence region, the region range that needs to be removed is divided within the secondary convergence region. Through coordinate mapping, the region range is made to correspond completely with the region segment whose mineralization-related matching operation results do not meet the requirements within the secondary convergence region. The coordinates of the continuous region block are compared with the original boundary of the secondary convergence region, and the boundary coordinates of the continuous region block are adjusted so that the continuous region block is completely within the range of the secondary convergence region. Based on the defined range of regions to be eliminated, the corresponding part of the secondary convergence region is eliminated through spatial region clipping operation, and the adjusted continuous region blocks are retained to generate the initial tertiary convergence region. The preliminary third-level convergence region is processed by a spatial integrity detection algorithm to fill in the missing mineralization-related matching operation results in the preliminary third-level convergence region and make the preliminary third-level convergence region as a whole coherent through boundary connection verification. The boundary of the preliminary three-level convergence region is processed, and its boundary is adjusted based on the spatial distribution coordinates of the mineralization-related tracing clues to generate the three-level convergence region.

8. A copper ore target area prediction system based on multi-source information data analysis, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; The processor is configured to execute the copper mine target area prediction method based on multi-source information data analysis as described in any one of claims 1 to 7 by executing the machine-executable instructions.

Images