Mining area geological information comprehensive analysis method and system based on data integration

Abstract

The invention relates to the technical field of data processing, in particular to a mining area geological information comprehensive analysis method and system based on data integration, and the method comprises the steps: obtaining and preprocessing multi-source geological data, carrying out the feature correlation analysis and normalization, and obtaining a standardized data set; classifying the magnetic anomaly and gravity anomaly data through a support vector machine to generate a fluid dynamic classification result; performing interpolation processing on the classification result to generate continuous fluid dynamic data, and analyzing the speed and direction change of the fluid to generate a permeability distribution diagram; extracting an abnormal region according to the dynamic change trend, matching the abnormal region with historical data, marking geological abnormal points and generating an abnormal distribution diagram; according to the geological flow monitoring report, the underground water body type or the change of the oil-gas mixing proportion is judged, a pressure fluctuation mode is recognized, and a refined geological abnormal point distribution diagram is generated. According to the invention, mining area resource management and potential risk early warning can be effectively supported.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for comprehensive analysis of geological information in mining areas based on data integration. Background Technology

[0002] As mineral resource development deepens, the demand for precision in geological exploration and fluid monitoring continues to increase. In the geological exploration process of mining areas, traditional single-source data analysis methods are no longer sufficient to cope with complex underground environments, especially in fields such as oil and gas exploration and groundwater monitoring, where accuracy and timeliness are crucial for resource development and risk management. Therefore, how to improve the accuracy of geological information analysis through multi-source data integration has become a significant challenge in geological information management in mining areas.

[0003] Currently, geological information monitoring systems mainly rely on single data sources such as magnetic fields, gravity anomalies, and temperature gradients for analysis. However, these single data sources provide limited information under different geological environments, and the resolution, format, and spatiotemporal correlation of the data vary, making the fusion and comprehensive analysis of different data sources quite difficult. Furthermore, the geological environment of mining areas is complex and variable, and traditional methods have failed to effectively handle the spatiotemporal correlation of multi-source geological data, often lacking the ability to comprehensively assess fluid dynamics and anomaly detection.

[0004] In geological resource exploration, the dynamic changes of fluids, the mixing ratio of oil and gas, and the type of groundwater often determine the development potential of a mining area. Therefore, precise monitoring of the dynamic evolution and pressure fluctuations of underground fluids is necessary to promptly detect potential geological anomalies and reduce resource waste and environmental risks during development. To achieve this goal, a comprehensive analysis method based on multi-source geological data integration is needed. This method can effectively integrate data from different sources and perform precise analysis, supporting the scientific management of underground resources.

[0005] Therefore, a comprehensive analysis method for geological information in mining areas based on data integration is proposed. This method aims to solve the problems of data inconsistency and inaccurate analysis in existing technologies by integrating multi-source geological data collected by UAVs, ground sensors, etc., and using modern data processing technology for feature extraction and dynamic analysis, thereby providing more accurate and reliable technical support for mining resource development. Summary of the Invention

[0006] This invention provides a method and system for comprehensive analysis of geological information in mining areas based on data integration, which improves the accuracy and reliability of geological information analysis in mining areas. In a first aspect, this invention provides a method for comprehensive analysis of geological information in mining areas based on data integration, comprising: Step S1: Obtain multi-source geological data corresponding to the mining area and perform preprocessing. Perform feature association analysis on the preprocessed multi-source geological data, obtain and normalize the multi-dimensional feature vectors to obtain a standardized geological dataset. Step S2: If the correlation strength between magnetic anomalies and gravity anomalies in the multidimensional feature vector set exceeds a preset threshold, then the groundwater type and oil-gas mixing ratio are classified by support vector machine, and combined with the trajectory starting point and deviation amplitude quantification results, fluid dynamic classification results are generated. Step S3: Interpolate the fluid dynamic classification results to generate continuous fluid dynamic data; determine the migration path sequence based on the dynamic data, fuse real-time monitoring signals, calculate velocity and direction changes, and generate a permeability distribution map to characterize the fluid dynamic change trend; Step S4: Extract abnormal deviation areas based on the dynamic change trend and match them with historical geological data. If the temperature gradient correlation analysis results contain pressure fluctuation patterns, mark the area as a geological anomaly point. Based on the geological anomaly point, construct an anomaly distribution map and extract the block network connection relationship. Based on this, establish and generate a geological flow monitoring report according to the dynamic model. Step S5: Based on the geological flow monitoring report, determine whether there are changes in groundwater type or abnormal oil and gas mixing ratio; if so, identify pressure fluctuation patterns and generate a refined geological anomaly point distribution map.

[0007] As a preferred embodiment of the present invention, in step S1, multi-source geological data corresponding to the mining area is acquired and preprocessed to obtain a standardized geological dataset, including: The process involves acquiring multi-source geological data corresponding to the mining area collected by drones and ground-based detection equipment, aligning the format and correcting resolution differences of the multi-source geological data, extracting the spatiotemporal correlation of the multi-source geological data, generating a multi-dimensional feature vector set, and performing standardization processing based on the multi-dimensional feature vector set to obtain a standardized geological dataset. The multi-source geological data includes the standardization process, which includes normalizing the feature vectors to unify the data scale.

[0008] As a preferred embodiment of the present invention, step S1, generating fluid dynamic classification results, includes: Calculate the correlation strength between magnetic anomalies and gravity anomalies in a multidimensional feature vector set, and determine whether the correlation strength exceeds a preset threshold. If the correlation strength exceeds the preset threshold, the groundwater type and oil and gas mixing ratio are classified by support vector machine. The support vector machine achieves classification by maximizing the margin hyperplane, and the input feature vector includes magnetic anomaly data and gravity anomaly data. The trajectory starting point coordinates of the fluid are fused with the deviation amplitude quantification results to generate a complete fluid dynamic classification result. The trajectory starting point coordinates are the starting geographical location of the fluid flow, and the deviation amplitude is the degree of deviation of the fluid path from the standard path. Based on the fluid dynamics classification results, cross-validation is used to verify the classification accuracy. If the accuracy exceeds a preset threshold, the reliability of the classification results is confirmed.

[0009] As a preferred embodiment of the present invention, step S3, determining the complete transport path sequence and calculating the dynamic change trend, includes: Identify missing data segments from the fluid dynamics classification results; fill in the missing data segments using an interpolation method to generate continuous fluid dynamics data; determine the complete transport path sequence based on the continuous fluid dynamics data; Extract fluid dynamic parameters from real-time monitoring signals; calculate the velocity change of the migration path sequence based on the fluid dynamic parameters; determine the directional change of the migration path sequence based on the velocity change; fuse the velocity change and directional change to generate a fluid dynamic feature vector; and generate a permeability distribution map based on the fluid dynamic feature vector to characterize the dynamic trend of fluid migration.

[0010] As a preferred embodiment of the present invention, step S4, determining the distribution of geological anomaly points, includes: Based on the fluid velocity and direction change data in the dynamic trend, fluid path regions with deviations greater than a set threshold are obtained and these regions are designated as abnormal deviation regions. The multidimensional feature vectors corresponding to the abnormal deviation regions are compared with magnetic and gravity anomaly data in the historical geological dataset to calculate similarity scores. Consistency is verified based on the similarity scores. Calculate the temperature gradient value within the abnormal deviation area, analyze the correlation coefficient between the temperature gradient and pressure data, extract the pressure fluctuation pattern based on the correlation coefficient, determine whether the extracted pressure fluctuation pattern matches the preset pattern library, if they match, mark the abnormal deviation area as a geological anomaly point, and generate an anomaly distribution map based on the geological anomaly point to characterize the spatial distribution of geological anomalies.

[0011] As a preferred embodiment of the present invention, step S4, generating a geological flow monitoring report, includes: Extract the block network connectivity from the distribution of the geological anomalies; construct a dynamic model based on the block network connectivity to predict future migration patterns; integrate the prediction results of the dynamic model to generate a risk level stratification assessment; adjust the management protocol based on the risk level stratification assessment to generate a customized geological flow monitoring report; verify the completeness of the geological flow monitoring report to ensure its accuracy and operability.

[0012] As a preferred embodiment of the present invention, updating the feature vector set based on the geological flow monitoring report includes: Extract the block network connection relationship from the geological flow monitoring report; determine whether the magnetic anomaly in the block network connection relationship indicates a change in the groundwater type; if a change in the groundwater type is indicated, align the real-time monitoring signal with historical geological data using a coordinate system; update the multidimensional feature vector set based on the alignment result; verify the spatiotemporal consistency of the updated multidimensional feature vector set to ensure data reliability.

[0013] As a preferred embodiment of the present invention, the step of determining the pressure fluctuation pattern and identifying the refined geological anomaly point distribution map includes: Extract the oil and gas mixing ratio and velocity direction changes from the updated multidimensional feature vector set; analyze the pressure fluctuation pattern in the permeability distribution map based on the oil and gas mixing ratio and velocity direction changes; identify the feature changes of the abnormal area through the pressure fluctuation pattern; determine the refined geological anomaly point distribution map based on the feature changes; verify the accuracy of the refined geological anomaly point distribution map to ensure its consistency with the actual geological features.

[0014] Secondly, the present invention also provides a comprehensive analysis system for geological information in mining areas based on data integration, for implementing the above-mentioned method, the system comprising: The data standardization unit is used to acquire multi-source geological data corresponding to the mining area, perform preprocessing, conduct feature correlation analysis on the preprocessed multi-source geological data, and obtain and normalize the multi-dimensional feature vectors to obtain a standardized geological dataset. The dynamic classification unit is used to classify the groundwater type and oil and gas mixing ratio by support vector machine if the correlation strength between magnetic anomaly and gravity anomaly in the multidimensional feature vector set exceeds a preset threshold, and to generate fluid dynamic classification results by combining the trajectory starting point and deviation amplitude quantification results. The trend acquisition unit is used to interpolate the fluid dynamic classification results to generate continuous fluid dynamic data; based on the dynamic data, it determines the migration path sequence, integrates real-time monitoring signals, calculates velocity and direction changes, and generates a permeability distribution map to characterize the fluid dynamic change trend. The report generation unit is used to extract abnormal deviation areas based on the dynamic change trend and match them with historical geological data. If the temperature gradient correlation analysis results contain pressure fluctuation patterns, the area is marked as a geological anomaly point. Based on the geological anomaly point, an anomaly distribution map is constructed, and the block network connection relationship is extracted. Based on this, a geological flow monitoring report is established and generated according to the dynamic model. The distribution map refinement unit is used to determine whether there are changes in groundwater type or abnormal oil and gas mixing ratios based on geological flow monitoring reports; if so, it identifies pressure fluctuation patterns and generates a refined geological anomaly point distribution map.

[0015] Thirdly, the present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0016] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention acquires and preprocesses multi-source geological data from mining areas, aligning and resolving data collected by UAVs and ground-based detection equipment to obtain a standardized geological dataset. The extraction of spatiotemporal correlations provides an accurate foundation for subsequent analysis. Through feature correlation analysis, a multi-dimensional feature vector set is extracted from the standardized data, enabling the classification of groundwater types and hydrocarbon mixing ratios, providing data support for fluid dynamics analysis. Based on the fluid dynamics classification results, interpolation methods are used to fill in missing data, ensuring data integrity. Anomalies are identified by analyzing pressure fluctuation patterns in permeability distribution mapping. Further calculations are performed by combining real-time monitoring signals and historical geological data. Changes in velocity and direction generate a mapping of fluid dynamics, which in turn predicts fluid migration patterns through dynamic models, generates permeability distribution maps, and provides data support for subsequent risk assessments. Based on these dynamic trends, abnormal deviation areas are detected, pressure fluctuation patterns are determined through temperature gradient correlation analysis, geological anomalies are marked, and anomaly distribution maps are generated. Furthermore, by extracting block network connections, a dynamic model is constructed, ultimately generating a geological flow monitoring report. The synergy of these technical solutions ensures the high accuracy and practicality of the mining area geological information monitoring report, effectively identifying anomalies and providing dynamic predictions under different geological environments. This contributes to the optimized management of mining resources and early warning of potential risks. Attached Figure Description

[0017] Figure 1 This is a flowchart of the comprehensive analysis method for geological information in mining areas based on data integration, as described in this embodiment of the invention. Figure 2 This is a structural diagram of a comprehensive geological information analysis system for mining areas based on data integration, as described in an embodiment of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1 The comprehensive analysis method for geological information in mining areas based on data integration in this embodiment may specifically include: Step S1: Obtain multi-source geological data corresponding to the mining area and perform preprocessing. Perform feature association analysis on the preprocessed multi-source geological data to obtain and normalize the multi-dimensional feature vectors to obtain a standardized geological dataset. Specifically, in Step S1, obtaining multi-source geological data corresponding to the mining area and performing preprocessing to obtain a standardized geological dataset includes: The process involves acquiring multi-source geological data corresponding to the mining area collected by UAVs and ground-based detection equipment, aligning the formats and correcting resolution differences of the multi-source geological data, extracting the spatiotemporal correlation of the multi-source geological data, generating a multi-dimensional feature vector set, and performing standardization processing based on the multi-dimensional feature vector set to obtain a standardized geological dataset. The multi-source geological data includes aerial geological images, magnetic field data, and underground gravity anomaly data. The standardization processing includes normalizing the feature vectors to unify the data scale.

[0020] Specifically, in this embodiment, multi-source geological data of the mining area is collected from drones and ground-based detection equipment. This data includes aerial geological images, magnetic field anomaly data, and underground gravity anomaly data. Magnetic field data shows magnetic differences in underground rock strata; when the measured magnetic field strength deviates significantly from the normal range, it is generally considered magnetic anomaly data. Underground gravity data is used to detect density differences in underground materials. Measurements above or below the normal gravity value range can be considered gravity anomaly data. Through this multi-source geological data, a comprehensive understanding of the geological characteristics of the mining area can be achieved. The multi-source geological data undergoes format alignment and resolution difference correction to eliminate differences in format and resolution between different data sources, enabling unified analysis of data from different sources within the same coordinate system. Spatiotemporal correlation is extracted from the multi-source geological data. Spatiotemporal correlation refers to the dependence of data in time and space, thereby improving the accuracy of geological feature and fluid movement analysis. Based on the spatiotemporally correlated multi-source geological data, a multi-dimensional feature vector set is generated. This set contains features extracted from various types of geological data, including magnetic field anomaly data, gravity anomaly data, and corresponding time and location information, laying the foundation for subsequent monitoring of the geological structure of the mining area.

[0021] The generated set of multidimensional feature vectors is standardized to obtain a standardized geological dataset. The standardization process includes normalizing the feature vectors, ensuring comparability of different features at the same data scale, thereby eliminating analytical errors caused by scale differences. Through normalization, all feature vectors are adjusted to a uniform range, ensuring data consistency and stability in subsequent processing and providing reliable data support for subsequent geological analysis and fluid dynamic monitoring.

[0022] Step S2: Calculate the correlation strength between magnetic anomalies and gravity anomalies in the multidimensional feature vector set. If the correlation strength exceeds a preset threshold, classify the groundwater type and oil-gas mixing ratio using a support vector machine, and generate fluid dynamic classification results by combining the trajectory starting point and deviation amplitude quantization results; specifically including: Calculate the correlation strength between magnetic anomalies and gravity anomalies in a multidimensional feature vector set, and determine whether the correlation strength exceeds a preset threshold. If the correlation strength exceeds the preset threshold, the groundwater type and oil and gas mixing ratio are classified by support vector machine. The support vector machine achieves classification by maximizing the margin hyperplane, and the input feature vector includes magnetic anomaly data and gravity anomaly data. The trajectory starting point coordinates of the fluid are fused with the deviation amplitude quantification results to generate a complete fluid dynamic classification result. The trajectory starting point coordinates are the starting geographical location of the fluid flow, and the deviation amplitude is the degree of deviation of the fluid path from the standard path. Based on the fluid dynamics classification results, cross-validation is used to verify the classification accuracy. If the accuracy exceeds a preset threshold, the reliability of the classification results is confirmed.

[0023] Specifically, in the geological environment of mining areas, magnetic anomalies and gravity anomalies are two important geological features that are often used to identify the presence and distribution of underground fluids. Magnetic anomalies are usually caused by differences in the magnetic properties of rocks, while gravity anomalies reflect differences in the density of underground materials. Traditional methods usually treat these two separately, making it difficult to combine them effectively as a whole. By calculating the correlation between them, the distribution and dynamic changes of underground fluids can be determined more accurately. Especially in geological exploration in mining areas, the high correlation between magnetic anomalies and gravity anomalies often indicates the presence of oil and gas mixtures.

[0024] The linear correlation between magnetic anomalies and gravity anomalies is measured by calculating the Pearson correlation coefficient. This correlation coefficient reflects the strength of the linear relationship between the two features. The correlation measure is obtained by first calculating the covariance between the two features and dividing it by the product of their respective standard deviations. When the absolute value of the calculated Pearson correlation coefficient exceeds a preset threshold, it is determined that the correlation between magnetic anomalies and gravity anomalies is strong, indicating a significant correlation between them and suggesting the possible existence of potential oil and gas mixtures or geological anomalies in the area.

[0025] When the correlation between magnetic anomalies and gravity anomalies is strong, the aforementioned multidimensional feature vectors are used as input data to a support vector machine (SVM) model to classify groundwater types and hydrocarbon mixing ratios. SVM is a classification algorithm based on finding the maximum margin hyperplane, which can effectively handle nonlinear data. Specifically, an SVM model is constructed, and the aforementioned multidimensional feature vectors corresponding to the training dataset are used as input data. The SVM is trained to obtain a classification model that can accurately classify groundwater types, such as freshwater or saline water, and estimate hydrocarbon mixing ratios. The training dataset includes known groundwater types and corresponding hydrocarbon mixing ratios, such as saline and freshwater, and combines feature data including magnetic and gravity anomalies. Through the learning of the SVM model, the final output is a classification label and the corresponding hydrocarbon mixing ratio.

[0026] Subsequently, when generating the fluid dynamic classification results, the starting coordinates of the fluid's trajectory (i.e., the water body) and the deviation amplitude are further fused, and the deviation amplitude, i.e., the degree of deviation of the fluid path from the standard path, is quantified. The fluid's starting coordinates, such as latitude and longitude, are collected, and its path changes are measured, thereby generating a dynamic description of geological fluid movement. The oil and gas ratio and path deviation output by the support vector machine are used to describe the dynamic changes of the geological fluid, ensuring the integrity and accuracy of the geological fluid migration path.

[0027] Step S3: Interpolate the fluid dynamics classification results to generate continuous fluid dynamics data; determine the migration path sequence based on the dynamics data, fuse real-time monitoring signals, calculate velocity and direction changes, and generate a permeability distribution map to characterize the fluid dynamics trend; specifically including: Identify missing data segments from the fluid dynamics classification results; fill in the missing data segments using an interpolation method to generate continuous fluid dynamics data; determine the complete transport path sequence based on the continuous fluid dynamics data; Extract fluid dynamic parameters from real-time monitoring signals; calculate the velocity change of the migration path sequence based on the fluid dynamic parameters; determine the directional change of the migration path sequence based on the velocity change; fuse the velocity change and directional change to generate a fluid dynamic feature vector; and generate a permeability distribution map based on the fluid dynamic feature vector to characterize the dynamic trend of fluid migration.

[0028] Specifically, in this embodiment, by traversing the spatiotemporal sequence in the multidimensional feature vector set corresponding to the above classification results, when the time or spatial interval between adjacent data points exceeds a preset threshold, it is marked as a missing data segment. In order to fill in these missing parts, an interpolation method is used to process them to generate a continuous fluid dynamic data sequence. Based on the above continuous fluid dynamic data sequence, it is checked whether the filled fluid dynamic data sequence forms a closed chain. If all segments are connected without interruption, it is considered a complete path, which ensures the continuity of data and the integrity of the path sequence, thereby providing accurate data support for subsequent dynamic analysis.

[0029] Subsequently, real-time monitoring signals are integrated, and the velocity and direction of the fluid's corresponding migration path sequence are calculated based on these signals. Specifically, the trajectory starting point coordinates collected by the UAV are superimposed with signals from ground equipment. Alignment processing of the coordinate systems resolves resolution differences, ensuring accurate signal matching between different sources. After alignment, vector difference is used to quantify the deviation amplitude between path points and calculate velocity changes. The velocity calculation formula is the distance between adjacent points divided by the time difference. Directional changes are obtained by calculating the vector angle, using the cosine formula to ensure that the path's directional changes accurately reflect the fluid's dynamic characteristics. This not only considers the impact of the oil-gas mixing ratio on fluid dynamics but also effectively captures subtle fluctuations during fluid migration, thus providing early prediction of abnormal areas.

[0030] Based on the calculated changes in fluid velocity and direction, a permeability distribution map is further generated to characterize the dynamic trend of fluid migration. Kriging interpolation is used to estimate the permeability distribution. First, a two-dimensional grid is constructed, with velocity and direction as input parameters. Based on a variogram model, Kriging interpolation is used to calculate the covariance between points to predict the permeability value at unknown points. The variogram model is calculated using the following formula: γ(h) = C0 + C(1 - exp(-h / a)), where C0 is the nugget effect, C is the sill value, a is the range parameter, and h is the distance between points. This generates a dynamically changing permeability distribution map, visually representing the changing trends of permeability in different regions. For example, when a certain direction changes frequently and the permeability map shows a steep gradient, it can be marked as a potential risk area, thus supporting subsequent risk assessment and management strategy formulation.

[0031] The above technical solution fills in the missing data through interpolation, enabling the fluid dynamic data to fully reflect the fluid migration path. It also ensures the spatiotemporal consistency of the data by fusing real-time monitoring signals with historical data to calculate changes in speed and direction. The generation of the permeability distribution mapping depends on the speed and direction changes in the previous step. Through Kriging interpolation, this dynamic information is transformed into actual geological change trends, thus providing an accurate and dynamic visualization tool for the entire geological information monitoring.

[0032] Step S4: Extract abnormal deviation areas based on the dynamic change trend and match them with historical geological data. If the temperature gradient correlation analysis results contain pressure fluctuation patterns, mark the area as a geological anomaly point. Based on the geological anomaly point, construct an anomaly distribution map and extract the block network connection relationship. Based on this, establish and generate a geological flow monitoring report according to the dynamic model. In step S4, determining the distribution of geological anomalies includes: Based on the fluid velocity and direction change data in the dynamic trend, fluid path regions with deviations greater than a set threshold are obtained and these regions are designated as abnormal deviation regions. The multidimensional feature vectors corresponding to the abnormal deviation regions are compared with magnetic and gravity anomaly data in the historical geological dataset to calculate similarity scores. Consistency is verified based on the similarity scores. Calculate the temperature gradient value within the abnormal deviation area, analyze the correlation coefficient between the temperature gradient and pressure data, extract the pressure fluctuation pattern based on the correlation coefficient, determine whether the extracted pressure fluctuation pattern matches the preset pattern library, if they match, mark the abnormal deviation area as a geological anomaly point, and generate an anomaly distribution map based on the geological anomaly point to characterize the spatial distribution of geological anomalies.

[0033] Specifically, in this embodiment, the process of determining the distribution of geological anomalies first relies on fluid velocity and direction change data within the dynamic trend. This is achieved by identifying path regions with deviations exceeding a set threshold, and these path regions are then considered as abnormal deviation areas. In this process, the set threshold is typically based on the statistical average of historical geological data. For example, the deviation threshold could be set to a 10% deviation of the fluid velocity change. This ensures that we capture areas with significant dynamic changes, which may indicate geological anomalies.

[0034] Next, these anomalous deviation areas are further analyzed. Magnetic and gravity anomaly data from their corresponding multidimensional feature vectors are compared with those from historical geological datasets to calculate similarity scores. The consistency of the data is then verified based on these similarity scores. If the similarity score is higher than a set threshold, the current anomalous deviation area is considered consistent with historical geological data, further confirming it as a potential geological anomaly area. This step ensures that the anomalous deviation area not only exhibits significant dynamic changes but also maintains consistency with historical data, thereby improving the accuracy of anomaly detection.

[0035] Furthermore, temperature gradient correlation analysis is used to conduct a more in-depth examination of abnormal deviation areas. The temperature gradient value within the abnormal deviation area is calculated. The temperature gradient refers to the rate of temperature change per unit distance. The temperature gradient value of the cedar tree can be obtained by dividing the temperature difference between adjacent monitoring points by the distance. Then, the correlation coefficient between the temperature gradient and pressure data is analyzed using the Pearson correlation coefficient formula. The Pearson correlation coefficient can measure the strength of the linear relationship between two variables. If the absolute value of the calculated correlation coefficient is greater than the set similarity, it is considered that there is a strong correlation between the temperature gradient and pressure data in this area, and obvious pressure fluctuation patterns can be extracted.

[0036] Furthermore, Fourier transform analysis is used to analyze the periodic changes of pressure fluctuation patterns, thereby identifying the fluctuation frequency and determining whether the extracted pressure fluctuation patterns match a preset pattern library. If the extracted fluctuation pattern matches a certain pattern in the pattern library, such as sinusoidal waveform fluctuation, it is confirmed that the region contains a pressure fluctuation pattern, thus marking the abnormal deviation area as a geological anomaly point. This helps to identify potential geological anomalies in depth and provide early signals for geological disaster warning.

[0037] Finally, based on the marked geological anomalies, an anomaly distribution map is generated to characterize the spatial distribution of geological anomalies. This map is populated with spatial data of geological anomalies using interpolation methods, such as Kriging interpolation. Kriging interpolation is a geostatistical method based on variograms, which estimates the values ​​of unknown points by calculating the covariance between points, ensuring that the anomaly distribution map reflects the spatial distribution of geological anomalies. For example, when generating the anomaly distribution map, if geological anomalies are found to be concentrated in a certain coordinate region, Kriging interpolation will extend the anomalies in that region to the surrounding grid, thus visually demonstrating the connectivity and spatial characteristics of the anomalies and supporting subsequent analysis of block network connections.

[0038] The above-mentioned technical solution, by combining the analysis of fluid dynamic data, historical geological data, temperature gradients and pressure fluctuation patterns, can accurately identify and mark geological anomalies, and generate anomaly distribution maps through interpolation methods, further providing reliable spatial data support for geological information monitoring and risk assessment.

[0039] Furthermore, a geological flow monitoring report is generated, including: The coordinates of each geological anomaly are extracted from the distribution of the anomalies. The spatial distance between the anomalies and the correlation strength between the corresponding magnetic and gravity anomalies are calculated. Based on the spatial distance and the correlation strength, the block network connection relationship is obtained. Using the anomalies as nodes and the correlation strength as edges, a dynamic model is constructed by incorporating the velocity and direction change data from the fluid dynamic classification results to predict the future migration patterns of the fluid. Based on the prediction results of the dynamic model, a risk level stratification assessment is generated. Based on the risk level stratification assessment, the management protocol is adjusted to generate a customized geological information monitoring report. The completeness of the geological information monitoring report is verified to ensure its accuracy and operability.

[0040] Specifically, in this embodiment, the coordinates of each anomaly point in the geological anomaly distribution map are identified, and the spatial distance and correlation strength between the anomalies are calculated. The correlation strength is determined by the correlation value between magnetic anomalies and gravity anomalies, which ensures that the spatial relationship between geological anomalies is accurately modeled and provides the necessary input for the subsequent construction of dynamic models.

[0041] Based on the extracted block network connections, a grid model is constructed using the finite element method. In this model, geological anomalies are used as nodes, and correlation strength is used as edges. Velocity and direction change data from fluid dynamic classification results are incorporated into the model. Based on this grid model, time series analysis is used to predict the migration path changes between nodes. The time series analysis uses the autoregressive integral moving average (ARIMA) model to process historical geological data sequences, which can not only obtain the predicted fluid dynamic change trend, but also effectively predict the future migration pattern of fluids, especially the flow trend of oil and gas or groundwater in mining areas.

[0042] Furthermore, real-time monitoring signals are integrated to adjust model parameters to simulate the evolution of oil and gas mixing ratios, ensuring that the model can accurately capture pressure fluctuation patterns. This allows the model to reflect actual fluid dynamic changes at different time steps, improving prediction accuracy and enabling the dynamic model to cope with uncertainties and complexities in oil and gas or groundwater flows.

[0043] Based on the prediction results of the aforementioned dynamic model, a risk level stratification assessment is generated. This assessment quantifies the risk value by comparing the predicted migration patterns with historical geological data, and classifies the risk into high-risk, medium-risk, and low-risk levels according to the degree of prediction deviation. Based on the assessment results for high-risk areas, monitoring frequency parameters are adjusted; for example, the monitoring frequency is increased from once a day to once an hour, and a custom alarm threshold is defined. Furthermore, the stratified assessment results are integrated to generate a report template, which is filled with anomaly distribution maps and predicted trend data. For medium-risk areas, the deviation magnitude of the permeability mapping in the protocol is adjusted and set to not exceed a predetermined value, ensuring that the report reflects real-time adjustments. This allows for the development of targeted response measures based on different risk levels, enhancing the report's operability and practicality.

[0044] Finally, the completeness of the geological information monitoring report is verified to ensure its accuracy and operability. Specifically, all data fields in the report are checked for completeness and compared with a standardized geological dataset. If the match rate of the report content reaches or exceeds a set limit, the report is confirmed as valid. This verification step ensures the accuracy and reliability of the report, enabling the final monitoring report to provide robust data support for subsequent geological analysis and decision-making.

[0045] The above technical solution extracts the block network connection relationship from the distribution of geological anomalies, constructs a dynamic model to predict future fluid migration patterns, and combines it with real-time monitoring signals for adjustment, ultimately generating a customized geological information monitoring report, providing accurate prediction and scientific decision support for the comprehensive analysis of geological information in mining areas.

[0046] Further, the feature vector set is updated based on the geological flow monitoring report, including: Extract the block network connection relationship from the geological flow monitoring report; determine whether the magnetic anomaly in the block network connection relationship indicates a change in the groundwater type; if a change in the groundwater type is indicated, align the real-time monitoring signal with historical geological data using a coordinate system; update the multidimensional feature vector set based on the alignment result; verify the spatiotemporal consistency of the updated multidimensional feature vector set to ensure data reliability.

[0047] Specifically, in this embodiment, anomaly distribution map data is read from the aforementioned geological flow monitoring report, and the network connection relationship between blocks is parsed out. Nodes and edges represent the geological correlation between blocks, providing a key data structure foundation for subsequent analysis and ensuring accurate modeling of the relationship between geological anomaly points. Based on the extracted block network connection relationship, it is determined whether the magnetic anomaly indicates a change in groundwater type. This is achieved by calculating the correlation strength between the magnetic anomaly value on each connection edge and the groundwater type index. The magnetic anomaly value is obtained through a magnetic measurement device, reflecting the deviation of the underground magnetic field. The groundwater type index includes classification labels for saline water, fresh water, or polluted water. When the correlation strength exceeds a preset threshold, it is determined that a change in groundwater type is indicated; otherwise, it is considered that no change has occurred. This helps to identify the dynamic evolution of underground fluids in a timely manner during geological monitoring, providing an important basis for subsequent data updates and monitoring.

[0048] If the judgment results indicate a change in the groundwater type, the real-time monitoring signal and historical geological data are aligned using a coordinate system alignment process. This involves converting the real-time monitoring signal and historical geological data to the same coordinate system to ensure spatial alignment. If there are differences in temporal resolution, linear interpolation is used to align the timestamps, making the data match in the spatiotemporal dimension and avoiding errors caused by spatiotemporal inconsistencies. The above coordinate alignment process is usually achieved through affine transformation. Rotation, scaling, and translation operations help minimize alignment errors, solve the problem of inconsistency in multi-source geological data, and improve the reliability of data fusion.

[0049] By fusing aligned real-time signals with historical data into the original feature vector set (e.g., adding magnetic and gravity anomaly dimensions), an updated vector set is generated. This ensures the feature vector set not only includes the original data but also incorporates the latest real-time monitoring information, providing more comprehensive and real-time data support. To ensure the reliability of the updated feature vector set, spatiotemporal consistency verification is performed. First, the spatiotemporal correlation coefficient of each feature vector in the updated vector set is calculated, and the Pearson correlation coefficient is used to evaluate the consistency of the time series. If the correlation coefficient is greater than a set value, it is considered consistent. Simultaneously, the Euclidean distance between vectors is calculated to check spatial consistency. If the distance is less than a preset threshold, spatial matching is confirmed. This technical solution ensures the temporal and spatial continuity of the data, effectively preventing data inconsistencies caused by noise or other interference factors, thereby improving the overall reliability of geological flow monitoring reports.

[0050] Step S5: Based on the geological flow monitoring report, determine whether there are changes in groundwater type or abnormal oil and gas mixing ratios; if so, identify pressure fluctuation patterns and generate a refined geological anomaly point distribution map; specifically including: Extract the oil and gas mixing ratio and velocity direction changes from the updated multidimensional feature vector set; analyze the pressure fluctuation pattern in the permeability distribution map based on the oil and gas mixing ratio and velocity direction changes; identify the feature changes of the abnormal area through the pressure fluctuation pattern; determine the refined geological anomaly point distribution map based on the feature changes; verify the accuracy of the refined geological anomaly point distribution map to ensure its consistency with the actual geological features.

[0051] Specifically, in this embodiment, vector components containing changes in oil-gas mixing ratio and velocity direction are selected from the updated multidimensional feature vector set. Based on the extracted oil-gas mixing ratio and velocity direction changes, the pressure fluctuation patterns in the permeability distribution map are analyzed. The permeability distribution map is a two-dimensional or three-dimensional grid map generated based on a geological dataset, where each grid point represents the permeability value of the rock layer. In this process, the oil-gas mixing ratio is used as a weighting factor to adjust the permeability value, and then the velocity direction change is used to correct the direction of pressure fluctuations. The pressure values ​​are then subjected to time-series analysis to identify the fluctuation period and amplitude. The pressure fluctuation pattern is defined by statistically analyzing the fluctuation frequency and peak value, such as calculating the standard deviation and mean deviation of the pressure. The analysis of these pressure fluctuation patterns can reveal the dynamic characteristics of underground fluid migration, help identify potential anomaly areas, and improve the accuracy of geological monitoring.

[0052] Based on the pressure fluctuation patterns obtained from the analysis, the next step is to identify the characteristic changes in abnormal areas. By applying threshold comparisons, areas where the fluctuation amplitude exceeds the average value are marked, and then the characteristic changes in these areas, such as temperature correlation or density variation, are extracted. Characteristic changes are identified by comparing the difference between the current fluctuation pattern and the historical baseline pattern. The degree of difference between the two patterns is calculated using Euclidean distance to quantify the degree of change. For example, if the pressure fluctuation pattern shows periodic interruptions, it is considered a characteristic change. The degree of change is further quantified, which can effectively distinguish between natural fluctuations and abnormal events, thereby improving the accuracy of geological anomaly detection and the reliability of monitoring reports.

[0053] After identifying the characteristic changes, a more detailed geological anomaly distribution map is further determined based on these changes. By mapping the characteristic changes to a coordinate system and adjusting the boundaries and density of the anomalies, a more detailed distribution map is formed. This makes the location of the anomalies more accurate, which is helpful for further geological flow monitoring decisions and risk assessments. It also more clearly depicts the spatial distribution of geological anomalies, improving the relevance and reliability of the report, especially in complex oil and gas mixing environments in mining areas or groundwater monitoring scenarios. The accuracy of the detailed geological anomaly distribution map is verified to ensure its consistency with actual geological characteristics. Specifically, the detailed distribution map is compared with field sampling data, and the matching degree is calculated. If the matching degree reaches or exceeds a set level, the distribution map is confirmed to be valid. The above technical solution ensures the high accuracy of the geological anomaly distribution map, enabling the monitoring report to reflect the actual geological characteristics and ensuring its operability in subsequent applications.

[0054] This invention also provides a comprehensive geological information analysis system for mining areas based on data integration, used to implement the above-mentioned methods, such as... Figure 2 As shown, the system includes: The data standardization unit is used to acquire multi-source geological data corresponding to the mining area, perform preprocessing, conduct feature correlation analysis on the preprocessed multi-source geological data, and obtain and normalize the multi-dimensional feature vectors to obtain a standardized geological dataset. The dynamic classification unit is used to classify the groundwater type and oil and gas mixing ratio by support vector machine if the correlation strength between magnetic anomaly and gravity anomaly in the multidimensional feature vector set exceeds a preset threshold, and to generate fluid dynamic classification results by combining the trajectory starting point and deviation amplitude quantification results. The trend acquisition unit is used to interpolate the fluid dynamic classification results to generate continuous fluid dynamic data; based on the dynamic data, it determines the migration path sequence, integrates real-time monitoring signals, calculates velocity and direction changes, and generates a permeability distribution map to characterize the fluid dynamic change trend. The report generation unit is used to extract abnormal deviation areas based on the dynamic change trend and match them with historical geological data. If the temperature gradient correlation analysis results contain pressure fluctuation patterns, the area is marked as a geological anomaly point. Based on the geological anomaly point, an anomaly distribution map is constructed, and the block network connection relationship is extracted. Based on this, a geological flow monitoring report is established and generated according to the dynamic model. The distribution map refinement unit is used to determine whether there are changes in groundwater type or abnormal oil and gas mixing ratios based on geological flow monitoring reports; if so, it identifies pressure fluctuation patterns and generates a refined geological anomaly point distribution map.

[0055] The present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0056] In summary, this invention acquires and preprocesses multi-source geological data from mining areas, aligns and corrects the resolution of data collected by UAVs and ground-based detection equipment to obtain a standardized geological dataset. The extraction of spatiotemporal correlations provides an accurate foundation for subsequent analysis. Through feature correlation analysis, a multi-dimensional feature vector set is extracted from the standardized data, enabling the classification of groundwater types and hydrocarbon mixing ratios, providing data support for fluid dynamics analysis. Based on the fluid dynamics classification results, interpolation methods are used to fill in missing data, ensuring data integrity. Furthermore, by analyzing pressure fluctuation patterns in the permeability distribution mapping, abnormal areas are identified. By combining real-time monitoring signals and historical geological data, further calculations are performed... The system calculates changes in velocity and direction to generate a mapping of fluid dynamics trends. Through dynamic models, it predicts fluid transport patterns, generates permeability distribution maps, and provides data support for subsequent risk assessments. Based on these dynamic trends, it detects abnormal deviation areas, determines pressure fluctuation patterns through temperature gradient correlation analysis, marks geological anomalies, and generates anomaly distribution maps. Furthermore, by extracting block network connections, it constructs dynamic models and ultimately generates a geological flow monitoring report. The synergy of these technologies ensures the high accuracy and practicality of the mining area geological information monitoring report, effectively identifying anomalies and providing dynamic predictions under different geological environments. This contributes to the optimized management of mining resources and early warning of potential risks.

[0057] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the concept of this application. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A data integration-based comprehensive analysis method for mine geological information, characterized in that, Comprise: Step S1: Obtain the corresponding multi-source geological data of the mining area, and pre-process it. Perform feature correlation analysis on the pre-processed multi-source geological data, obtain and normalize the multi-dimensional feature vector to obtain a standardized geological data set; Step S2: If the correlation strength of the magnetic anomaly and gravity anomaly in the multi-dimensional feature vector set exceeds the preset threshold, classify the groundwater type and oil-gas mixing ratio by support vector machine, and combine the trajectory starting point and deviation amplitude quantification result to generate the fluid dynamic classification result; Step S3: Interpolate the fluid dynamic classification result to generate continuous fluid dynamic data; Based on the dynamic data, determine the migration path sequence, fuse the real-time monitoring signal, calculate the speed and direction change, and generate a permeability distribution map to represent the fluid dynamic change trend; Step S4: According to the dynamic change trend, extract the abnormal deviation area, and match it with the historical geological data. If the temperature gradient correlation analysis result contains a pressure fluctuation mode, mark the area as a geological anomaly point. Based on the geological anomaly point, construct an anomaly distribution map and extract the block network connection relationship. According to the dynamic model, a geological flow monitoring report is generated; Step S5: According to the geological flow monitoring report, determine whether there is a change in groundwater type or an abnormal oil-gas mixing ratio. If so, identify the pressure fluctuation mode and generate a refined geological anomaly point distribution map.

2. The method of claim 1, wherein, In step S1, the corresponding multi-source geological data of the mining area is obtained and pre-processed to obtain a standardized geological data set, including: Obtain the multi-source geological data of the mining area collected by unmanned aerial vehicles and ground detection equipment. Align the format and correct the resolution difference of the multi-source geological data. Extract the spatio-temporal correlation of the multi-source geological data to generate a multi-dimensional feature vector set. Standardize the multi-dimensional feature vector set to obtain a standardized geological data set. The multi-source geological data includes the standardized processing, which includes normalizing the feature vector to unify the data scale.

3. The method of claim 1, wherein, In step S1, the fluid dynamic classification result is generated, including: Calculate the correlation strength between the magnetic anomaly and the gravity anomaly in the multi-dimensional feature vector set, and determine whether the correlation strength exceeds the preset threshold; If the correlation strength exceeds the preset threshold, classify the groundwater type and oil-gas mixing ratio by support vector machine. The support vector machine realizes classification by maximizing the interval hyperplane, and the input feature vector includes magnetic anomaly data and gravity anomaly data; Fuse the trajectory starting point coordinates and deviation amplitude quantification result to generate a complete fluid dynamic classification result. The trajectory starting point coordinates are the starting geographical position of fluid flow, and the deviation amplitude is the deviation degree of the fluid path relative to the standard path; According to the fluid dynamic classification result, use the cross-validation method to verify the classification accuracy. If the accuracy exceeds the preset threshold, the reliability of the classification result is confirmed.

4. The method of claim 1, wherein, In step S3, the complete migration path sequence is determined and the dynamic change trend is calculated, including: Identify missing data paragraphs from the fluid dynamic classification results; fill in the missing data paragraphs using an interpolation method to generate continuous fluid dynamic data; determine a complete migration path sequence based on the continuous fluid dynamic data; Extract fluid dynamic parameters from real-time monitoring signals; calculate the speed change of the migration path sequence based on the fluid dynamic parameters; determine the direction change of the migration path sequence through the speed change; fuse the speed change and direction change to generate a fluid dynamic feature vector, and generate a permeability distribution map based on the fluid dynamic feature vector to represent the dynamic change trend of fluid migration.

5. The method of claim 1, wherein, In step S4, the distribution of geological anomaly points is determined, including: According to the fluid velocity and direction change data in the dynamic change trend, and obtaining the fluid path region with a deviation amplitude greater than a set threshold, and taking the path region as an abnormal deviation region; comparing the multi-dimensional feature vector corresponding to the abnormal deviation region with the magnetic anomaly and gravity anomaly data in the historical geological data set, calculating the similarity score, and verifying the consistency according to the similarity score; Calculate the temperature gradient value in the abnormal deviation region, and correlation analyze the correlation coefficient of the temperature gradient and the pressure data, and extract the pressure fluctuation mode according to the correlation coefficient, and judge whether the extracted pressure fluctuation mode matches the preset mode library, if it matches, mark the abnormal deviation region as a geological anomaly point, and generate an abnormal distribution map based on the geological anomaly point to represent the spatial distribution of the geological anomaly.

6. The method of claim 5, wherein, In step S4, a geological flow monitoring report is generated, including: Extract the block network connection relationship from the distribution of geological anomaly points; build a dynamic model to predict future migration rules according to the block network connection relationship; fuse the prediction results of the dynamic model to generate a risk level hierarchical evaluation; adjust the management protocol according to the risk level hierarchical evaluation to generate a customized geological flow monitoring report; verify the integrity of the geological flow monitoring report to ensure its accuracy and operability.

7. The method of claim 6, wherein, Update the feature vector set according to the geological flow monitoring report, including: Extract the block network connection relationship from the geological flow monitoring report; determine whether the magnetic anomaly in the block network connection relationship shows the change of underground water body type; if it shows the change of underground water body type, align the real-time monitoring signal and the historical geological data through the coordinate system; update the multi-dimensional feature vector set according to the alignment result; verify the spatiotemporal consistency of the updated multi-dimensional feature vector set to ensure the data reliability.

8. The method of claim 1, wherein, Determine the refined geological anomaly point distribution map by judging the pressure fluctuation mode, including: Extract the oil-gas mixing ratio and speed direction change from the updated multi-dimensional feature vector set; analyze the pressure fluctuation mode in the permeability distribution map according to the oil-gas mixing ratio and speed direction change; identify the characteristic change of the abnormal region through the pressure fluctuation mode; determine the refined geological anomaly point distribution map according to the characteristic change; verify the accuracy of the refined geological anomaly point distribution map to ensure its consistency with the actual geological features.

9. A data integration-based comprehensive analysis system for geological information of a mining area, for implementing the method according to any one of claims 1-8, characterized in that, The system includes: The data standardization unit is configured to acquire multi-source geological data corresponding to a mining area, pre-process the multi-source geological data, perform feature correlation analysis on the pre-processed multi-source geological data, acquire a multi-dimensional feature vector, and normalize the multi-dimensional feature vector to obtain a standardized geological data set; The dynamic classification unit is configured to, if the correlation strength of the magnetic anomaly and the gravity anomaly in the multi-dimensional feature vector set exceeds a preset threshold, classify the groundwater type and the oil-gas mixing ratio by using a support vector machine, combine the trajectory starting point and the deviation amplitude quantization result, and generate a fluid dynamic classification result; The trend acquisition unit is configured to interpolate the fluid dynamic classification result to generate continuous fluid dynamic data, determine a migration path sequence based on the dynamic data, fuse a real-time monitoring signal, calculate a speed and a direction change, generate a permeability distribution map to represent a fluid dynamic change trend, and output the fluid dynamic change trend. The report generation unit is configured to extract an abnormal deviation area according to the dynamic change trend, match the abnormal deviation area with historical geological data, mark the area as a geological anomaly point if the temperature gradient correlation analysis result contains a pressure fluctuation mode, construct an abnormal distribution map based on the geological anomaly point, extract a block network connection relationship, establish a dynamic model according to the block network connection relationship, and generate a geological flow monitoring report. The distribution map refinement unit is configured to determine whether there is a change in the groundwater type or an abnormality in the oil-gas mixing ratio according to the geological flow monitoring report, identify a pressure fluctuation mode if there is a change in the groundwater type or an abnormality in the oil-gas mixing ratio, and generate a refined geological anomaly point distribution map.

10. A computer-readable storage medium having stored thereon instructions, the instructions comprising, The instructions are executed by the processor to implement the method of any one of claims 1-8.

Images