A multi-source data fusion ore-prospecting prediction method and system based on big data analysis

Abstract

The application provides a multi-source data fusion ore-prospecting prediction method and system based on big data analysis, relates to the technical fields of big data analysis and geological exploration, and comprises the following steps: acquiring initial exploration data; acquiring historical background information related to the initial exploration data according to a collection time; uniformly processing the initial exploration data in units, terms and codes according to a processing specification to obtain standardized exploration data; adjusting the standardized exploration data according to a geological event to generate target exploration data; and using a preset comprehensive prediction model to generate a predicted ore-forming area according to the target exploration data, wherein the preset comprehensive prediction model is used to predict an ore-forming area according to the target exploration data. The application can improve the accuracy and reliability of ore-prospecting prediction.

Description

Technical Field

[0001] This application relates to the fields of big data analysis and geological exploration technology, specifically to a method and system for mineral exploration prediction based on multi-source data fusion using big data analysis. Background Technology

[0002] In modern mineral exploration, multi-source data fusion technology is widely used to predict mineral resources. This technology integrates various exploration data, such as geological maps, geophysical data, geochemical data, and remote sensing imagery, aiming to standardize the processing of these heterogeneous data and uncover their inherent connections to delineate favorable mineralization areas. However, existing technologies often face challenges in processing this multi-source data, including large data acquisition time spans and inconsistent timeliness among different data types. Current prediction systems, when performing multi-source data fusion analysis, often treat all input data as static descriptions of the same point in time, simply performing overlay analysis while ignoring the different rates of change of different data types over time. This approach can lead to the system incorrectly associating "outdated" geochemical high-value areas with recent remote sensing alteration information, resulting in seemingly reasonable but actually inconsistent "false" mineralization targets that do not reflect the current geological reality. For example, a region may have experienced extreme rainfall events or minor seismic activity over the past decade. These geological events can significantly alter surface runoff patterns, geochemical environments, and even affect the porosity and permeability of shallow rock masses. Consequently, early geochemical or geophysical data may fail to accurately reflect the current geological conditions. This inconsistency in timeliness makes it difficult for traditional multi-source data fusion prediction methods to accurately assess the true indicative significance of different data in mineralization prediction, leading to reduced reliability of prediction results and even significant economic losses. Therefore, in mineral exploration projects, facing the complex situation of large time spans in the collection of various types of exploration information such as geological, geophysical, geochemical, and remote sensing data, and the continuous evolution of the surface and shallow geological environment due to factors such as climate, hydrology, and weak tectonic activity, how to design a multi-source information fusion prediction method that can differentiate information from different collection periods based on the inherent change rate of different information types and the stability of the regional environment during comprehensive analysis, and adjust its importance in mineralization prediction in a timely manner, thereby avoiding erroneous correlation analysis caused by inconsistent information timeliness and improving the consistency between prediction results and the current geological conditions, is a pressing technical challenge that needs to be solved. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a multi-source data fusion mineral exploration prediction method and system based on big data analysis, aiming to solve the problems faced by existing multi-source data fusion technologies in mineral exploration, such as the large time span of data acquisition, inconsistent timeliness of different types of data, and the difficulty of accurately assessing the true indicative significance of different data in mineralization prediction, which leads to reduced reliability of prediction results.

[0004] Firstly, this application provides a multi-source data fusion method for mineral exploration prediction based on big data analysis, including:

[0005] Acquire initial exploration data, which includes geological maps, geophysical data, geochemical data, remote sensing images, and acquisition time.

[0006] Based on the acquisition time, historical background information related to the initial exploration data is obtained. The historical background information includes the processing specifications at the time of acquisition of the initial exploration data, as well as geological events that occurred in the acquisition area corresponding to the initial exploration data after the acquisition of the initial exploration data. The geological events include floods or earthquakes.

[0007] The initial exploration data is processed according to the processing specifications to unify units, terminology, and coding, resulting in standardized exploration data, which includes standardized geological maps, standardized geophysical data, standardized geochemical data, and standardized remote sensing images.

[0008] The standardized exploration data is adjusted based on the geological events to generate target exploration data;

[0009] Based on the target exploration data, a preset comprehensive prediction model is used to generate a predicted mineralization area. The preset comprehensive prediction model is used to predict the mineralization area based on the target exploration data.

[0010] According to some embodiments of this application, when the geological event is an earthquake, the step of adjusting the standardized exploration data according to the geological event to generate target exploration data includes:

[0011] When the geological event is an earthquake, obtain the magnitude, focal depth, and seismogenic mechanism of the earthquake;

[0012] Based on the magnitude, the focal depth, and the seismogenic mechanism, a first correction factor is generated, which is used to correct the magnetic anomaly region in the standardized geophysical data.

[0013] The geometric center of the magnetic anomaly region is determined based on the magnetic anomaly region.

[0014] Using the geometric center as the center and the first correction factor as the scaling factor, the magnetic anomaly region is scaled to obtain the corrected magnetic anomaly region.

[0015] The standardized exploration data is adjusted based on the corrected magnetic anomaly region to generate target exploration data.

[0016] According to some embodiments of this application, when the geological event is a flood, the step of adjusting the standardized exploration data according to the geological event to generate target exploration data includes:

[0017] Obtain the flood's grade, duration, and direction of flow.

[0018] Based on the flood runoff direction, a second correction factor is generated. This second correction factor is used to correct the chemical elements in areas with high chemical element content in the standardized geochemical data.

[0019] A third correction factor is generated based on the flood level and the flood duration, and the third correction factor is used to dilute the chemical element content in the geochemical data;

[0020] The chemical elements in the standardized geochemical data are corrected according to the second correction factor and the third correction factor to generate target exploration data.

[0021] According to some embodiments of this application, the step of adjusting the standardized exploration data based on the geological event to generate target exploration data includes:

[0022] When wavy or rope-like texture features are identified based on the standardized remote sensing image, it is determined that karst landforms exist.

[0023] When the existence of the karst landform is confirmed, a simulator consistent with the karst landform and the geological event is selected from the preset physicochemical response simulator library as the target simulator based on the karst landform and the geological event. The simulator is used to simulate the dynamic changes of the physicochemical properties inside the geological body under the geological event. The preset physicochemical response simulator library is used to store simulators applicable to different geological formations and different combinations of geological events.

[0024] Based on the standardized exploration data, target exploration data is generated using the target simulator.

[0025] According to some embodiments of this application, the step of adjusting the standardized exploration data based on the geological event to generate target exploration data includes:

[0026] When an anisotropic rock mass is identified based on the standardized geological map, and the geological event is an earthquake, the focal mechanism parameters of the earthquake and the structural tensor of the anisotropic rock mass are obtained. The focal mechanism parameters include the direction of the principal compressive stress axis, the direction of the principal stress axis, and the dip angle. The structural tensor includes the normal vector and density of the foliation surface.

[0027] Based on the source mechanism parameters and the structural tensor, a preset stress propagation inference module is invoked to determine the stress propagation path and stress concentration region in the anisotropic rock mass. The preset stress propagation inference module is used to infer the propagation of stress in the anisotropic rock mass.

[0028] Based on the stress propagation path and the stress concentration area, and in conjunction with the standardized geological map, deep-seated concealed shear zones with activation potential are identified, and the activated shear zones and their stresses are obtained.

[0029] Based on the activated shear band stress, a fluid channel potential layer is constructed, which is used to indicate the location, size, and fluid conductivity of potential enhancements in fluid activity;

[0030] Based on the fluid channel potential layer, an alteration zone attribute rebalancing correction layer is generated, which is used to indicate the changes in mineral composition and mineral composition content in the alteration zone.

[0031] The standardized exploration data is adjusted based on the alteration zone attribute rebalancing correction layer to generate target exploration data.

[0032] According to some embodiments of this application, the step of constructing a fluid channel potential layer based on the activated shear band stress includes:

[0033] Based on the viscoelastic creep equation, the creep displacement rate of the activated shear band under continuous stress is simulated, where the creep displacement rate is = Aσ^nexp(-Q / RT), and A, n, and Q are material constants, σ ​​is the stress of the activated shear band, R is the gas constant, and T is the temperature.

[0034] Based on the creep displacement rate, the change in the opening degree of the cracks inside the shear band is inferred;

[0035] Based on the change in opening, predict the location, size, and fluid conductivity of the new fluid channel;

[0036] A fluid channel potential layer is constructed based on the location, size, and fluid conductivity of the new fluid channel.

[0037] According to some embodiments of this application, the step of generating an alteration zone property rebalancing correction layer based on the fluid channel potential layer includes:

[0038] Retrieve new fluid channels from the fluid channel potential layer;

[0039] Based on a preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reaction, the changes of alteration zone in the new fluid channel are simulated to obtain an alteration zone mineral equilibrium distribution layer.

[0040] Based on the mineral equilibrium distribution layer of the alteration zone, an alteration zone attribute rebalancing correction layer is generated.

[0041] According to some embodiments of this application, when the alteration zone is a sericite alteration zone, the step of simulating the changes of the alteration zone in the new fluid channel and obtaining the mineral equilibrium distribution layer of the alteration zone based on a preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reaction includes:

[0042] Obtain the temperature and pH value of the new fluid channel;

[0043] Calculate the solubility of sericite at the stated temperature and pH value;

[0044] Based on the preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reaction, the concentration of sericite after the reaction is calculated, and the concentration of sericite is obtained.

[0045] Based on the sericite concentration and solubility, the changes in the alteration zone in the new fluid channel are simulated to obtain an equilibrium distribution layer of alteration zone minerals.

[0046] According to some embodiments of this application, the step of generating a predicted mineralization area based on the target exploration data using a preset comprehensive prediction model includes:

[0047] Identify the mineralization indicator features contained in the target exploration data, determine the spatial correlation between the mineralization indicator features, and generate mineralization indicator features with spatial correlation.

[0048] Identify the spatial uncertainty distribution of mineralization indicator features contained in the target exploration data, wherein the spatial uncertainty distribution describes the range of variation of the mineralization indicator features in terms of spatial location, geometric shape, or attribute value;

[0049] For each pair of mineralization indicator features with spatial correlation, the probability distribution of the spatial correlation strength between the mineralization indicator features is calculated based on their respective spatial uncertainty distributions.

[0050] The probability distribution of the spatial correlation strength is used as input, a preset comprehensive prediction model is applied, and it is incorporated into the evaluation of the interaction between the mineralization indicator features in the comprehensive prediction to generate a predicted mineralization area.

[0051] Secondly, this application also discloses a multi-source data fusion mineral exploration prediction system based on big data analysis, including:

[0052] The data acquisition module is used to acquire initial exploration data, which includes geological maps, geophysical data, geochemical data, remote sensing images, and acquisition time.

[0053] The historical background information acquisition module is used to acquire historical background information related to the initial exploration data based on the acquisition time. The historical background information includes the processing specifications at the time of acquisition of the initial exploration data, and geological events that have occurred in the acquisition area corresponding to the initial exploration data after the acquisition of the initial exploration data. The geological events include floods or earthquakes.

[0054] The standardization processing module is used to process the initial exploration data according to the processing specifications to unify units, terminology, and coding, so as to obtain standardized exploration data, which includes standardized geological maps, standardized geophysical data, standardized geochemical data, and standardized remote sensing images.

[0055] The target exploration data generation module is used to adjust the standardized exploration data according to the geological event to generate target exploration data;

[0056] The prediction result generation module is used to generate a predicted mineralization area based on the target exploration data and a preset comprehensive prediction model. The preset comprehensive prediction model is used to predict the mineralization area based on the target exploration data.

[0057] The technical solution according to the embodiments of this application has at least the following beneficial effects: The multi-source data fusion mineral exploration prediction method based on big data analysis disclosed in this application obtains initial exploration data and its collection time, and obtains relevant historical background information based on the collection time, including the processing specifications during data collection and geological events that occurred in the collection area. This method first standardizes the initial exploration data according to the processing specifications, solving the problem of inconsistencies in units, terminology, and coding between different data sources. More importantly, this method adjusts the standardized exploration data according to geological events to generate target exploration data, effectively solving the problem in the prior art where early-collected data cannot accurately reflect the current geological conditions due to geological events (such as floods and earthquakes), and avoiding the incorrect association of "outdated" information with recent information. Finally, a preset comprehensive prediction model is used to predict the adjusted target exploration data to generate predicted mineralized areas. In this way, this application can fully consider the differences in the rate of change of different data types over time and the impact of geological events, and perform differentiated processing and timely adjustment of information from different collection periods. This avoids erroneous correlation analysis caused by inconsistent information timeliness, significantly improves the consistency between prediction results and current geological conditions, enhances the accuracy and reliability of mineral exploration prediction, and overcomes the shortcomings of reduced reliability of prediction results in existing technologies.

[0058] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0059] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0060] Figure 1 A flowchart illustrating a multi-source data fusion mineral exploration prediction method based on big data analysis, provided in one embodiment of this application;

[0061] Figure 2 This is a schematic diagram of a multi-source data fusion mineral exploration prediction system based on big data analysis, provided as an embodiment of this application. Detailed Implementation

[0062] To make the objectives, technical methods, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that the meaning of "multiple" (or "more than") in the description of the embodiments of this application refers to two or more, and "greater than," "less than," "exceeding," etc. are understood to exclude the number itself, while "above," "below," "within," etc. are understood to include the number itself. If "first," "second," etc. are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0064] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: the existence of a alone, the existence of b alone, the existence of c alone, the simultaneous existence of a and b, the simultaneous existence of a and c, the simultaneous existence of b and c, or the simultaneous existence of a, b, and c, where a, b, and c can be single or multiple.

[0065] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0066] The multi-source data fusion mineral exploration prediction method based on big data analysis provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms; the software can be an application that implements the multi-source data fusion mineral exploration prediction method based on big data analysis, but is not limited to the above forms.

[0067] This application can be applied to numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via communication networks. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices. It should be noted that in various specific embodiments of this invention, when processing is required based on data related to the characteristics of an object (e.g., user attributes or sets of attribute information), permission or consent from the corresponding object is obtained first, and the collection, use, and processing of this data comply with relevant laws and standards. Furthermore, when the embodiments of the present invention need to obtain the attribute information of an object, they will obtain the separate permission or separate consent of the corresponding object through pop-up windows or redirection to a confirmation page. After obtaining the separate permission or separate consent of the corresponding object, they will then obtain the relevant data of the object necessary for the embodiments of the present invention to operate normally.

[0068] See Figure 1 , Figure 1 This is a flowchart illustrating a multi-source data fusion mineral exploration prediction method based on big data analysis, provided in one embodiment of this application. The multi-source data fusion mineral exploration prediction method based on big data analysis provided in this embodiment includes, but is not limited to, steps S110 to S150, which are described in detail below.

[0069] Step S110: Obtain initial exploration data, which includes geological maps, geophysical data, geochemical data, remote sensing images, and acquisition time.

[0070] Step S120: Based on the acquisition time, obtain historical background information related to the initial exploration data. The historical background information includes the processing specifications when the initial exploration data was acquired, as well as the geological events that occurred in the acquisition area corresponding to the initial exploration data after the initial exploration data was acquired. Geological events include floods or earthquakes.

[0071] Step S130: According to the processing specifications, the initial exploration data is processed to unify units, terms and codes to obtain standardized exploration data. The standardized exploration data includes standardized geological maps, standardized geophysical data, standardized geochemical data and standardized remote sensing images.

[0072] Step S140: Adjust the standardized exploration data according to geological events to generate target exploration data;

[0073] Step S150: Based on the target exploration data, use a preset comprehensive prediction model to generate a predicted mineralization area. The preset comprehensive prediction model is used to predict the mineralization area based on the target exploration data.

[0074] It should be noted that initial exploration data refers to all types of data originally acquired during mineral exploration, including geological maps, geophysical data, geochemical data, remote sensing imagery, and the acquisition time of this data. Geological maps are maps reflecting information such as surface and subsurface geological structures, rock types, and stratigraphic distribution. Geophysical data is subsurface physical field data obtained through geophysical exploration methods (such as magnetic, electrical, and gravity methods). Geochemical data is data analyzing the content and distribution characteristics of chemical elements in samples such as rocks, soil, and water. Remote sensing imagery is surface image data acquired through aerial or spaceborne remote sensing technology. The acquisition time records the specific time point when each set of data was acquired. Historical background information refers to historical environmental information related to the acquisition of initial exploration data, including the processing standards during data acquisition and geological events that occurred in the acquisition area after data acquisition, such as floods or earthquakes. Processing standards refer to the standards and methods followed during data acquisition, processing, and storage. Geological events refer to natural events that have a significant impact on the geological environment. Standardized exploration data refers to initial exploration data processed through unified units, terminology, and coding, aiming to eliminate differences between heterogeneous data. Target exploration data is generated by adjusting standardized exploration data based on geological events, and it more accurately reflects the current geological conditions. A pre-defined comprehensive prediction model is an algorithm or model used to predict metallogenic areas based on target exploration data. It can comprehensively analyze multi-source data to identify favorable metallogenic areas.

[0075] In one embodiment, firstly, various methods can be used to acquire initial exploration data. For example, information from traditional materials such as paper geological maps, geophysical exploration reports, and geochemical analysis reports can be manually entered into a database, with the acquisition time recorded. Alternatively, electronic geological maps, geophysical data, geochemical data, and remote sensing images can be acquired in batches from existing geological information systems, geophysical data centers, geochemical laboratory databases, and remote sensing image platforms via data interfaces or file import, and the acquisition time contained in their metadata can be automatically extracted. Secondly, regarding the acquisition of historical background information, retrieval can be performed based on the acquisition time of the initial exploration data. For example, a historical event database can be established, storing records of geological events (such as floods, earthquakes, etc.) in specific areas within different time periods, along with the data processing standards at the time. Once the acquisition time of the initial exploration data is obtained, the system can automatically query the geological events that occurred in that area within that time period and obtain the data processing standards at that time. Another approach is to manually consult historical documents, geological reports, or geological experts to obtain processing standards and geological event information related to a specific acquisition time and input them into the system. Next, regarding the standardization of initial exploration data, the following measures can be taken. For unit standardization, for example, the magnetic anomaly unit in all geophysical data can be standardized to nanoteslas (nT), and the elemental content unit in geochemical data can be standardized to ppm. For terminology standardization, for example, different terms representing the same rock type in different geological legends can be standardized into standard terms. Subsequently, in adjusting the standardized exploration data according to geological events, different adjustment strategies can be adopted based on different types of geological events. For example, when an earthquake event is identified in the acquisition area after data acquisition, the magnetic anomaly region in the standardized geophysical data can be corrected based on parameters such as earthquake magnitude, focal depth, and seismogenic mechanism to reflect the possible displacement or deformation impact of the earthquake on underground magnetic bodies. When a flood event is identified in the acquisition area, the chemical element content in the standardized geochemical data can be corrected based on the flood's level, duration, and runoff direction to reflect the impact of the flood on the migration and dilution of surface chemical elements. Finally, in generating predicted mineralization areas using a pre-set comprehensive prediction model, multiple models can be employed. For example, machine learning-based predictive models such as Support Vector Machines (SVM), Random Forests, or Deep Learning Networks can be used. These models can be pre-trained using large amounts of known mineral deposit data to learn the complex relationship between mineralization indicator features and mineral deposit distribution.After receiving the target exploration data, the model will identify the mineralization indicator features contained in the data, and combine the spatial correlation and uncertainty distribution of these features to calculate the mineralization probability of different regions, thereby generating a predicted mineralization area map.

[0076] It should be noted that this application employs a mechanism for dynamically adjusting exploration data by incorporating historical background information and geological events. By obtaining the acquisition time of the initial exploration data and accordingly acquiring relevant historical background information, including the data processing standards during acquisition and geological events (such as floods or earthquakes) that occurred in the acquisition area after acquisition, this application can make targeted adjustments to standardized exploration data. For example, when the geological event is an earthquake, the magnetic anomaly region in the geophysical data can be corrected based on seismic parameters; when the geological event is a flood, the chemical element content in the geochemical data can be corrected based on flood parameters. This dynamic adjustment allows the generated target exploration data to more accurately reflect the current geological conditions, thereby effectively avoiding erroneous correlation analysis caused by inconsistent data timeliness.

[0077] When the aforementioned geological event is an earthquake, the steps for adjusting the standardized exploration data according to the geological event to generate the target exploration data include:

[0078] When the geological event is an earthquake, obtain the earthquake's magnitude, focal depth, and seismogenic mechanism;

[0079] Based on the magnitude, focal depth and seismogenic mechanism, a first correction factor is generated. The first correction factor is used to correct the magnetic anomaly region in the standardized geophysical data.

[0080] Determine the geometric center of the magnetic anomaly region based on the magnetic anomaly region;

[0081] Using the geometric center as the center and the first correction factor as the scaling factor, the magnetic anomaly region is scaled to obtain the corrected magnetic anomaly region.

[0082] Based on the standardized exploration data adjusted according to the corrected magnetic anomaly region, target exploration data is generated.

[0083] Specifically, when a geological event is identified as an earthquake, it is necessary to obtain key parameters of the earthquake, including magnitude, focal depth, and seismogenic mechanism. Magnitude reflects the amount of energy released by the earthquake, focal depth indicates the underground location of the earthquake, and the seismogenic mechanism describes the movement of the fault during the earthquake, such as strike-slip, reverse, or normal faulting. These parameters are fundamental to assessing the degree and extent of the earthquake's impact on geological bodies. Based on the obtained magnitude, focal depth, and seismogenic mechanism, a first correction factor can be generated. This first correction factor is a parameter that quantifies the earthquake's impact; its value is related to the earthquake's intensity, depth, and the degree of its influence on the crustal stress field. This first correction factor is specifically used to correct magnetic anomaly regions in standardized geophysical data. Magnetic anomaly regions typically indicate the presence of subsurface rock or ore bodies with magnetic differences. Seismic activity may cause displacement, deformation, or changes in the internal structure of these magnetic bodies, thus affecting their magnetic anomaly characteristics. Before correcting magnetic anomaly regions, it is necessary to first determine the geometric center of the magnetic anomaly region. The geometric center can be understood as the centroid of the magnetic anomaly in a two-dimensional plane, and can be determined through geometric calculations of the anomaly region's boundaries or through image processing algorithms. Subsequently, using the determined geometric center as the center point and a generated first correction factor as the scaling factor, the magnetic anomaly region is scaled. This scaling operation aims to simulate the displacement or deformation of the magnetic body caused by an earthquake. For example, a strong earthquake may cause the magnetic anomaly to stretch or compress horizontally, or to uplift or subside vertically, thus altering its appearance in geophysical data. Through scaling, a corrected magnetic anomaly region is obtained, making it more consistent with the actual geological conditions after the earthquake. Finally, based on the obtained corrected magnetic anomaly region, the standardized exploration data is adjusted overall to generate the target exploration data. This adjustment process may include updating the numerical, location, or morphological information related to the magnetic anomaly in the geophysical data to ensure that the target exploration data accurately reflects the impact of the earthquake on the subsurface magnetic geological body.

[0084] In this regard, this application further proposes that when the geological event is a flood, the steps for adjusting standardized exploration data according to the geological event to generate target exploration data include:

[0085] Obtain the flood level, flood duration, and flood runoff direction;

[0086] A second correction factor is generated based on the direction of flood runoff. This second correction factor is used to correct the chemical elements in areas with high chemical element content in the standardized geochemical data.

[0087] A third correction factor is generated based on the flood level and duration. This third correction factor is used to dilute the chemical element content in the geochemical data.

[0088] The chemical elements in the standardized geochemical data are corrected using the second and third correction factors to generate the target exploration data.

[0089] Specifically, obtaining flood classification, duration, and runoff direction involves collecting key parameters of flood events through historical hydrological records, remote sensing image analysis, or field surveys. Flood classification reflects the intensity and extent of the flood, flood duration indicates the duration of interaction between water bodies and surface materials, and flood runoff direction determines the possible transport and redistribution paths of chemical elements. These parameters form the basis for assessing the extent and manner in which floods affect geochemical data. Furthermore, a second correction factor is generated based on flood runoff direction to simulate the spatial redistribution effect of floods on chemical elements. Flood runoff typically carries chemical elements from the surface or shallow soils, transporting and depositing them along the runoff direction. Therefore, the second correction factor is designed to correct areas with high chemical element content in standardized geochemical data, reflecting potential element migration, enrichment, or dilution under flood conditions. In addition, a third correction factor is generated based on flood classification and duration to quantify the dilution effect of floods on the chemical element content in geochemical data. Large-scale floods typically introduce large bodies of water, diluting the concentration of chemical elements in surface or near-surface soils. The higher the flood level and the longer its duration, the more significant the dilution effect may be. A third correction factor is used to dilute and correct the chemical element content in geochemical data to eliminate or mitigate false low-value anomalies caused by floods. Ultimately, by combining the second and third correction factors to comprehensively correct the chemical elements in standardized geochemical data, the true state of the surface geochemical field after a flood event can be more fully and accurately reflected, thus generating more reliable target exploration data.

[0090] It should be noted that the steps described above for adjusting standardized exploration data based on geological events to generate target exploration data include:

[0091] When wavy or rope-like texture features are identified based on standardized remote sensing images, it is determined that karst landforms exist.

[0092] When karst landforms are confirmed to exist, a simulator that matches the karst landforms and geological events is selected from the preset physical and chemical response simulator library as the target simulator based on the karst landforms and geological events. The simulator is used to simulate the dynamic changes of the physical and chemical properties inside the geological body under geological events. The preset physical and chemical response simulator library is used to store simulators applicable to different geological conditions and combinations of different geological events.

[0093] Based on standardized exploration data, target exploration data is generated using a target simulator.

[0094] Specifically, before adjusting standardized exploration data, it is necessary to first analyze standardized remote sensing imagery. By identifying unique wavy or rope-like texture features in the remote sensing imagery, the presence of karst landforms in the target area can be effectively determined. These texture features are typical representations of karst landforms in remote sensing imagery. For example, wavy textures may indicate solution channels or troughs formed by surface water erosion, while rope-like textures may be associated with cave systems or collapse zones formed by groundwater flow. Once the presence of karst landforms is confirmed, it is necessary to select a simulator from a pre-built physicochemical response simulator library that matches the current karst landform type and geological event type as the target simulator, taking into account the current geological events. This pre-built physicochemical response simulator library is a pre-constructed database that stores simulators applicable to different geological conditions and combinations of geological events. Each simulator is specifically designed and calibrated to simulate the dynamic changes in the physicochemical properties within a geological body under the influence of geological events. For example, for flood events, the simulator can simulate the impact of flood runoff on the migration and dilution of chemical elements within karst conduits; for earthquake events, the simulator can simulate the propagation characteristics of seismic waves in karst media and their impact on rock mass structure and fracture systems. Subsequently, standardized exploration data is used as input, and the selected target simulator is used for simulation calculations. The target simulator, based on its built-in physicochemical models and algorithms, combined with the initial geological conditions reflected in the standardized exploration data, simulates the specific impact of geological events on various physicochemical properties within the karst landform area. Thus, the simulator can output finely adjusted data that more accurately reflects the true state of the geological body under the influence of geological events, thereby generating target exploration data.

[0095] In one embodiment, it is assumed that an exploration area has typical karst landforms, and that a moderate-intensity flood event recently occurred in the area. First, the system acquires standardized remote sensing imagery of the area. Analysis of this imagery identifies distinct wavy and rope-like texture features, thus confirming the presence of karst landforms. Subsequently, based on the identified karst landform type (karst topography) and the geological event (flood), the system selects a target simulator from a pre-defined physicochemical response simulator library. This simulator is specifically designed to simulate the impact of floods on geochemical data within karst topography. This simulator incorporates physicochemical models related to water flow dynamics, mineral dissolution-precipitation reactions, and element migration and diffusion. Next, standardized geochemical data (distribution of specific elements in soil or water) for the area is input into the target simulator. The simulator then simulates the dilution, migration, and redistribution of chemical elements within the karst conduit system based on parameters such as flood intensity, duration, and runoff direction. For example, the simulator can calculate the decrease in the content of certain soluble elements in surface or shallow soils caused by flood erosion, while simulating the migration of these elements deeper into caverns with groundwater flow and their potential enrichment or precipitation in specific locations. Ultimately, the simulator outputs adjusted geochemical data that reflects the corrections made to the original geochemical characteristics by the flood event, thus generating more realistic target exploration data. This target exploration data will be used in subsequent integrated predictive models to more accurately identify potential mineralized areas.

[0096] In the above method, the steps of adjusting standardized exploration data based on geological events to generate target exploration data include:

[0097] When an anisotropic rock mass is identified based on a standardized geological map, and the geological event is an earthquake, the focal mechanism parameters of the earthquake and the structural tensor of the anisotropic rock mass are obtained. The focal mechanism parameters include the direction of the principal compressive stress axis, the direction of the principal stress axis, and the dip angle. The structural tensor includes the normal vector and density of the foliation surface.

[0098] Based on the source mechanism parameters and structural tensor, a preset stress propagation inference module is invoked to determine the stress propagation path and stress concentration region in anisotropic rock masses. The preset stress propagation inference module is used to infer the propagation of stress in anisotropic rock masses.

[0099] Based on the stress propagation path and stress concentration area, combined with standardized geological maps, deep-seated concealed shear zones with activation potential are identified, and the activated shear zones and their stresses are obtained.

[0100] Based on the activated shear band stress, a fluid channel potential layer is constructed. The fluid channel potential layer is used to indicate the location, size, and fluid conductivity of potential enhancements in fluid activity.

[0101] Based on the fluid channel potential layer, an alteration zone attribute rebalancing correction layer is generated. The alteration zone attribute rebalancing correction layer is used to indicate the changes in mineral composition and mineral composition content in the alteration zone.

[0102] Based on the alteration zone properties, the standardized exploration data is adjusted by rebalancing the correction layer to generate the target exploration data.

[0103] Specifically, anisotropic rock masses refer to rocks whose physical properties (e.g., seismic wave velocity, electrical conductivity, permeability, etc.) vary with direction. This anisotropy is usually due to the directional arrangement of minerals (e.g., foliation, lineation) or structural features (e.g., fractures, bedding). In mineralization prediction, anisotropic rock masses can significantly influence stress distribution and fluid flow paths. The focal mechanism parameters of an earthquake describe the azimuth and direction of motion of the fault plane at the time of earthquake occurrence, including the direction of the principal compressive stress axis, the direction of the principal stress axis, and the dip angle. These parameters are crucial for understanding the stress field induced by earthquakes. The structural tensor of anisotropic rock masses is a mathematical representation used to describe the direction and degree of anisotropy within the rock mass. It typically includes the normal vector and density of foliation surfaces, which helps quantify the response of the rock's internal structure to external stresses. The preset stress propagation inference module is a computational model or algorithm designed to simulate and predict how seismic stress propagates in complex geological media, particularly anisotropic rock masses. The purpose of this module is to infer the stress distribution and changes induced by earthquakes in these heterogeneous environments. Stress propagation paths refer to the trajectories of seismic energy and associated stresses propagating within rock masses, while stress concentration areas are regions where stress amplitudes are significantly increased due to differences in geological structure, material properties, or stress field geometry. These areas typically correspond to the initiation or reactivation of geological structures. Deeply concealed shear zones with activation potential refer to planar or plate-like areas of rock undergoing intense ductile or brittle deformation under shear stress; their deep concealment means they are not visible at the surface. Activation potential refers to their ease of reactivation or enhanced deformation under new stress conditions (such as seismically induced stress). Activated shear zones can serve as conduits for ore-forming fluids. Activated shear zone stress refers to a specific stress state within an identified activated shear zone that drives further deformation, fracturing, and potential fluid flow. Furthermore, a fluid conduit potential layer is a spatial data layer used to map and quantify the likelihood and capacity of subsurface fluid flow. This layer indicates locations where fluid activity may intensify, the estimated size of these potential conduits, and their fluid conductivity, which is crucial for understanding the migration paths of ore-forming fluids. The alteration zone property rebalancing correction layer is another type of spatial data layer that describes predicted variations in mineral composition and content within existing or newly formed alteration zones. Alteration zones are areas of rock chemically altered by hydrothermal fluids and are typically associated with mineralization.

[0104] According to the above method, the steps for constructing a fluid channel potential layer based on the activated shear band stress include:

[0105] Based on the viscoelastic creep equation, the creep displacement rate of the activated shear band under continuous stress is simulated. Creep displacement rate = Aσ^n exp(-Q / RT), where A, n, and Q are material constants, σ ​​is the stress of the activated shear band, R is the gas constant, and T is the temperature.

[0106] Based on the creep displacement rate, the change in the opening degree of the cracks inside the shear band is inferred;

[0107] Based on the change in opening degree, predict the location, size, and fluid conduction capacity of the new fluid channel;

[0108] A potential fluid channel layer is constructed based on the location, size, and fluid conduction capacity of the new fluid channel.

[0109] The viscoelastic creep equation is a mathematical model describing the deformation of materials over time under long-term stress, reflecting the slow, irreversible deformation behavior of geological bodies under sustained stress. This equation allows for the accurate simulation of the creep displacement rate of activated shear bands under specific stress conditions, thus quantifying the degree of deformation. The calculation of the creep displacement rate involves material constants A, n, and Q, activated shear band stress σ, gas constant R, and temperature T; accurate acquisition of these parameters is crucial for the reliability of the simulation results. Furthermore, based on the simulated creep displacement rate, the change in the opening of fractures within the shear band can be inferred. A larger creep displacement rate generally indicates more significant deformation within the shear band, and a potentially larger fracture opening. This inference can be achieved by establishing an empirical relationship or physical model between the creep displacement rate and fracture opening. Changes in fracture opening directly affect the fluid flow capacity within the shear band. Based on this, the location, size, and fluid conductivity of new fluid channels can be predicted according to the inferred changes in fracture opening. New fluid channels refer to pathways that form or expand within activated shear bands due to stress and creep deformation, enabling efficient fluid transport. Their location can be determined by analyzing the spatial distribution of fracture opening, while their size is related to the width and length of the fractures. Fluid conductivity reflects the ease with which fluid passes through these channels, typically related to permeability. Finally, based on the predicted location, size, and fluid conductivity of the new fluid channels, a potential fluid channel layer can be constructed.

[0110] Specifically, in some of the above embodiments, the step of generating an alteration zone property rebalancing correction layer can be further refined to more accurately reflect the impact of geological events on the mineral properties of the alteration zone.

[0111] The steps for generating an alteration zone property rebalancing correction layer based on the fluid channel potential layer include:

[0112] Retrieve new fluid channels from the fluid channel potential layer;

[0113] Based on a pre-defined thermodynamic equilibrium calculation program for mineral dissolution-precipitation reactions, the changes of alteration zones in new fluid channels are simulated to obtain an alteration zone mineral equilibrium distribution layer.

[0114] Based on the mineral equilibrium distribution layer of the alteration zone, a rebalancing correction layer for alteration zone attributes is generated.

[0115] The acquisition of new fluid channels in the fluid channel potential layer refers to identifying and extracting regions from the previously constructed fluid channel potential layer that indicate the location, size, and fluid conductivity of potential enhancements in fluid activity. These new fluid channels are formed due to creep of activated shear zones under sustained stress, leading to changes in the opening of fractures within the shear zones. Further, based on a pre-defined thermodynamic equilibrium calculation program for mineral dissolution-precipitation reactions, the changes in alteration zones within the new fluid channels are simulated to obtain an alteration zone mineral equilibrium distribution layer. Specifically, the pre-defined thermodynamic equilibrium calculation program for mineral dissolution-precipitation reactions can be understood as a computational model built based on geochemical principles and thermodynamic data. Its purpose is to simulate reactions such as dissolution, precipitation, and transformation of minerals under fluid action under specific physicochemical conditions, and to calculate the mineral composition and its content distribution when reaching equilibrium. By using the characteristics of the new fluid channels, such as fluid properties, temperature, and pressure, as input, the program can predict the dynamic changes in mineral composition and content within the alteration zone, thereby obtaining an alteration zone mineral equilibrium distribution layer reflecting the mineral distribution in equilibrium. Therefore, based on the mineral equilibrium distribution layer of the alteration zone, a rebalancing correction layer for alteration zone attributes is generated. This correction layer aims to indicate changes in mineral composition and content within the alteration zone, providing a basis for subsequent adjustments to standardized exploration data. Specifically, when the alteration zone is a sericite alteration zone, the steps described above, based on a preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reactions, to simulate the changes in the alteration zone within the new fluid channel and obtain the mineral equilibrium distribution layer of the alteration zone, include:

[0116] Obtain the temperature and pH value of the new fluid channel;

[0117] Calculate the solubility of sericite at different temperatures and pH values;

[0118] Based on the preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reaction, the concentration of sericite after the reaction is calculated, and the concentration of sericite is obtained.

[0119] Based on the concentration and solubility of sericite, the changes of alteration zones in the new fluid channel are simulated to obtain an equilibrium distribution layer of alteration zone minerals.

[0120] Obtaining the temperature and pH of the new fluid channel involves determining key physicochemical parameters of the fluid within the channel through geothermal gradient models, fluid inclusion analysis, or geochemical simulations. Temperature affects the rate and equilibrium constant of mineral dissolution-precipitation reactions, while pH determines the concentration of hydrogen or hydroxide ions in the solution, thus influencing the stability of minerals in aqueous solutions. Calculating the solubility of sericite at specific temperatures and pH values ​​involves using thermodynamic databases and geochemical software to calculate the saturation or solubility of sericite under the current fluid conditions, based on the input temperature and pH. This provides a basis for determining whether sericite is dissolving or precipitating. Calculating the concentration of sericite after the reaction, based on a pre-set thermodynamic equilibrium calculation program for mineral dissolution-precipitation reactions, involves obtaining the sericite concentration. This concentration is calculated by using a thermodynamic equilibrium calculation program, combined with the initial fluid composition, sericite solubility, and reaction kinetic parameters, to simulate the final concentration of sericite after reaching equilibrium with the fluid following the interaction between the fluid and the sericite alteration zone. This concentration reflects the actual change in sericite under the influence of the fluid. Based on the concentration and solubility of sericite, the changes of alteration zones in a new fluid channel are simulated to obtain an alteration zone mineral equilibrium distribution layer. This means combining the calculated concentration and solubility of sericite to assess whether sericite dissolves, precipitates, or remains stable in the fluid channel, and mapping it spatially to generate a detailed alteration zone mineral equilibrium distribution layer.

[0121] In one embodiment, it is assumed that fluid inclusion analysis and geochemical sampling of an activated shear zone in a certain region revealed an average temperature of 250°C and a pH of 4.5 for the new fluid channel. Simultaneously, a widespread sericite alteration zone was identified in this region using a standardized geological map. To accurately simulate the changes in this sericite alteration zone under the influence of the new fluid channel, firstly, using geochemical simulation software (e.g., PHREEQC), the theoretical solubility of sericite under these conditions is calculated by inputting the temperature of 250°C and the pH of 4.5. It is assumed that the calculation results show that the solubility of sericite at this temperature and pH is X mg / L. Next, based on a pre-defined thermodynamic equilibrium calculation program for mineral dissolution-precipitation reactions, combined with initial fluid component data, the actual concentration of sericite after the fluid reacts with the sericite is simulated. It is assumed that the simulated actual concentration of sericite is Y mg / L. By comparing X and Y, if Y is less than X, it indicates that sericite tends to dissolve under these fluid conditions; if Y is greater than X, it tends to precipitate. For example, if Y is significantly less than X, it can be inferred that significant dissolution will occur in the sericite alteration zone in this region. Finally, based on these calculations, a detailed mineral equilibrium distribution layer of the alteration zone is generated. This layer clearly indicates the degree of dissolution or precipitation of sericite at different spatial locations, thus providing a precise basis for identifying mineralization potential areas associated with sericite alteration.

[0122] In some embodiments of this application, the step of generating a predicted mineralization area based on target exploration data and using a preset comprehensive prediction model includes:

[0123] Identify mineralization indicator features contained in target exploration data, determine the spatial correlation between mineralization indicator features, and generate mineralization indicator features with spatial correlation.

[0124] Identify the spatial uncertainty distribution of mineralization indicator features contained in the target exploration data. The spatial uncertainty distribution describes the range of variation of mineralization indicator features in terms of spatial location, geometric shape, or attribute value.

[0125] For each pair of mineralization indicator features with spatial correlation, the probability distribution of the spatial correlation strength between the mineralization indicator features is calculated based on their respective spatial uncertainty distributions.

[0126] Using the probability distribution of spatial correlation strength as input, a pre-set comprehensive prediction model is applied, and this model is integrated into the evaluation of the interaction between mineralization indicator features to generate predicted mineralization areas.

[0127] Specifically, identifying mineralization indicator features in target exploration data refers to extracting geological, geophysical, geochemical, and remote sensing anomalies directly or indirectly related to mineralization from the adjusted target exploration data. These features can be specific lithological assemblages, tectonic fault zones, areas of high geochemical anomalies, geophysical anomalies, or alteration information in remote sensing images. Furthermore, determining the spatial correlation between mineralization indicator features involves analyzing the symbiotic, associated, superimposed, or mutually exclusive relationships among these identified features in space. For example, a certain type of mineralization may always be accompanied by specific wall rock alteration zones and tectonic ore-controlling features. This generates a set of mineralization indicator features with spatial correlations, laying the foundation for subsequent analysis. The spatial uncertainty distribution of identifying mineralization indicator features in target exploration data can be understood as follows: due to data acquisition errors, the ambiguity of geological interpretation, and the heterogeneity of the geological body itself, any mineralization indicator feature has a certain range of variation or confidence interval in its spatial location, geometric shape, or attribute values. The spatial uncertainty distribution is precisely a quantitative description of this range of variation. In practical applications, for each pair of spatially correlated mineralization indicator features, calculating the probability distribution of the spatial correlation strength between these features based on their respective spatial uncertainty distributions means that, considering the uncertainty of each feature itself, the correlation strength between them should also be expressed in probabilistic form. Furthermore, using the probability distribution of spatial correlation strength as input, applying a pre-defined comprehensive prediction model, and integrating it into the assessment of the interaction between mineralization indicator features in the comprehensive prediction to generate predicted mineralization areas means that traditional comprehensive prediction models may only use deterministic correlation strengths.

[0128] See Figure 2 , Figure 2 A schematic diagram of a multi-source data fusion mineral exploration prediction system based on big data analysis, provided in one embodiment of this application. The multi-source data fusion mineral exploration prediction system 200 based on big data analysis includes:

[0129] The data acquisition module 210 is used to acquire initial exploration data, which includes geological maps, geophysical data, geochemical data, remote sensing images, and acquisition time.

[0130] The historical background information acquisition module 220 is used to acquire historical background information related to the initial exploration data based on the acquisition time. The historical background information includes the processing specifications when the initial exploration data was acquired, as well as geological events that occurred in the acquisition area corresponding to the initial exploration data after the acquisition of the initial exploration data. Geological events include floods or earthquakes.

[0131] The standardization processing module 230 is used to process the initial exploration data according to the processing specifications to unify the units, terms and codes, so as to obtain standardized exploration data, which includes standardized geological maps, standardized geophysical data, standardized geochemical data and standardized remote sensing images.

[0132] The target exploration data generation module 240 is used to adjust the standardized exploration data according to geological events and generate target exploration data.

[0133] The prediction result generation module 250 is used to generate a predicted mineralization area based on the target exploration data and a preset comprehensive prediction model. The preset comprehensive prediction model is used to predict the mineralization area based on the target exploration data.

[0134] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0135] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0136] The foregoing has provided a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined in this application.

Claims

1. A multi-source data fusion method for mineral exploration prediction based on big data analysis, characterized in that, include: Acquire initial exploration data, which includes geological maps, geophysical data, geochemical data, remote sensing images, and acquisition time. Based on the acquisition time, historical background information related to the initial exploration data is obtained. The historical background information includes the processing specifications at the time of acquisition of the initial exploration data, as well as geological events that occurred in the acquisition area corresponding to the initial exploration data after the acquisition of the initial exploration data. The geological events include floods or earthquakes. The initial exploration data is processed according to the processing specifications to unify units, terminology, and coding, resulting in standardized exploration data, which includes standardized geological maps, standardized geophysical data, standardized geochemical data, and standardized remote sensing images. The standardized exploration data is adjusted based on the geological events to generate target exploration data; Based on the target exploration data, a preset comprehensive prediction model is used to generate a predicted mineralization area. The preset comprehensive prediction model is used to predict the mineralization area based on the target exploration data. When the geological event is an earthquake, the steps for adjusting the standardized exploration data according to the geological event to generate target exploration data include: When the geological event is an earthquake, obtain the magnitude, focal depth, and seismogenic mechanism of the earthquake; Based on the magnitude, the focal depth, and the seismogenic mechanism, a first correction factor is generated, which is used to correct the magnetic anomaly region in the standardized geophysical data. The geometric center of the magnetic anomaly region is determined based on the magnetic anomaly region. Using the geometric center as the center and the first correction factor as the scaling factor, the magnetic anomaly region is scaled to obtain the corrected magnetic anomaly region. Based on the corrected magnetic anomaly region, the standardized exploration data is adjusted to generate target exploration data; When the geological event is a flood, the steps for adjusting the standardized exploration data according to the geological event to generate target exploration data include: Obtain the flood's grade, duration, and direction of flow. Based on the flood runoff direction, a second correction factor is generated. This second correction factor is used to correct the chemical elements in areas with high chemical element content in the standardized geochemical data. A third correction factor is generated based on the flood level and the flood duration, and the third correction factor is used to dilute the chemical element content in the geochemical data; The chemical elements in the standardized geochemical data are corrected according to the second correction factor and the third correction factor to generate target exploration data.

2. The multi-source data fusion mineral exploration prediction method based on big data analysis according to claim 1, characterized in that, The step of adjusting the standardized exploration data according to the geological event to generate the target exploration data includes: When wavy or rope-like texture features are identified based on the standardized remote sensing image, it is determined that karst landforms exist. When the existence of the karst landform is confirmed, a simulator consistent with the karst landform and the geological event is selected from the preset physicochemical response simulator library as the target simulator based on the karst landform and the geological event. The simulator is used to simulate the dynamic changes of the physicochemical properties inside the geological body under the geological event. The preset physicochemical response simulator library is used to store simulators applicable to different geological formations and different combinations of geological events. Based on the standardized exploration data, target exploration data is generated using the target simulator.

3. The multi-source data fusion mineral exploration prediction method based on big data analysis according to claim 1, characterized in that, The step of adjusting the standardized exploration data according to the geological event to generate the target exploration data includes: When an anisotropic rock mass is identified based on the standardized geological map, and the geological event is an earthquake, the focal mechanism parameters of the earthquake and the structural tensor of the anisotropic rock mass are obtained. The focal mechanism parameters include the direction of the principal compressive stress axis, the direction of the principal stress axis, and the dip angle. The structural tensor includes the normal vector and density of the foliation surface. Based on the source mechanism parameters and the structural tensor, a preset stress propagation inference module is invoked to determine the stress propagation path and stress concentration region in the anisotropic rock mass. The preset stress propagation inference module is used to infer the propagation of stress in the anisotropic rock mass. Based on the stress propagation path and the stress concentration area, and in conjunction with the standardized geological map, deep-seated concealed shear zones with activation potential are identified, and the activated shear zones and their stresses are obtained. Based on the activated shear band stress, a fluid channel potential layer is constructed, which is used to indicate the location, size, and fluid conductivity of potential enhancements in fluid activity; Based on the fluid channel potential layer, an alteration zone attribute rebalancing correction layer is generated, which is used to indicate the changes in mineral composition and mineral composition content in the alteration zone. The standardized exploration data is adjusted based on the alteration zone attribute rebalancing correction layer to generate target exploration data.

4. The multi-source data fusion mineral exploration prediction method based on big data analysis according to claim 3, characterized in that, The step of constructing the fluid channel potential layer based on the activated shear band stress includes: Based on the viscoelastic creep equation, the creep displacement rate of the activated shear band under continuous stress is simulated. The creep displacement rate is = A σ^n exp(-Q / RT), where A, n, and Q are material constants, σ ​​is the stress of the activated shear band, R is the gas constant, and T is the temperature. Based on the creep displacement rate, the change in the opening degree of the cracks inside the shear band is inferred; Based on the change in opening, predict the location, size, and fluid conductivity of the new fluid channel; A fluid channel potential layer is constructed based on the location, size, and fluid conductivity of the new fluid channel.

5. The multi-source data fusion mineral exploration prediction method based on big data analysis according to claim 3, characterized in that, The step of generating an alteration zone property rebalancing correction layer based on the fluid channel potential layer includes: Retrieve new fluid channels from the fluid channel potential layer; Based on a preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reaction, the changes of alteration zone in the new fluid channel are simulated to obtain an alteration zone mineral equilibrium distribution layer. Based on the mineral equilibrium distribution layer of the alteration zone, an alteration zone attribute rebalancing correction layer is generated.

6. The multi-source data fusion mineral exploration prediction method based on big data analysis according to claim 5, characterized in that, When the alteration zone is a sericite alteration zone, the step of simulating the changes of the alteration zone in the new fluid channel and obtaining the mineral equilibrium distribution layer of the alteration zone based on the preset thermodynamic equilibrium calculation program of mineral dissolution-precipitation reaction includes: Obtain the temperature and pH value of the new fluid channel; Calculate the solubility of sericite at the stated temperature and pH value; Based on the preset thermodynamic equilibrium calculation program for mineral dissolution-precipitation reaction, the concentration of sericite after the reaction is calculated, and the concentration of sericite is obtained. Based on the sericite concentration and solubility, the changes in the alteration zone in the new fluid channel are simulated to obtain an equilibrium distribution layer of alteration zone minerals.

7. The multi-source data fusion mineral exploration prediction method based on big data analysis according to claim 1, characterized in that, The step of generating a predicted mineralization area based on the target exploration data and using a preset comprehensive prediction model includes: Identify the mineralization indicator features contained in the target exploration data, determine the spatial correlation between the mineralization indicator features, and generate mineralization indicator features with spatial correlation. Identify the spatial uncertainty distribution of mineralization indicator features contained in the target exploration data, wherein the spatial uncertainty distribution describes the range of variation of the mineralization indicator features in terms of spatial location, geometric shape, or attribute value; For each pair of mineralization indicator features with spatial correlation, the probability distribution of the spatial correlation strength between the mineralization indicator features is calculated based on their respective spatial uncertainty distributions. The probability distribution of the spatial correlation strength is used as input, a preset comprehensive prediction model is applied, and it is incorporated into the evaluation of the interaction between the mineralization indicator features in the comprehensive prediction to generate a predicted mineralization area.

8. A multi-source data fusion mineral exploration prediction system based on big data analysis, characterized in that, include: The data acquisition module is used to acquire initial exploration data, which includes geological maps, geophysical data, geochemical data, remote sensing images, and acquisition time. The historical background information acquisition module is used to acquire historical background information related to the initial exploration data based on the acquisition time. The historical background information includes the processing specifications at the time of acquisition of the initial exploration data, and geological events that have occurred in the acquisition area corresponding to the initial exploration data after the acquisition of the initial exploration data. The geological events include floods or earthquakes. The standardization processing module is used to process the initial exploration data according to the processing specifications to unify units, terminology, and coding, so as to obtain standardized exploration data, which includes standardized geological maps, standardized geophysical data, standardized geochemical data, and standardized remote sensing images. The target exploration data generation module is used to adjust the standardized exploration data according to the geological event to generate target exploration data; The prediction result generation module is used to generate a predicted mineralization area based on the target exploration data and using a preset comprehensive prediction model. The preset comprehensive prediction model is used to predict the mineralization area based on the target exploration data. When the geological event is an earthquake, the standardized exploration data is adjusted according to the geological event to generate target exploration data, including: When the geological event is an earthquake, obtain the magnitude, focal depth, and seismogenic mechanism of the earthquake; Based on the magnitude, the focal depth, and the seismogenic mechanism, a first correction factor is generated, which is used to correct the magnetic anomaly region in the standardized geophysical data. The geometric center of the magnetic anomaly region is determined based on the magnetic anomaly region. Using the geometric center as the center and the first correction factor as the scaling factor, the magnetic anomaly region is scaled to obtain the corrected magnetic anomaly region. Based on the corrected magnetic anomaly region, the standardized exploration data is adjusted to generate target exploration data; When the geological event is a flood, the standardized exploration data is adjusted according to the geological event to generate target exploration data, including: Obtain the flood's grade, duration, and direction of flow. Based on the flood runoff direction, a second correction factor is generated. This second correction factor is used to correct the chemical elements in areas with high chemical element content in the standardized geochemical data. A third correction factor is generated based on the flood level and the flood duration, and the third correction factor is used to dilute the chemical element content in the geochemical data; The chemical elements in the standardized geochemical data are corrected according to the second correction factor and the third correction factor to generate target exploration data.

Images