Comprehensive evaluation method of mine geological hazards considering spatial distribution characteristics

Abstract

The present invention relates to the technical field of geological disaster assessment, and in particular to a comprehensive assessment method for the risk of geological disasters in mines that takes into account spatial distribution characteristics. The method comprises the following steps: obtaining multi-source spatial data of mines; performing a distribution analysis of geological disaster risks in mines on the multi-source spatial data of mines to generate a distribution map of geological hazards in mines; performing a spatial regional potential disaster probability analysis on the distribution map of geological hazards in mines to generate geological distribution probability data of disasters in mines; and performing high-complexity spatial regional screening on the distribution map of geological hazards in mines using the geological distribution probability data of disasters in mines to obtain high-complexity spatial regional data. The present invention improves the accuracy and comprehensiveness of the comprehensive assessment of the risk of geological disasters in mines by integrating multi-source data, emphasizing spatial distribution characteristics, distinguishing between active and inactive areas, and analyzing ecological and water changes.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster assessment, and in particular to a comprehensive assessment method for the risk of geological disasters in mines taking into account spatial distribution characteristics. Background Art

[0002] As early as the 20th century, geological disaster research mainly focused on theoretical discussions and case analysis of disaster mechanisms, lacking a systematic approach. With the advancement of science and technology, the rise of remote sensing technology and geographic information systems (GIS) has provided new means for monitoring geological disasters in mines, enabling spatial analysis of geological features over a wide range. After entering the 21st century, comprehensive evaluation methods based on quantitative evaluation have gradually gained attention. Researchers began to apply multi-factor analysis methods to comprehensively consider multiple factors such as geology, topography, and meteorology, and formed evaluation models based on fuzzy mathematics and the analytic hierarchy process (AHP). These models improve the accuracy of evaluation by quantifying the impact of different factors. In recent years, the application of machine learning and big data technology has provided a new perspective for the assessment of geological disasters in mines. By analyzing massive historical data, it is possible to more accurately identify potential danger areas, thereby achieving dynamic monitoring and early warning. However, in many current assessments, there is no effective distinction between active and inactive areas of mines, which can easily lead to high-risk areas not being identified, thus affecting the effectiveness of disaster prevention decisions. At the same time, most evaluation methods rely too much on quantitative or qualitative analysis, and lack a multi-dimensional assessment that comprehensively considers multiple influencing factors, resulting in low accuracy and comprehensiveness in the comprehensive evaluation of the risk of geological hazards in mines. Summary of the invention

[0003] Based on this, it is necessary to provide a comprehensive evaluation method for the risk of mining geological hazards taking into account the spatial distribution characteristics to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics is provided, the method comprising the following steps:

[0005] Step S1: Acquire multi-source spatial data of mines; perform mine geological disaster risk distribution analysis on the mine multi-source spatial data to generate a mine geological hazard distribution map; perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data;

[0006] Step S2: screening the mine geological hazard distribution map with high complexity spatial regions through the mine geological distribution disaster probability data to obtain high complexity spatial region data; dividing the mine activity region data into mine activity regions and generating mine inactivity regions and mine inactivity regions; performing surface comprehensive deformation analysis on the mine activity region to generate comprehensive surface deformation data of the mine activity region;

[0007] Step S3: collect regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine; perform vegetation change dynamic analysis on the remote sensing images of the inactive area of ​​the mine to generate ecological change data of the inactive area; perform water body range change analysis on the remote sensing images of the inactive area of ​​the mine to generate water body range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data of the inactive area and the water body range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine;

[0008] Step S4: Conduct a comprehensive evaluation of the geological hazard risk of mines based on the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area to generate comprehensive evaluation data of the geological hazard risk of mines with high complexity; visualize the comprehensive evaluation data of the geological hazard risk of mines with high complexity to generate a comprehensive evaluation report of the geological hazard risk of mines with high complexity.

[0009] The present invention forms a global view of the geological conditions of the mine by acquiring multi-source spatial data of the mine. Such data integration ensures the comprehensiveness of the assessment, can reflect the potential geological disaster risks of the mine, and the generated mine geological hazard distribution map provides an intuitive risk assessment tool for mine managers to help them quickly identify high-risk areas. By analyzing the probability of potential disasters in the spatial area of ​​the mine geological hazard distribution map, the potential risks can be quantified, which provides data support for subsequent decision-making. The high-complexity spatial area screening in step S2 can help managers identify the areas that need the most attention, which are usually faced with higher geological disaster risks, and contribute to the effective allocation of resources. The division of mine activity areas and inactive areas enables managers to formulate different management strategies and emergency measures in a targeted manner. In step S2, the comprehensive deformation analysis of the surface of the mine activity area is carried out, which helps to monitor geological changes in time and warn of potential geological disasters. Step S3 analyzes ecological changes through remote sensing images, which can help managers understand the environmental dynamics of the inactive area of ​​the mine and provide a basis for ecological restoration and protection. The analysis of changes in the range of water bodies enables managers to understand the impact of mine activities on water resources, and then formulate corresponding water resource management measures. Step S4 conducts risk assessment by integrating surface deformation data and environmental suitability data, and the generated visualization report makes complex data easy to understand and helps managers make scientific decisions. The comprehensive evaluation data and visualization results provide a scientific basis for the emergency management of mines, so that managers can quickly formulate response strategies when emergencies occur. By identifying active and inactive areas of mines and assessing their geological risks, managers can allocate resources more reasonably and improve management efficiency. Therefore, the present invention improves the accuracy and comprehensiveness of the comprehensive evaluation of the risk of geological hazards in mines by integrating multi-source data, emphasizing spatial distribution characteristics, distinguishing between active and inactive areas, and analyzing ecological and water changes.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire multi-source spatial data of mines;

[0012] Step S12: preprocessing the mine multi-source spatial data to generate standard mine multi-source spatial data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0013] Step S13: Based on GIS technology, the mine geological disaster risk distribution analysis is performed on the standard mine multi-source spatial data to generate a mine geological risk distribution map;

[0014] Step S14: Perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data.

[0015] The present invention ensures the quality of multi-source spatial data of mines through data preprocessing (data cleaning, denoising, missing value filling and standardization). This high-quality data provides a reliable basis for subsequent analysis and decision-making, and reduces the analysis errors caused by data problems. By analyzing the standard multi-source spatial data of mines through GIS technology, the distribution of geological disaster hazards in the mine area can be accurately identified. This provides managers with a clear visualization tool, enabling them to quickly identify potential dangerous areas and take necessary preventive measures. The spatial regional potential disaster probability analysis of the mine geological hazard distribution map can quantitatively evaluate the risk of geological disasters in different areas. This quantitative evaluation provides a scientific basis for mine management, enabling decision makers to formulate targeted management measures and emergency response plans based on data. Clear mine geological hazard distribution and potential disaster probability data can help managers make more reasonable decisions on resource allocation, for example, prioritize the deployment of monitoring equipment and emergency resources in high-risk areas, thereby improving the efficiency and effectiveness of disaster prevention and mitigation. Through a comprehensive analysis of mine geological hazards and potential disaster probabilities, it can provide a scientific basis for mine safety management, help formulate effective risk management strategies, and reduce the impact of geological disasters on mine operations and the surrounding environment. Through the GIS technical analysis of multi-source spatial data of mines, the application of related technologies in mine management has been promoted, and technological progress and innovation have been promoted. This innovation will improve the intelligent level of mine management and enhance the adaptability to complex geological environments. Step S1 obtains and processes multi-source spatial data of mines through the system to generate mine geological hazard distribution maps and potential disaster probability data, which not only improves data quality and analysis capabilities, but also enhances the effects of mine safety management and environmental protection. These beneficial effects provide a solid foundation for the effective prevention of geological disasters in mines.

[0016] Preferably, step S13 includes the following steps:

[0017] Step S131: classifying the influencing factors of the standard mine multi-source spatial data to generate influencing factor classification data, wherein the influencing factor classification data includes geological factor data, meteorological factor data, topographic factor data and historical disaster factor data; using GIS technology to perform spatial distribution characteristic stratification on the geological factor data, meteorological factor data, topographic factor data and historical disaster factor data to generate a comprehensive influencing factor layer;

[0018] Step S132: performing spatial interpolation on the comprehensive influencing factor layer to generate a mine geological spatial distribution map; performing risk assessment on the geological factor data, meteorological factor data, topographic factor data and historical disaster factor data to generate comprehensive influencing factor risk assessment data;

[0019] Step S133: weighting the comprehensive influencing factor hazard assessment data to generate comprehensive influencing factor hazard weights; weighted superposition of the comprehensive influencing factor hazard weights by the mine geological spatial distribution map to generate a comprehensive geological disaster hazard index map;

[0020] Step S134: Classify the mine hazard areas of the standard mine multi-source spatial data according to the hazard weights of comprehensive influencing factors to generate mine hazard classification area data; spatially associate the mine hazard classification area data with the geological disaster hazard comprehensive index map to generate a mine geological hazard distribution map.

[0021] The present invention ensures the quality and consistency of data by cleaning, denoising, filling missing values ​​and standardizing multi-source spatial data of mines. This process provides a reliable data basis for subsequent analysis and avoids erroneous results caused by data quality problems. GIS technology is used to classify influencing factors and analyze spatial distribution characteristics, thereby enhancing the spatial visualization capability of data. The spatial analysis functions of GIS (such as buffer analysis and overlay analysis) enable risk factors in complex geological environments to be better understood and evaluated. Through spatial interpolation methods, irregularly distributed point data can be converted into continuous spatial distribution maps. This technology enables potential geological risks to be accurately located and provides spatial context for decision-making. In the comprehensive influencing factor hazard assessment, the relative importance of each influencing factor can be quantified through the weight distribution method. This quantification can make the geological disaster risk assessment more refined, reduce the influence of subjective judgment, and improve scientificity. The generated geological disaster hazard comprehensive index map provides managers with an intuitive decision support tool. Using data-driven analysis, managers can quickly identify high-risk areas and optimize resource allocation and emergency response measures. In subsequent applications, the combination of real-time monitoring data and the generated geological hazard distribution map can realize dynamic updating and monitoring, and enhance the real-time response capability to mining geological disasters. This technology can help to identify new risks in a timely manner and take corresponding measures. In the comprehensive risk assessment of influencing factors, machine learning and data mining technology can be further combined to establish a prediction model. By training and testing the model, future geological disaster risks can be predicted, so that preventive measures can be taken in advance. Through GIS and other visualization tools, complex geological data and analysis results can be presented in a graphical way. The enhanced visualization capability makes it easier for stakeholders from different professional backgrounds to understand the analysis results and improves the transparency of decision-making.

[0022] Preferably, step S14 includes the following steps:

[0023] Step S141: grid pixelating the mine geological hazard distribution map to generate a mine geological hazard distribution space unit; extracting pixel information from the mine geological hazard distribution space unit to obtain space unit pixel information data;

[0024] Step S142: Analyze the pixel size and spatial attribute of the spatial unit pixel information data to generate spatial unit pixel size data and spatial unit attribute data; perform potential probability calculation on the mine geological hazard distribution map based on the spatial unit pixel information data to obtain mine geological potential probability distribution data;

[0025] Step S143: spatially clustering the mine geological hazard distribution map based on the mine geological potential probability distribution data using the spatial unit pixel size data and the spatial unit attribute data to generate mine geological distribution disaster probability data.

[0026] The present invention can subdivide a large area into smaller spatial units by grid pixelating the mine geological hazard distribution map, thereby improving the spatial resolution of the data. This high-precision spatial unit provides more detailed basic data for subsequent analysis and enhances the accuracy of spatial analysis. Pixel information is extracted from the spatial unit to obtain rich spatial unit pixel information data. This information provides detailed data support for further analysis and helps identify key features related to mine geological hazards. Pixel information is extracted from the spatial unit to obtain rich spatial unit pixel information data. This information provides detailed data support for further analysis and helps identify key features related to mine geological hazards. The potential probability of mine geology is calculated based on the spatial unit pixel information data, and the geological hazard can be quantified. This quantitative assessment provides data support for formulating scientific risk management strategies and helps decision makers identify and prioritize high-risk areas. By spatially clustering the mine geological hazard distribution map, potential geological disaster clustering areas can be identified. This analysis not only helps to understand the existing hazard distribution, but also discovers hidden potential risk points, enhancing the foresight of disaster prevention and mitigation. In practical applications, by continuously updating the spatial unit pixel information and the potential probability distribution data of mine geology, dynamic monitoring of mine geological hazards can be achieved. This capability can improve the ability to quickly respond to and handle sudden geological disasters, enhance the flexibility of mine safety management, and the generated mine geological distribution disaster probability data provides managers with a scientific basis to help formulate more reasonable resource allocation and emergency response plans. This data-based decision-making process helps to improve resource utilization efficiency and reduce management costs.

[0027] Preferably, step S2 comprises the following steps:

[0028] Step S21: Calculate the disaster complexity of the mine geological hazard distribution map using the mine geological distribution disaster probability data to obtain regional disaster complexity data; screen the mine geological hazard distribution map for high-complexity spatial regions based on the regional disaster complexity data to obtain high-complexity spatial regional data;

[0029] Step S22: performing spatial RGB color mapping on the high-complexity spatial region data to generate spatial pixel color mapping data; dividing the high-complexity spatial region data into mine activity areas based on the spatial pixel color mapping data to generate mine activity areas and mine inactive areas;

[0030] Step S23: Perform global surface deformation monitoring on the mining activity area to generate global surface deformation monitoring data for the mining activity area; perform local surface deformation analysis on the surface deformation monitoring data for the mining activity area to generate local surface deformation analysis data for the local activity area; perform comprehensive data fusion on the global surface deformation monitoring data for the mining activity area and the surface deformation analysis data for the local activity area to generate comprehensive surface deformation data for the mining activity area.

[0031] The present invention can quantify geological hazards by calculating the complexity of disasters on the probability data of geological disasters in mine distribution. This quantification not only provides an objective basis for further analysis, but also helps identify high-risk areas and improves the scientific nature of overall risk management. Screening high-complexity spatial areas according to regional disaster complexity data helps to accurately locate areas with high geological hazards. This process can optimize resource allocation and concentrate efforts on monitoring and managing potential dangerous areas. Spatial RGB color mapping of high-complexity spatial regional data can intuitively display regional risk distribution and improve visualization. This visualization not only helps analysis, but also better communicates with stakeholders and improves risk awareness. The division of mine activity areas and inactive areas based on spatial pixel color mapping data can achieve refined mine management. This division can help formulate more effective management and monitoring strategies and reduce resource waste. Global surface deformation monitoring of mine activity areas can timely discover potential geological risks and provide early warning information. This global monitoring can improve mine safety and prevent disasters. Local surface deformation analysis can provide an in-depth understanding of geological changes in specific areas. This analysis can reveal key factors affecting mine activities and provide support for subsequent decision-making. The comprehensive integration of global and local monitoring data to generate comprehensive surface deformation data of mining activity areas can provide a more comprehensive risk assessment. This comprehensive data provides strong support for decision makers, making decisions more forward-looking and scientific.

[0032] Preferably, step S23 includes the following steps:

[0033] Step S231: performing global multi-temporal radar image acquisition on the mine activity area to obtain multi-temporal radar image data of the activity area; performing interference processing on the multi-temporal radar image data of the activity area to generate a synthetic aperture radar interferogram of the activity area;

[0034] Step S232: extracting phase information from the active area synthetic aperture radar interference pattern to obtain active area phase information data; performing phase unwrapping on the active area phase information data to generate unwrapped active area interference phase information data;

[0035] Step S233: Calculate the pixel deformation amplitude of the unwrapped interferometric phase information data of the active area to obtain the phase deformation amplitude data; perform deformation time series analysis on the phase deformation amplitude data to generate the global surface deformation monitoring data of the mine active area;

[0036] Step S234: Perform local surface deformation analysis on the global navigation satellite technology for the surface deformation monitoring data of the mine active area to generate local active area surface deformation analysis data; perform comprehensive data fusion on the global surface deformation monitoring data of the mine active area and the local active area surface deformation analysis data to generate comprehensive surface deformation data of the mine active area.

[0037] Through the global multi-temporal radar image acquisition, the present invention can comprehensively monitor the mine active area at different time points. This monitoring ability makes the identification and analysis of surface deformation more accurate, helping to detect potential risks in a timely manner. Performing interferometric processing on the multi-temporal radar image data of the active area to generate synthetic aperture radar interferograms can reveal tiny surface deformations. This refined analysis provides a solid foundation for subsequent deformation monitoring. Extracting phase information and performing phase unwrapping to generate the unwrapped interferometric phase information data can deeply understand the deformation mechanism of the mine area. This in-depth analysis can provide important data support for related research. Calculating the pixel deformation amplitude of the unwrapped phase information data can quantify the degree of surface deformation. This quantified information is of great significance for evaluating mine safety and can provide a basis for management and decision-making. Performing deformation time series analysis to generate the surface deformation monitoring data of the global mine active area can identify the dynamic change trend of deformation. This dynamic monitoring ability can help managers adjust the mine operation strategy in a timely manner to ensure safety. Combining with the global navigation satellite technology to perform local surface deformation analysis on the mine active area can achieve higher-precision surface monitoring. This combination improves the accuracy of the data and helps to comprehensively evaluate the impact of mine activities. Performing comprehensive fusion of the global surface deformation monitoring data and the analysis data of the local active area to generate the comprehensive surface deformation data of the mine active area can provide a comprehensive risk assessment. This comprehensive data provides more valuable reference information for decision-makers and helps to formulate effective safety management strategies. Through high-frequency radar monitoring and multi-temporal data analysis, the ability to quickly respond to emergencies can be improved. This ability is of great significance for ensuring mine safety and reducing potential losses.

[0038] Preferably, step S234 includes the following steps:

[0039] Step S2341: selecting key surface deformation positions of the surface deformation monitoring data of the mining activity area through global navigation satellite technology to obtain key surface deformation area data; deploying GNSS monitoring stations for the key surface deformation area data to generate GNSS monitoring station deployment position data;

[0040] Step S2342: collecting GNSS satellite signals for the GNSS monitoring station deployment location data to obtain GNSS satellite signals at key locations; discretizing the GNSS satellite signals at key locations to generate discrete data of GNSS satellite signals at key locations;

[0041] Step S2343: performing discrete point relative displacement calculation on the discrete data of GNSS satellite signals at key positions to obtain discrete point relative displacement data; performing baseline vectorization on the discrete point relative displacement data to generate horizontal displacement change data at key positions and vertical displacement change data at key positions;

[0042] Step S2344: Perform local key surface deformation analysis on the surface deformation monitoring data of the mining activity area through the horizontal displacement change data of key positions and the vertical displacement change data of key positions to generate local activity area surface deformation analysis data; perform comprehensive data fusion on the global mining activity area surface deformation monitoring data and the local activity area surface deformation analysis data to generate comprehensive surface deformation data of the mining activity area.

[0043] The present invention selects key surface deformation positions through global navigation satellite technology (GNSS), so that monitoring work is concentrated on areas with higher potential risks. This focus is conducive to the optimal allocation of resources and the improvement of monitoring efficiency. The deployment of GNSS monitoring stations in key surface deformation areas is conducive to obtaining more accurate location information. This precise monitoring provides a reliable basis for subsequent data analysis. By collecting satellite signals at key positions through GNSS monitoring stations, real-time monitoring of surface deformation can be achieved. This real-time data acquisition is very important for rapid response and decision-making. Discretization processing is performed on GNSS satellite signals to generate discrete data, making subsequent data analysis more efficient. This processing process can improve the calculation efficiency of data and reduce processing time. By calculating the relative displacement of discrete points, the degree of deformation of the surface can be quantified and relative displacement data can be generated. This quantification result provides necessary information for understanding and evaluating the surface dynamics of the mining area. The relative displacement data is subjected to baseline vectorization processing to generate horizontal and vertical displacement change data of key positions, which is conducive to a comprehensive analysis of the deformation characteristics of the mining activity area. This step can provide a deeper understanding of the geological dynamics of the mine. Based on the displacement change data of key positions, local surface deformation analysis of the mining activity area is performed to generate detailed surface deformation analysis data of the local activity area. This detailed analysis provides a key basis for mine safety management. The global surface deformation monitoring data of the mining activity area and the local activity area analysis data are integrated to generate comprehensive surface deformation data of the mining activity area. This comprehensive analysis helps to provide a more comprehensive risk assessment and support managers to make scientific decisions. Step S234 realizes accurate monitoring and analysis of the mining activity area through the application of GNSS technology. From the selection of key surface deformation positions, real-time signal collection to the discretization and fusion of data, this series of technical means greatly improves the efficiency and accuracy of surface deformation monitoring, provides strong support for mine safety management, and ensures the safety and sustainability of mine operations.

[0044] Preferably, step S3 comprises the following steps:

[0045] Step S31: collecting regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine;

[0046] Step S32: Calculate the vegetation index of the remote sensing image of the mine inactive area to generate the vegetation index of the mine inactive area; perform a dynamic analysis of vegetation changes on the remote sensing image of the mine inactive area by using the vegetation index of the mine inactive area to generate ecological change data of the inactive area;

[0047] Step S33: Analyze the water range changes of the remote sensing images of the inactive area of ​​the mine to generate water range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data and the water range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine.

[0048] The present invention can obtain large-scale, high-resolution image data by collecting regional remote sensing images of inactive areas of mines, providing a basis for subsequent analysis. This comprehensive coverage can help managers conduct all-round monitoring of inactive areas. Vegetation index calculation (such as NDVI) of remote sensing images can quantify the vegetation coverage of inactive areas of mines. This quantitative analysis provides a basis for evaluating the health status of the ecology and helps to understand the growth of plants and ecological recovery capacity. Dynamic analysis of vegetation changes in remote sensing images of inactive areas of mines through vegetation index can identify and track vegetation change trends. This dynamic monitoring helps to timely discover ecological degradation or recovery and provide a reference for ecological management. Water body range change analysis of remote sensing images of inactive areas of mines can monitor changes in the area and distribution of water bodies. This analysis provides important information for water resource management and ecological protection, helping decision makers take necessary measures to protect water resources, and the generated inactive area ecological change data provides a basis for understanding the dynamic changes of ecosystems. These data can help managers evaluate ecological restoration effects and potential environmental problems. Calculating environmental suitability based on the ecological change data of inactive areas and the change data of water body range can provide a scientific basis for land use planning and mine reclamation. This environmental suitability data helps to evaluate the feasibility of different uses and optimize resource allocation. The use of remote sensing technology for ecological monitoring can greatly improve the efficiency and accuracy of monitoring and reduce human intervention. This automated monitoring can save resources and time and obtain ecological change information more efficiently. The implementation of step S3 realizes comprehensive monitoring and analysis of inactive areas of mines through the application of remote sensing technology, forming a systematic ecological monitoring system from the calculation of vegetation index, analysis of water body range changes, to the calculation of environmental suitability.

[0049] Preferably, step S32 includes the following steps:

[0050] Step S321: performing image preprocessing on the remote sensing image of the mine inactive area to generate a standard remote sensing image of the mine inactive area, wherein the image preprocessing includes geometric correction, atmospheric correction and image boundary clipping;

[0051] Step S322: extracting red light band and near infrared band of remote sensing image of standard mine inactive area to obtain red light band data and near infrared band data; calculating vegetation index of red light band data and near infrared band data to generate vegetation index of mine inactive area;

[0052] Step S323: comparing the vegetation index of the mine inactive area with the preset vegetation index threshold set; when the vegetation index of the mine inactive area is less than the first vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the mine inactive area is marked as a water body or bare soil vegetation area and removed; when the vegetation index of the mine inactive area is greater than or equal to the first vegetation index threshold in the preset vegetation index threshold set and less than the second vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the mine inactive area is marked as a sparse vegetation area;

[0053] Step S324: when the vegetation index of the mine inactive area is greater than or equal to the second vegetation index threshold in the preset vegetation index threshold set and less than the third vegetation index threshold in the preset vegetation index threshold set, the corresponding mine inactive area remote sensing image is marked as a medium vegetation area;

[0054] Step S325: When the vegetation index of the inactive area of ​​the mine is greater than or equal to the third vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the inactive area of ​​the mine is marked as a dense vegetation area; based on the sparse vegetation area, medium vegetation area and dense vegetation area, a dynamic analysis of vegetation changes is performed to generate ecological change data of the inactive area.

[0055] The present invention can eliminate geometric distortion, atmospheric interference and irrelevant areas in remote sensing images through preprocessing steps such as geometric correction, atmospheric correction and image boundary clipping, thereby generating high-precision standard remote sensing images. This standardization process helps to improve the accuracy of subsequent vegetation index calculation and the reliability of ecological monitoring. The extraction of red light band and near infrared band is aimed at vegetation reflection characteristics, and can accurately capture the growth status and health of plants. Vegetation index calculation based on these bands, such as NDVI (normalized vegetation index), can effectively reflect the coverage and growth status of vegetation, and provide a basis for ecological dynamic analysis. By classifying the vegetation index by presetting the vegetation index threshold set, the area in the remote sensing image can be automatically marked as different types of vegetation areas (such as water bodies, bare soil, sparse vegetation, medium vegetation, dense vegetation). This automated processing improves the efficiency of ecological analysis in large areas and reduces the complexity of manual intervention. By marking the area with a vegetation index lower than the first threshold as a water body or bare soil and eliminating it, the interference of non-vegetation areas on the analysis results is eliminated. This screening method makes the subsequent dynamic analysis of vegetation changes more focused on vegetation coverage, thereby improving the accuracy of the analysis. Based on the preset vegetation index threshold set, sparse, medium and dense vegetation areas are marked so that areas with different vegetation densities can be clearly distinguished. Refined classification can provide more valuable reference data for ecological restoration monitoring and help managers formulate corresponding restoration plans. By conducting dynamic analysis of vegetation changes in sparse, medium and dense vegetation areas, the changing trends of vegetation in different time periods can be captured. This dynamic analysis helps managers understand the changes in the ecological environment in real time and identify the occurrence of ecological degradation or recovery phenomena in a timely manner. Dynamic analysis data based on vegetation index can provide a scientific basis for ecological management and restoration strategies. Regional classification of different vegetation densities can help managers identify areas that need to be protected or restored, and carry out targeted ecological governance. This step realizes the automated processing and analysis of remote sensing images, and can quickly generate vegetation index, classified images and change data over a large area. Through automated analysis, the manpower and time costs are greatly reduced, while the analysis efficiency is improved.

[0056] Preferably, step S4 comprises the following steps:

[0057] Step S41: dividing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area into data sets to generate a model training set and a model test set;

[0058] Step S42: training the model training set by using a convolutional neural network algorithm to generate a pre-model for comprehensive evaluation of mining geological hazards; optimizing and iterating the pre-model for comprehensive evaluation of mining geological hazards by using a model test set, thereby generating a comprehensive evaluation model for mining geological hazards;

[0059] Step S43: Importing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area into the mine geological disaster comprehensive evaluation model to conduct a comprehensive evaluation of the mine geological disaster risk, and generate comprehensive evaluation data of the geological disaster risk in the mine highly complex area;

[0060] Step S44: Visualize the comprehensive evaluation data of geological hazards in highly complex areas of mines, so as to generate a comprehensive evaluation report of geological hazards in highly complex areas of mines.

[0061] The present invention generates a model training set and a test set by reasonably dividing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area. This division strategy helps the model obtain enough diversified data during training, thereby avoiding overfitting, improving the generalization ability of the model, and enabling it to more accurately predict the risk of geological disasters. Convolutional neural network has powerful image recognition and spatial feature extraction capabilities. In step S42, by training the mine geological data through CNN, complex geological deformation features can be effectively extracted, and a mine geological disaster comprehensive evaluation model with high accuracy can be constructed. CNN can automatically learn and capture complex features related to geological disasters, reducing the errors caused by human intervention. During the training process, the mine geological disaster pre-model is optimized and iterated using the test set, and the weight parameters of the model can be continuously adjusted, thereby improving the evaluation accuracy of the model. Through this repeated iteration, the mine geological disaster comprehensive evaluation model finally generated is more accurate and stable when dealing with different geological conditions. After the comprehensive surface deformation data and environmental suitability data are input into the geological disaster comprehensive evaluation model, the model can comprehensively evaluate the geological disaster risks in the mine area. In this way, the geological disaster risk in the high-complexity area of ​​the mine can be accurately predicted, thus providing a scientific basis for mine safety management. Through comprehensive geological disaster assessment, the potential geological disaster risk in the high-complexity area of ​​the mine can be identified. This step can not only identify large-scale risks, but also accurately locate specific high-risk areas, thereby providing support for taking targeted preventive measures and reducing potential losses. Visualizing the geological hazard assessment data makes the geological risk information more intuitive and convenient for mine managers to understand and make decisions. The risk assessment report generated by visualization can enable managers to quickly grasp the overall risk status of the mine and help them make efficient decisions and formulate preventive measures. Through the application of convolutional neural networks and comprehensive evaluation models, the assessment process of geological disasters in mines is automated. Compared with traditional manual assessment, the automated process not only improves efficiency, but also reduces human errors, making the assessment results more scientific and reliable. Through the comprehensive evaluation of surface deformation data and environmental suitability data, the model can provide a specific scientific basis for mine disaster prevention. Managers can formulate more reasonable safety management plans and disaster prevention and control measures based on the generated reports and data results, thereby improving the safety of mine operations. Step S4 provides a complete solution for mining geological disaster assessment through scientific data set division, convolutional neural network training and optimization, comprehensive geological disaster risk assessment and data visualization. This step not only improves the accuracy and efficiency of the assessment, but also provides mine managers with an intuitive decision-making basis, thereby better ensuring the safe operation of the mining area.

[0062] The beneficial effect of the present invention is that by acquiring multi-source spatial data of mines and conducting geological disaster risk distribution analysis, the potential danger of the mining area can be comprehensively assessed, and a mine geological hazard distribution map can be generated to provide a scientific basis for subsequent decision-making. Using the probability data of mine geological distribution disasters to screen high-complexity spatial regions helps to identify and focus on areas with higher potential risks, enhancing the pertinence of risk assessment; at the same time, it divides the active and inactive areas of mines to ensure monitoring and management of various areas. Remote sensing image acquisition and analysis of inactive areas of mines can effectively monitor ecological changes and changes in water range, identify potential environmental influencing factors, and the generated environmental suitability data provides an important reference for regional governance. Comprehensively evaluating the comprehensive surface deformation data of the mine active area and the environmental suitability data of the inactive area makes the assessment results more comprehensive and reflects the geological disaster risks in different regions; through data visualization, the readability and intuitiveness of the report are improved, which helps relevant decision makers to understand the risk situation in a timely manner and take necessary measures. Therefore, the present invention improves the accuracy and comprehensiveness of the comprehensive evaluation of the risk of geological hazards in mines by integrating multi-source data, emphasizing spatial distribution characteristics, distinguishing between active and inactive areas, and analyzing ecological and water changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a schematic diagram of the steps of a comprehensive evaluation method for the risk of mining geological hazards taking into account spatial distribution characteristics;

[0064] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0065] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0066] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0068] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0069] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0070] To achieve this, please refer to Figures 1 to 3 A comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics is provided, the method comprising the following steps:

[0071] Step S1: Acquire multi-source spatial data of mines; perform mine geological disaster risk distribution analysis on the mine multi-source spatial data to generate a mine geological hazard distribution map; perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data;

[0072] Step S2: screening the mine geological hazard distribution map with high complexity spatial regions through the mine geological distribution disaster probability data to obtain high complexity spatial region data; dividing the mine activity region data into mine activity regions and generating mine inactivity regions and mine inactivity regions; performing surface comprehensive deformation analysis on the mine activity region to generate comprehensive surface deformation data of the mine activity region;

[0073] Step S3: collect regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine; perform vegetation change dynamic analysis on the remote sensing images of the inactive area of ​​the mine to generate ecological change data of the inactive area; perform water body range change analysis on the remote sensing images of the inactive area of ​​the mine to generate water body range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data of the inactive area and the water body range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine;

[0074] Step S4: Conduct a comprehensive evaluation of the geological hazard risk of mines based on the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area to generate comprehensive evaluation data of the geological hazard risk of mines with high complexity; visualize the comprehensive evaluation data of the geological hazard risk of mines with high complexity to generate a comprehensive evaluation report of the geological hazard risk of mines with high complexity.

[0075] The present invention forms a global view of the geological conditions of the mine by acquiring multi-source spatial data of the mine. Such data integration ensures the comprehensiveness of the assessment, can reflect the potential geological disaster risks of the mine, and the generated mine geological hazard distribution map provides an intuitive risk assessment tool for mine managers to help them quickly identify high-risk areas. By analyzing the probability of potential disasters in the spatial area of ​​the mine geological hazard distribution map, the potential risks can be quantified, which provides data support for subsequent decision-making. The high-complexity spatial area screening in step S2 can help managers identify the areas that need the most attention, which are usually faced with higher geological disaster risks, and contribute to the effective allocation of resources. The division of mine activity areas and inactive areas enables managers to formulate different management strategies and emergency measures in a targeted manner. In step S2, the comprehensive deformation analysis of the surface of the mine activity area is carried out, which helps to monitor geological changes in time and warn of potential geological disasters. Step S3 analyzes ecological changes through remote sensing images, which can help managers understand the environmental dynamics of the inactive area of ​​the mine and provide a basis for ecological restoration and protection. The analysis of changes in the range of water bodies enables managers to understand the impact of mine activities on water resources, and then formulate corresponding water resource management measures. Step S4 conducts risk assessment by integrating surface deformation data and environmental suitability data, and the generated visualization report makes complex data easy to understand and helps managers make scientific decisions. The comprehensive evaluation data and visualization results provide a scientific basis for the emergency management of mines, so that managers can quickly formulate response strategies when emergencies occur. By identifying active and inactive areas of mines and assessing their geological risks, managers can allocate resources more reasonably and improve management efficiency. Therefore, the present invention improves the accuracy and comprehensiveness of the comprehensive evaluation of the risk of geological hazards in mines by integrating multi-source data, emphasizing spatial distribution characteristics, distinguishing between active and inactive areas, and analyzing ecological and water changes.

[0076] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics of the present invention. In this example, the comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics includes the following steps:

[0077] Step S1: Acquire multi-source spatial data of mines; perform mine geological disaster risk distribution analysis on the mine multi-source spatial data to generate a mine geological hazard distribution map; perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data;

[0078] In the embodiment of the present invention, by determining the required data types, including geological data (such as topography, soil, rock type), meteorological data (such as rainfall, temperature), historical disaster data (such as landslide, collapse records), etc. Collect data from multiple channels such as satellite remote sensing, ground monitoring stations, geological exploration, etc. Integrate data from different sources into a unified database to ensure that the data format is consistent and convenient for subsequent analysis. Perform necessary data preprocessing, such as denoising, missing value filling, standardization, etc., to improve data quality. Classify the influencing factors of the integrated multi-source spatial data, including geological factors (such as lithology, faults), meteorological factors (such as rainfall, wind speed), environmental factors (such as vegetation coverage, terrain slope), etc. GIS technology is used to perform spatial distribution analysis on these factors and generate various influencing factor layers. Select a suitable hazard assessment model (such as hierarchical analysis method, fuzzy logic model, etc.), calculate the disaster hazard index of each region according to the spatial distribution characteristics of the influencing factors, generate a mine geological hazard distribution map, and identify the hazard level (low, medium, high) of different regions. Based on the mine geological hazard distribution map and combined with historical disaster data, a probability model for potential disasters is established (such as logistic regression, Bayesian network, etc.). The key factors related to potential disasters are determined and statistically analyzed to identify their relationship with the occurrence of disasters. The established probability model is applied to the mine geological hazard distribution map to calculate the potential probability of geological disasters in each area, generate mine geological distribution disaster probability data, and provide a potential disaster probability score for each area to guide subsequent risk assessment and management measures.

[0079] Step S2: screening the mine geological hazard distribution map with high complexity spatial regions through the mine geological distribution disaster probability data to obtain high complexity spatial region data; dividing the mine activity region data into mine activity regions and generating mine inactivity regions and mine inactivity regions; performing surface comprehensive deformation analysis on the mine activity region to generate comprehensive surface deformation data of the mine activity region;

[0080] In an embodiment of the present invention, by determining the evaluation index of the high-complexity area, such as the potential disaster probability, the rate of change of geological factors, the frequency of historical disasters, etc., a complexity threshold is set, and the characteristics of the high-complexity area are identified through statistical analysis. Using the geological distribution disaster probability data of the mine, spatial analysis is performed to identify the area that meets the complexity threshold, generate high-complexity spatial area data, and identify the area with significant disaster risk. Formulate the division standards of the active area and the inactive area of ​​the mine, such as the mining operation time, equipment usage, surface deformation, etc. Analyze different areas in combination with the geographic information system (GIS) to identify the boundaries of the active and inactive areas. Analyze the high-complexity spatial area data, divide the area into the active area of ​​the mine and the inactive area of ​​the mine according to the set standards, and generate geographic information data of the active area of ​​the mine and the inactive area of ​​the mine, which is convenient for subsequent processing. Collect surface monitoring data of the active area of ​​the mine, including remote sensing images, GNSS data, etc., to ensure the timeliness and accuracy of the data. Perform data preprocessing, such as denoising and correction, to improve data quality. Apply synthetic aperture radar (SAR) interferometry technology or surface deformation monitoring models to analyze surface deformation in the mining activity area. Calculate deformation amplitude, speed, and spatial distribution characteristics to generate comprehensive surface deformation data for the mining activity area. Combine the generated comprehensive surface deformation data with information on the mining activity area to provide an overview of the dynamic changes in the surface of the activity area. Output analysis results to facilitate decision support and risk management.

[0081] Step S3: collect regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine; perform vegetation change dynamic analysis on the remote sensing images of the inactive area of ​​the mine to generate ecological change data of the inactive area; perform water body range change analysis on the remote sensing images of the inactive area of ​​the mine to generate water body range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data of the inactive area and the water body range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine;

[0082] In an embodiment of the present invention, a suitable satellite platform (such as Landsat, Sentinel, etc.) is selected by determining the acquisition time, frequency and resolution of the remote sensing image. The acquisition range is set to ensure that all inactive areas are covered and the impact of seasonal changes is taken into account. Remote sensing image acquisition is performed by satellite or drone to ensure the acquisition of high-quality image data. Image download and storage are completed, and relevant metadata such as acquisition time, meteorological conditions, etc. are recorded. Geometric correction and atmospheric correction are performed on the collected remote sensing images to eliminate the influence of environmental factors and ensure the accuracy of the data. The image boundary is cropped and focused on the inactive area. The red light band and the near-infrared band are extracted, and the vegetation index (such as NDVI) is calculated to assess the health status of the vegetation. The vegetation index is compared with historical data to analyze the dynamic trend of vegetation changes. Based on the changes in the vegetation index, ecological change data of the inactive area is generated to identify vegetation recovery, decline or other changes. The water body range is extracted from the remote sensing image using a water body index (such as NDWI). Threshold processing is performed to separate the water body area from the background. Compare the extracted water body range with historical images to identify the expansion or contraction of the water body range, generate data on changes in the water body range in the inactive area, and evaluate changes in the water body ecological environment. Integrate the ecological change data and water body range change data to identify the key factors affecting the environmental suitability of the inactive area. According to the ecological changes and water body changes, use multi-factor analysis models (such as AHP method, weighted index method, etc.) to calculate the environmental suitability of the inactive area. Set the suitability threshold, determine the suitability of the regional environment, generate environmental suitability data for the inactive area of ​​the mine, and provide an assessment of the regional environmental health status. Output a report containing the analysis results of ecological changes and water body changes to provide a basis for environmental management and decision-making.

[0083] Step S4: Conduct a comprehensive evaluation of the geological hazard risk of mines based on the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area to generate comprehensive evaluation data of the geological hazard risk of mines with high complexity; visualize the comprehensive evaluation data of the geological hazard risk of mines with high complexity to generate a comprehensive evaluation report of the geological hazard risk of mines with high complexity.

[0084] In the embodiment of the present invention, the comprehensive surface deformation data of the active area of ​​the mine is collected, including information such as deformation amplitude and speed. The environmental suitability data of the inactive area of ​​the mine is collected, covering indicators such as ecological changes and water body changes. The two types of data are standardized to ensure the comparability between different data sources. Combined with the geographic information system (GIS), the data of the active area and the inactive area are integrated in the same coordinate system to form a unified data set. Select a suitable comprehensive evaluation method, such as fuzzy comprehensive evaluation method, hierarchical analysis method (AHP) or machine learning model to construct a comprehensive evaluation model for the risk of geological hazards in mines. Determine the weight of each indicator, considering the influence of factors such as surface deformation, environmental suitability, and historical disasters. The integrated data is input into the comprehensive evaluation model to conduct a comprehensive evaluation of the risk of geological hazards in highly complex areas of mines, generate a risk score for highly complex areas of mines, and identify the risk level of different areas. Analyze the comprehensive evaluation results, identify high-risk areas, potential disaster types and impact levels, generate comprehensive evaluation data for the risk of geological hazards in highly complex areas of mines, and provide a basis for decision-making. Select appropriate visualization tools, such as ArcGIS, Tableau, or Python visualization libraries (such as Matplotlib, Seaborn), to display data. Visualize the comprehensive hazard evaluation data through heat maps, three-dimensional models, pie charts, etc. to clearly display the hazard levels of different areas. Ensure that the information in the charts is intuitive and easy to understand for different stakeholders. Integrate the visualization results with the analysis text to generate a comprehensive evaluation report on the geological hazard of highly complex areas in mines. The report should include evaluation methods, data sources, interpretation of results, and recommended measures to provide a reference for subsequent management and monitoring.

[0085] Preferably, step S1 comprises the following steps:

[0086] Step S11: Acquire multi-source spatial data of mines;

[0087] Step S12: preprocessing the mine multi-source spatial data to generate standard mine multi-source spatial data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0088] Step S13: Based on GIS technology, the mine geological disaster risk distribution analysis is performed on the standard mine multi-source spatial data to generate a mine geological risk distribution map;

[0089] Step S14: Perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data.

[0090] In the embodiment of the present invention, high-resolution images of the mine are obtained by using drones for aerial photography to capture the terrain and vegetation conditions. Geological sensors are deployed to monitor groundwater levels, soil moisture and seismic activity in real time to obtain dynamic geological data. Multispectral images are obtained from remote sensing satellites to analyze the geological characteristics and land use of the mining area. All acquired data are aggregated into a unified platform to ensure compatibility and availability between different data sources. The collected data are screened to remove invalid or duplicate data records to ensure data accuracy and consistency. The sensor data is denoised and algorithms are used to reduce measurement errors and environmental interference to improve data quality. The missing values ​​in the data are analyzed and filled according to the trends of adjacent data points to ensure data integrity. Data of different dimensions are converted to a unified standard so that different data sources can be directly compared in subsequent analysis. The preprocessed standardized data is input into a GIS (geographic information system) platform. GIS tools are used for spatial analysis to identify the relationship between geological features (such as rock formation type, soil composition) and geological hazards (such as landslides and collapses). By creating buffer zones, the impact of certain features (such as water bodies and mining area boundaries) on geological hazards is evaluated. Generate a geological hazard distribution map in GIS to highlight high-risk areas and provide intuitive support for subsequent decision-making. Collect historical disaster occurrence data and analyze factors that affect disaster occurrence, such as rainfall, soil moisture, and terrain features. Establish a statistical model to calculate the probability of potential disasters in each area, which can be achieved by analyzing the relationship between historical data and existing geological conditions. Overlay the calculated probability data with the geological hazard distribution map to form a comprehensive analysis map to show the potential disaster probability in each area. The specific process of the mine geological disaster hazard distribution analysis includes importing standardized mine multi-source spatial data into the GIS platform to ensure that the data includes information on geology, topography, climate, etc. According to the geological map, identify the location and distribution of different rock formation types. Use the overlay analysis tool in GIS to overlay the rock formation data with other environmental factors (such as water flow and vegetation cover) to determine the landslide area. Based on soil sample data, analyze the impact of different soil types on geological disasters and identify high-risk soils (such as clay and loose soil). Collect historical meteorological data and analyze the relationship between rainfall and geological disasters. Use statistical analysis (such as correlation analysis) to determine the probability of disasters when rainfall reaches a certain threshold. Combining the above analysis results, a risk matrix is ​​created: Low risk: stable soil, low rainfall, strong rock formation. Medium risk: medium soil, moderate rainfall, weak rock formation. High risk: loose soil, high rainfall, weak rock formation. According to the risk matrix, a risk level is assigned to each area, and a geological hazard distribution map is generated. At the same time, the specific process of potential disaster probability analysis includes collecting geological disaster records in the past ten years, including landslides, mudslides and other events, and recording the time, location and related meteorological data.Determine the main factors that affect the occurrence of disasters, such as rainfall, soil moisture, slope, etc. Use multiple regression analysis to evaluate the impact of these factors on the occurrence of disasters. Based on historical data and influencing factors, a logistic regression model is constructed: Independent variables: rainfall, soil moisture, slope, etc. Dependent variable: whether a disaster occurs (yes / no). Through model training, the influence coefficient of each factor on the occurrence of disasters is calculated to determine the probability of disasters under different conditions. Calculate each geological unit (such as a plot) and use the model to generate the potential disaster probability of each unit. For example, if the rainfall in an area is 100mm, the soil moisture is 30%, and the slope is 25 degrees, enter these data into the model to obtain the disaster probability of the area. Superimpose the calculated potential disaster probability with the hazard distribution map to form a comprehensive analysis map, mark the probability levels of different areas (such as 0-20%, 21-50%, 51-100%), and provide a reference for decision-making.

[0091] Preferably, step S13 includes the following steps:

[0092] Step S131: classifying the influencing factors of the standard mine multi-source spatial data to generate influencing factor classification data, wherein the influencing factor classification data includes geological factor data, meteorological factor data, topographic factor data and historical disaster factor data; using GIS technology to perform spatial distribution characteristic stratification on the geological factor data, meteorological factor data, topographic factor data and historical disaster factor data to generate a comprehensive influencing factor layer;

[0093] Step S132: performing spatial interpolation on the comprehensive influencing factor layer to generate a mine geological spatial distribution map; performing risk assessment on the geological factor data, meteorological factor data, topographic factor data and historical disaster factor data to generate comprehensive influencing factor risk assessment data;

[0094] Step S133: weighting the comprehensive influencing factor hazard assessment data to generate comprehensive influencing factor hazard weights; weighted superposition of the comprehensive influencing factor hazard weights by the mine geological spatial distribution map to generate a comprehensive geological disaster hazard index map;

[0095] Step S134: Classify the mine hazard areas of the standard mine multi-source spatial data according to the hazard weights of comprehensive influencing factors to generate mine hazard classification area data; spatially associate the mine hazard classification area data with the geological disaster hazard comprehensive index map to generate a mine geological hazard distribution map.

[0096] In the embodiment of the present invention, by collecting relevant data, including geological, meteorological, topographical and historical disaster information, it is ensured that these data are in the same coordinate system. The data are divided into four main categories: geological factors: rock type, soil characteristics, groundwater level, etc. Meteorological factors: rainfall, temperature, wind speed, etc. Topographic factors: slope, terrain undulation, soil type, etc. Historical disaster factors: frequency, location and type of past disaster events. Use GIS technology to analyze the spatial distribution characteristics of each factor: each factor is layered, the characteristic differences in different regions are identified, and a comprehensive influencing factor layer is generated to visualize the distribution of each factor, laying the foundation for subsequent analysis. The comprehensive influencing factor layer is spatially interpolated, and a method such as Kriging interpolation is used to generate a mine geological spatial distribution map, fill in the data blank area, and provide more continuous spatial characteristics. According to the characteristics of different factors, set the evaluation criteria: for example, the area with high rock stratum vulnerability is evaluated as high risk, generate comprehensive influencing factor hazard assessment data, and integrate the assessment results into GIS to form the risk level of each area. For the hazard assessment results of each influencing factor, a weight is assigned according to its impact on geological disasters. Expert evaluation method or analytic hierarchy process (AHP) can be used to determine the relative importance of each factor. Through the mine geological spatial distribution map, the weight of the risk of comprehensive influencing factors is weighted and superimposed. The comprehensive risk index of each area is calculated to generate a comprehensive index map of geological hazard risk. According to the risk weight of comprehensive influencing factors, the standard mine multi-source spatial data is regionally classified. The area is divided into high-risk, medium-risk and low-risk areas to implement targeted management and prevention and control measures. The mine hazard classification area data is spatially associated with the geological hazard comprehensive index map to generate the final mine geological hazard distribution map, marking the risk level of each area for subsequent monitoring and management. The specific spatial position association process includes importing the mine hazard classification area data and the geological hazard comprehensive index map in GIS software (such as ArcGIS or QGIS). Use the spatial overlay analysis tool in GIS (such as "overlay" or "intersection" tool) to select the mine hazard classification area data as the base layer and the geological hazard comprehensive index map as the overlay layer. Run the overlay analysis to generate a new layer containing the information of the two data sets. This new layer will contain the hazard level and corresponding comprehensive index of each area. Extract the mine hazard classification and geological disaster comprehensive index value of each area from the generated new layer. According to the comprehensive index value and hazard classification, add a label to each area for easy identification. For example: high-risk area: comprehensive index>0.7 medium-risk area: 0.4<comprehensive index≤0.7 low-risk area: comprehensive index≤0.4. Set the layer style and use different colors or symbols to represent different risk levels to enhance the visualization effect. For example: red represents high-risk area, yellow represents medium-risk area, and green represents low-risk area.The overlay results are used to generate the final mine geological hazard distribution map and saved in a format suitable for display or sharing (such as PDF or high-resolution image).

[0097] Preferably, step S14 includes the following steps:

[0098] Step S141: grid pixelating the mine geological hazard distribution map to generate a mine geological hazard distribution space unit; extracting pixel information from the mine geological hazard distribution space unit to obtain space unit pixel information data;

[0099] Step S142: Analyze the pixel size and spatial attribute of the spatial unit pixel information data to generate spatial unit pixel size data and spatial unit attribute data; perform potential probability calculation on the mine geological hazard distribution map based on the spatial unit pixel information data to obtain mine geological potential probability distribution data;

[0100] Step S143: spatially clustering the mine geological hazard distribution map based on the mine geological potential probability distribution data using the spatial unit pixel size data and the spatial unit attribute data to generate mine geological distribution disaster probability data.

[0101] In an embodiment of the present invention, the mine geological hazard distribution map is gridded by using GIS software, and the entire area is divided into uniform grid units (such as each grid unit is 10m x 10m). Each grid unit represents a certain geographical area and records the hazard index of the area. The pixel information of each spatial unit is extracted from the pixelated grid, and the corresponding hazard index and spatial coordinates are recorded. The generated spatial unit pixel information data includes the risk level, geographical location and other related attributes of each unit. The area of ​​each spatial unit is calculated based on the grid size (for example, each unit is 100 square meters). The size information of each unit is recorded to generate spatial unit pixel size data. Combined with the geological, meteorological and other attributes of the spatial unit, the spatial unit attribute data is generated. These attributes may include: terrain features (such as slope, soil type), meteorological conditions (such as average rainfall, humidity), historical disaster records (such as landslides or mudslides that occurred in the past). Based on the spatial unit pixel information data, the potential probability of each unit is calculated to evaluate the possibility of geological disasters in the area. The risk level is associated with each attribute factor using a statistical model (such as logistic regression) to obtain the potential probability distribution data of each unit. Collect spatial unit pixel size data, spatial unit attribute data, and mine geological potential probability distribution data to ensure that these data are available for analysis in the same format. Select a specific spatial clustering algorithm (such as K-means clustering, DBSCAN, etc.) to identify potential high-risk areas. The goal of clustering is to find areas with similar characteristics in the probability of geological disasters based on the size and attribute data of spatial units. Perform cluster analysis in GIS software, group spatial units according to potential probabilities and their spatial attributes, generate mine geological distribution disaster probability data, and indicate the clustering results of different areas and their corresponding disaster probability levels. Display the clustering results in the form of a map, use different colors or symbols to indicate the risk levels of different clustering areas, generate the final mine geological hazard distribution map, and highlight high-risk areas.

[0102] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0103] Step S21: Calculate the disaster complexity of the mine geological hazard distribution map using the mine geological distribution disaster probability data to obtain regional disaster complexity data; screen the mine geological hazard distribution map for high-complexity spatial regions based on the regional disaster complexity data to obtain high-complexity spatial regional data;

[0104] Step S22: performing spatial RGB color mapping on the high-complexity spatial region data to generate spatial pixel color mapping data; dividing the high-complexity spatial region data into mine activity areas based on the spatial pixel color mapping data to generate mine activity areas and mine inactive areas;

[0105] Step S23: Perform global surface deformation monitoring on the mining activity area to generate global surface deformation monitoring data for the mining activity area; perform local surface deformation analysis on the surface deformation monitoring data for the mining activity area to generate local surface deformation analysis data for the local activity area; perform comprehensive data fusion on the global surface deformation monitoring data for the mining activity area and the surface deformation analysis data for the local activity area to generate comprehensive surface deformation data for the mining activity area.

[0106] In the embodiment of the present invention, by importing the probability data of geological disasters in mines, it is ensured that the data contains the potential disaster probability of each spatial unit. A disaster complexity calculation model is designed, and the factors considered include: potential disaster probability, geological characteristics (such as rock layer stability, soil type), and environmental factors (such as water source, rainfall, etc.). The formula example is: C = f (P, G, E); where C is the disaster complexity, P is the potential disaster probability, G is the geological characteristics, and E is the environmental factor. The complexity is calculated for each area, regional disaster complexity data is generated, and the results are visualized in GIS. According to the regional disaster complexity data, a high complexity threshold is set. For example, an area with a complexity exceeding a certain value (such as 0.7) is set as a high complexity area. According to the set threshold, the high complexity spatial area that meets the conditions is screened out to generate high complexity spatial area data. The corresponding RGB color values ​​are set for different complexity levels, for example: high complexity area: red, medium complexity area: yellow, low complexity area: green. In GIS, the preset RGB color map is applied to the high complexity spatial area data to generate spatial pixel color mapping data. According to the spatial pixel color mapping data, the division standards of mining active areas and inactive areas are formulated. The mining active areas and mining inactive areas are extracted through GIS tools to generate corresponding data sets. The global surface deformation monitoring data of the mining active area is collected using remote sensing technology (such as InSAR and LiDAR). Data cleaning and preprocessing are performed to extract the surface deformation information of the mining active area and generate the global surface deformation monitoring data of the mining active area. In the global monitoring data, specific high-risk mining active areas are selected for detailed analysis. The spatiotemporal analysis model is applied to evaluate the local surface deformation trend and generate the surface deformation analysis data of the local active area. The global mining active area surface deformation monitoring data and the local active area surface deformation analysis data are integrated by using data fusion algorithms (such as weighted average, principal component analysis, etc.). The generated comprehensive surface deformation data of the mining active area is output to facilitate further analysis and decision-making.

[0107] Preferably, step S23 includes the following steps:

[0108] Step S231: performing global multi-temporal radar image acquisition on the mine activity area to obtain multi-temporal radar image data of the activity area; performing interference processing on the multi-temporal radar image data of the activity area to generate a synthetic aperture radar interferogram of the activity area;

[0109] Step S232: extracting phase information from the active area synthetic aperture radar interference pattern to obtain active area phase information data; performing phase unwrapping on the active area phase information data to generate unwrapped active area interference phase information data;

[0110] Step S233: Calculate the pixel deformation amplitude of the unwrapped active area interference phase information data to obtain phase deformation amplitude data; perform deformation time series analysis on the phase deformation amplitude data to generate global mine active area surface deformation monitoring data;

[0111] Step S234: Perform local surface deformation analysis on the surface deformation monitoring data of the mining activity area through global navigation satellite technology to generate surface deformation analysis data of the local activity area; perform comprehensive data fusion on the global mining activity area surface deformation monitoring data and the local activity area surface deformation analysis data to generate comprehensive surface deformation data of the mining activity area.

[0112] In an embodiment of the present invention, a synthetic aperture radar (SAR) system is used to collect multi-phase images of the active area of ​​the mine. Images at different time points are selected to capture surface changes. Ensure that the collected radar images cover all important active areas of the mine, and record the acquisition time and conditions of each image. Perform interference processing on the multi-phase radar images to generate a synthetic aperture radar interferogram of the active area. Apply interferometric measurement technology to generate an interferogram by calculating the phase difference, which displays the surface deformation information. Extract phase information from the synthetic aperture radar interferogram to obtain phase information data of the active area. Ensure that the extraction process retains the high-resolution characteristics of the phase data. Perform unwrapping processing on the phase information data to eliminate errors caused by phase ambiguity and generate unwrapped interference phase information data. Apply a phase unwrapping algorithm (such as least squares unwrapping method) to ensure the accuracy of the data. Calculate the pixel deformation amplitude based on the unwrapped phase information data. Use the formula: ; where D is the deformation amplitude, r is the radar wavelength, is the phase difference. Perform time series analysis on the phase deformation amplitude data, identify the time trend of deformation, generate global surface deformation monitoring data of the mining activity area, and describe the deformation in different time periods. Use the global navigation satellite system (GNSS) technology to monitor local surface deformation in the mining activity area. Use GNSS receivers to obtain high-precision location information. Collect data, analyze the deformation characteristics of the local area, and generate surface deformation analysis data for the local activity area. Fuse the global mining activity area surface deformation monitoring data with the local activity area surface deformation analysis data, and use weighted average or other fusion algorithms to integrate data from different sources to generate comprehensive surface deformation data for the mining activity area, providing comprehensive deformation information for mine safety monitoring.

[0113] Preferably, step S234 includes the following steps:

[0114] Step S2341: selecting key surface deformation positions of the surface deformation monitoring data of the mining activity area through global navigation satellite technology to obtain key surface deformation area data; deploying GNSS monitoring stations for the key surface deformation area data to generate GNSS monitoring station deployment position data;

[0115] Step S2342: collecting GNSS satellite signals for the GNSS monitoring station deployment location data to obtain GNSS satellite signals at key locations; discretizing the GNSS satellite signals at key locations to generate discrete data of GNSS satellite signals at key locations;

[0116] Step S2343: performing discrete point relative displacement calculation on the discrete data of GNSS satellite signals at key positions to obtain discrete point relative displacement data; performing baseline vectorization on the discrete point relative displacement data to generate horizontal displacement change data at key positions and vertical displacement change data at key positions;

[0117] Step S2344: Perform local key surface deformation analysis on the surface deformation monitoring data of the mining activity area through the horizontal displacement change data of key positions and the vertical displacement change data of key positions to generate local activity area surface deformation analysis data; perform comprehensive data fusion on the global mining activity area surface deformation monitoring data and the local activity area surface deformation analysis data to generate comprehensive surface deformation data of the mining activity area.

[0118] In an embodiment of the present invention, potential key deformation areas are identified based on global surface deformation monitoring data. These areas usually show significant deformation characteristics, such as large deformation or deformation rate. GIS technology is used to visualize deformation data to assist in selecting key locations. GNSS monitoring stations are deployed in selected key surface deformation areas. Considering the stability of the site and the effectiveness of signal reception, it is ensured that all key locations can be covered, and GNSS monitoring station deployment location data is generated, and the specific location and technical parameters of each monitoring station are recorded. Real-time satellite signal collection is performed at the deployed GNSS monitoring sites. Satellite data, including pseudorange and carrier phase information, are acquired using a high-precision GNSS receiver. Ensure that the collected signals cover multiple satellites to improve positioning accuracy. The collected GNSS satellite signals are discretized to convert continuous signals into discrete data for subsequent analysis, generate discrete data of GNSS satellite signals at key locations, and record the signal strength and reception status at each time point. Based on the discrete data, the relative displacement between GNSS monitoring sites is calculated. Using differential positioning technology, the position information at different time points is compared to obtain the relative displacement data of discrete points. Formula example: ΔP = P t ―P 0 ; Among them, P t is the current position, P 0 is the position at the initial moment. The relative displacement data of discrete points are converted into baseline vectors to generate horizontal displacement change data and vertical displacement change data of key positions. The three-dimensional coordinate transformation method is applied to obtain the displacement vector of each monitoring point. The horizontal and vertical displacement change data of key positions are used to conduct local analysis of the surface deformation monitoring data of the mining activity area. The characteristics and trends of surface deformation are identified, and surface deformation analysis data of local activity areas are generated to provide a detailed understanding of key areas. The surface deformation monitoring data of the global mining activity area is fused with the surface deformation analysis data of the local activity area. Weighted averaging or other data fusion techniques are applied to obtain more comprehensive deformation information, generate comprehensive surface deformation data of the mining activity area, and provide a reliable scientific basis for decision-making.

[0119] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0120] Step S31: collecting regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine;

[0121] Step S32: Calculate the vegetation index of the remote sensing image of the mine inactive area to generate the vegetation index of the mine inactive area; perform a dynamic analysis of vegetation changes on the remote sensing image of the mine inactive area by using the vegetation index of the mine inactive area to generate ecological change data of the inactive area;

[0122] Step S33: Analyze the water range changes of the remote sensing images of the inactive area of ​​the mine to generate water range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data and the water range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine.

[0123] In an embodiment of the present invention, images of inactive areas of mines are collected by using high-resolution remote sensing satellites (such as Landsat, Sentinel-2, etc.). A specific time period is selected for image acquisition to avoid the influence of seasonal changes and ensure that the acquired images represent the actual situation of the inactive areas. The acquisition time, meteorological conditions and sensor parameters of each image are recorded for subsequent analysis. Vegetation index (such as NDVI, i.e., normalized difference vegetation index) is calculated using remote sensing images, and the formula is as follows: Among them, NIR is the reflectance of the near-infrared band, and Red is the reflectance of the red band. By calculating the NDVI value, a vegetation index map of the inactive area of ​​the mine is generated to show the growth of vegetation. Based on the vegetation index data, time series analysis is performed to monitor the dynamic changes of vegetation. This includes analyzing the changes in NDVI values ​​at different time points, generating ecological change data in inactive areas, identifying areas of vegetation growth, decline or stability, and evaluating the health of the ecosystem. Common methods for identifying and analyzing water bodies using remote sensing images include using the normalized water index (NWI), etc. The formula example is: Green is the reflectance of the green band. The changes in water area in different time periods are analyzed to generate data on changes in water range in inactive areas, showing the expansion or contraction of water bodies. The ecological change data and water range change data of inactive areas are combined to evaluate the environmental suitability of inactive areas. A comprehensive assessment model is applied to generate environmental suitability data for inactive areas of mines, taking into account factors such as vegetation index, water body changes, and soil types.

[0124] Preferably, step S32 includes the following steps:

[0125] Step S321: performing image preprocessing on the remote sensing image of the mine inactive area to generate a standard remote sensing image of the mine inactive area, wherein the image preprocessing includes geometric correction, atmospheric correction and image boundary clipping;

[0126] Step S322: extracting red light band and near infrared band of remote sensing image of standard mine inactive area to obtain red light band data and near infrared band data; calculating vegetation index of red light band data and near infrared band data to generate vegetation index of mine inactive area;

[0127] Step S323: comparing the vegetation index of the mine inactive area with the preset vegetation index threshold set; when the vegetation index of the mine inactive area is less than the first vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the mine inactive area is marked as a water body or bare soil vegetation area and removed; when the vegetation index of the mine inactive area is greater than or equal to the first vegetation index threshold in the preset vegetation index threshold set and less than the second vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the mine inactive area is marked as a sparse vegetation area;

[0128] Step S324: when the vegetation index of the mine inactive area is greater than or equal to the second vegetation index threshold in the preset vegetation index threshold set and less than the third vegetation index threshold in the preset vegetation index threshold set, the corresponding mine inactive area remote sensing image is marked as a medium vegetation area;

[0129] Step S325: When the vegetation index of the inactive area of ​​the mine is greater than or equal to the third vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the inactive area of ​​the mine is marked as a dense vegetation area; based on the sparse vegetation area, medium vegetation area and dense vegetation area, a dynamic analysis of vegetation changes is performed to generate ecological change data of the inactive area.

[0130] In an embodiment of the present invention, the remote sensing image is geometrically corrected by using geographic reference data to ensure that each pixel in the image corresponds to a real geographic coordinate. Ground control points (GCPs) and interpolation algorithms are used to correct deformations caused by shooting angles and terrain. An atmospheric correction model (such as the 6S model) is applied to remove the effects of atmospheric scattering and absorption on the image, making the image data more realistic. The corrected image can more accurately reflect surface features, especially vegetation and water bodies. According to the boundaries of the study area, the preprocessed image is cropped into a remote sensing image of a standard mine inactive area, and irrelevant areas are removed. The generated standard image provides a clear data basis for subsequent analysis. Red light band and near-infrared band data are extracted from the remote sensing image of the standard mine inactive area to ensure the integrity and validity of the data. The reflectance value of each band is recorded for subsequent calculations. Calculate NDVI (Normalized Difference Vegetation Index) using the extracted red light band and near-infrared band data, and the formula is as follows: Among them, NIR is the reflectance of the near infrared band, and Red is the reflectance of the red band. The vegetation index map of the inactive area of ​​the mine is generated to reflect the vegetation coverage. The calculated vegetation index is compared with the preset vegetation index threshold set item by item. The remote sensing images are classified according to different thresholds: when the vegetation index is less than the first threshold, it is marked as a water body or bare soil area and removed from the analysis. When the vegetation index is between the first threshold and the second threshold, it is marked as a sparse vegetation area. When the vegetation index is between the second threshold and the third threshold, the corresponding remote sensing image is marked as a medium vegetation area. The characteristics of the area are recorded for subsequent analysis. When the vegetation index is greater than or equal to the third threshold, the remote sensing image is marked as a dense vegetation area. Through these marks, the vegetation areas are classified into sparse, medium and dense. Based on the marking results, the dynamic change analysis of sparse vegetation areas, medium vegetation areas and dense vegetation areas is carried out to generate ecological change data of inactive areas, analyze the change trends of different types of vegetation, and evaluate the health status and changes of the ecosystem.

[0131] Preferably, step S4 comprises the following steps:

[0132] Step S41: dividing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area into data sets to generate a model training set and a model test set;

[0133] Step S42: training the model training set by using a convolutional neural network algorithm to generate a pre-model for comprehensive evaluation of mining geological hazards; optimizing and iterating the pre-model for comprehensive evaluation of mining geological hazards by using a model test set, thereby generating a comprehensive evaluation model for mining geological hazards;

[0134] Step S43: Importing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area into the mine geological disaster comprehensive evaluation model to conduct a comprehensive evaluation of the mine geological disaster risk, and generate comprehensive evaluation data of the geological disaster risk in the mine highly complex area;

[0135] Step S44: Visualize the comprehensive evaluation data of geological hazards in highly complex areas of mines, so as to generate a comprehensive evaluation report of geological hazards in highly complex areas of mines.

[0136] In an embodiment of the present invention, the integrity and validity of the data are ensured by collecting comprehensive surface deformation data of the active area of ​​the mine and environmental suitability data of the inactive area of ​​the mine. The two types of data are integrated into a comprehensive data set for subsequent processing. The comprehensive data set is divided according to a certain ratio (for example, 70% training set and 30% test set). Ensure that the training set and the test set are representative in feature distribution to avoid overfitting or underfitting of the model. According to the known geological disaster situation, the data in the training set are labeled and the category of each sample is defined (for example, low, medium, and high risk areas). Construct a convolutional neural network architecture, select the appropriate number of layers, convolution kernel size, activation function, etc. Use the training set to train the CNN model, and adjust the network weights through the back propagation algorithm so that the model can accurately identify the risk of geological disasters. Use the test set to verify the trained model and evaluate its performance on unseen data. According to the prediction accuracy and loss function value of the model, hyperparameter adjustment and optimization (such as learning rate, batch size, etc.) are performed. Model training and testing are iterated until the model performance reaches the expected standard. The comprehensive surface deformation data of the active mining area and the environmental suitability data of the inactive mining area are input into the trained comprehensive geological disaster evaluation model. Ensure that the data format matches the model input requirements and perform necessary data preprocessing (such as normalization). The model is used to infer the input data and generate the comprehensive evaluation results of the geological hazard risk in each area. The output results include the hazard level (low, medium, high) of each area and its probability score, forming the comprehensive evaluation data of the geological hazard risk in the high-complexity area of ​​the mine. Use visualization tools (such as Matplotlib, Tableau, etc.) to visualize the comprehensive evaluation data of the geological hazard risk in the high-complexity area of ​​the mine, and generate various charts, such as heat maps, pie charts or bar charts, so as to intuitively present the distribution of risks in different areas. Combine the visualization results with the comprehensive evaluation data to generate a detailed comprehensive evaluation report on the geological hazard risk in the high-complexity area of ​​the mine. The report content includes evaluation methods, data sources, model construction process, result analysis and recommended measures, etc., to provide decision support and reference basis.

[0137] The beneficial effect of the present invention is that by acquiring multi-source spatial data of mines and conducting geological disaster risk distribution analysis, the potential danger of the mining area can be comprehensively assessed, and a mine geological hazard distribution map can be generated to provide a scientific basis for subsequent decision-making. Using the probability data of mine geological distribution disasters to screen high-complexity spatial regions helps to identify and focus on areas with higher potential risks, enhancing the pertinence of risk assessment; at the same time, it divides the active and inactive areas of mines to ensure monitoring and management of various areas. Remote sensing image acquisition and analysis of inactive areas of mines can effectively monitor ecological changes and changes in water range, identify potential environmental influencing factors, and the generated environmental suitability data provides an important reference for regional governance. Comprehensively evaluating the comprehensive surface deformation data of the mine active area and the environmental suitability data of the inactive area makes the assessment results more comprehensive and reflects the geological disaster risks in different regions; through data visualization, the readability and intuitiveness of the report are improved, which helps relevant decision makers to understand the risk situation in a timely manner and take necessary measures. Therefore, the present invention improves the accuracy and comprehensiveness of the comprehensive evaluation of the risk of geological hazards in mines by integrating multi-source data, emphasizing spatial distribution characteristics, distinguishing between active and inactive areas, and analyzing ecological and water changes.

[0138] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0139] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A comprehensive evaluation method for the risk of mining geological hazards taking into account spatial distribution characteristics, characterized in that: The following steps are involved: Step S1: Acquire multi-source spatial data of mines; perform mine geological disaster risk distribution analysis on the mine multi-source spatial data to generate a mine geological hazard distribution map; perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data; Step S2: screening the mine geological hazard distribution map for high-complexity spatial regions using the mine geological distribution disaster probability data to obtain high-complexity spatial region data; Divide the mining activity area of ​​high-complexity spatial regional data into mining activity areas and generate mining inactivity areas; Conducting comprehensive surface deformation analysis on the mining activity area to generate comprehensive surface deformation data of the mining activity area; the division of the mining activity area for the highly complex spatial regional data is specifically as follows: Perform spatial RGB color mapping on the high-complexity spatial region data to generate spatial pixel color mapping data; divide the high-complexity spatial region data into mine activity areas based on the spatial pixel color mapping data to generate mine activity areas and mine inactive areas; Step S3: collect regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine; perform vegetation change dynamic analysis on the remote sensing images of the inactive area of ​​the mine to generate ecological change data of the inactive area; perform water body range change analysis on the remote sensing images of the inactive area of ​​the mine to generate water body range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data of the inactive area and the water body range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine; Step S4: Conduct a comprehensive evaluation of the geological hazard risk of mines based on the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area to generate comprehensive evaluation data of the geological hazard risk of mines with high complexity; visualize the comprehensive evaluation data of the geological hazard risk of mines with high complexity to generate a comprehensive evaluation report of the geological hazard risk of mines with high complexity.

2. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire multi-source spatial data of mines; Step S12: preprocessing the mine multi-source spatial data to generate standard mine multi-source spatial data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S13: Based on GIS technology, the mine geological disaster risk distribution analysis is performed on the standard mine multi-source spatial data to generate a mine geological risk distribution map; Step S14: Perform spatial regional potential disaster probability analysis on the mine geological hazard distribution map to generate mine geological distribution disaster probability data.

3. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 2 is characterized in that: Step S13 includes the following steps: Step S131: classifying the influencing factors of the standard mine multi-source spatial data to generate influencing factor classification data, wherein the influencing factor classification data includes geological factor data, meteorological factor data, topographic factor data and historical disaster factor data; using GIS technology to perform spatial distribution characteristic stratification on the geological factor data, meteorological factor data, topographic factor data and historical disaster factor data to generate a comprehensive influencing factor layer; Step S132: performing spatial interpolation on the comprehensive influencing factor layer to generate a mine geological spatial distribution map; performing risk assessment on the geological factor data, meteorological factor data, topographic factor data and historical disaster factor data to generate comprehensive influencing factor risk assessment data; Step S133: weighting the comprehensive influencing factor hazard assessment data to generate comprehensive influencing factor hazard weights; weighted superposition of the comprehensive influencing factor hazard weights by the mine geological spatial distribution map to generate a comprehensive geological disaster hazard index map; Step S134: Classify the mine hazard areas of the standard mine multi-source spatial data according to the hazard weights of comprehensive influencing factors to generate mine hazard classification area data; spatially associate the mine hazard classification area data with the geological disaster hazard comprehensive index map to generate a mine geological hazard distribution map.

4. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: grid pixelating the mine geological hazard distribution map to generate a mine geological hazard distribution space unit; extracting pixel information from the mine geological hazard distribution space unit to obtain space unit pixel information data; Step S142: Analyze the pixel size and spatial attribute of the spatial unit pixel information data to generate spatial unit pixel size data and spatial unit attribute data; perform potential probability calculation on the mine geological hazard distribution map based on the spatial unit pixel information data to obtain mine geological potential probability distribution data; Step S143: spatially clustering the mine geological hazard distribution map based on the mine geological potential probability distribution data using the spatial unit pixel size data and the spatial unit attribute data to generate mine geological distribution disaster probability data.

5. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Calculate the disaster complexity of the mine geological hazard distribution map using the mine geological distribution disaster probability data to obtain regional disaster complexity data; screen the mine geological hazard distribution map for high-complexity spatial regions based on the regional disaster complexity data to obtain high-complexity spatial regional data; Step S22: performing spatial RGB color mapping on the high-complexity spatial region data to generate spatial pixel color mapping data; dividing the high-complexity spatial region data into mine activity areas based on the spatial pixel color mapping data to generate mine activity areas and mine inactive areas; Step S23: Perform global surface deformation monitoring on the mining activity area to generate global surface deformation monitoring data for the mining activity area; perform local surface deformation analysis on the surface deformation monitoring data for the mining activity area to generate local surface deformation analysis data for the local activity area; perform comprehensive data fusion on the global surface deformation monitoring data for the mining activity area and the surface deformation analysis data for the local activity area to generate comprehensive surface deformation data for the mining activity area.

6. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 5 is characterized in that: Step S23 includes the following steps: Step S231: performing global multi-temporal radar image acquisition on the mine activity area to obtain multi-temporal radar image data of the activity area; performing interference processing on the multi-temporal radar image data of the activity area to generate a synthetic aperture radar interferogram of the activity area; Step S232: extracting phase information from the active area synthetic aperture radar interference pattern to obtain active area phase information data; performing phase unwrapping on the active area phase information data to generate unwrapped active area interference phase information data; Step S233: Calculate the pixel deformation amplitude of the unwrapped active area interference phase information data to obtain phase deformation amplitude data; perform deformation time series analysis on the phase deformation amplitude data to generate global mine active area surface deformation monitoring data; Step S234: Perform local surface deformation analysis on the surface deformation monitoring data of the mining activity area through global navigation satellite technology to generate surface deformation analysis data of the local activity area; perform comprehensive data fusion on the global mining activity area surface deformation monitoring data and the local activity area surface deformation analysis data to generate comprehensive surface deformation data of the mining activity area.

7. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 6 is characterized in that: Step S234 includes the following steps: Step S2341: selecting key surface deformation positions of the surface deformation monitoring data of the mining activity area through global navigation satellite technology to obtain key surface deformation area data; deploying GNSS monitoring stations for the key surface deformation area data to generate GNSS monitoring station deployment position data; Step S2342: collecting GNSS satellite signals for the GNSS monitoring station deployment location data to obtain GNSS satellite signals at key locations; discretizing the GNSS satellite signals at key locations to generate discrete data of GNSS satellite signals at key locations; Step S2343: performing discrete point relative displacement calculation on the discrete data of GNSS satellite signals at key positions to obtain discrete point relative displacement data; performing baseline vectorization on the discrete point relative displacement data to generate horizontal displacement change data at key positions and vertical displacement change data at key positions; Step S2344: Perform local key surface deformation analysis on the surface deformation monitoring data of the mining activity area through the horizontal displacement change data of key positions and the vertical displacement change data of key positions to generate local activity area surface deformation analysis data; perform comprehensive data fusion on the global mining activity area surface deformation monitoring data and the local activity area surface deformation analysis data to generate comprehensive surface deformation data of the mining activity area.

8. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: collecting regional remote sensing images of the inactive area of ​​the mine to obtain remote sensing images of the inactive area of ​​the mine; Step S32: Calculate the vegetation index of the remote sensing image of the mine inactive area to generate the vegetation index of the mine inactive area; perform a dynamic analysis of vegetation changes on the remote sensing image of the mine inactive area by using the vegetation index of the mine inactive area to generate ecological change data of the inactive area; Step S33: Analyze the water range changes of the remote sensing images of the inactive area of ​​the mine to generate water range change data of the inactive area; calculate the environmental suitability of the inactive area based on the ecological change data and the water range change data of the inactive area to obtain the environmental suitability data of the inactive area of ​​the mine.

9. The comprehensive evaluation method for the risk of mining geological hazards considering spatial distribution characteristics according to claim 8 is characterized in that: Step S32 The following steps are involved: Step S321: performing image preprocessing on the remote sensing image of the mine inactive area to generate a standard remote sensing image of the mine inactive area, wherein the image preprocessing includes geometric correction, atmospheric correction and image boundary clipping; Step S322: extracting red light band and near infrared band of remote sensing image of standard mine inactive area to obtain red light band data and near infrared band data; calculating vegetation index of red light band data and near infrared band data to generate vegetation index of mine inactive area; Step S323: comparing the vegetation index of the mine inactive area with the preset vegetation index threshold set; when the vegetation index of the mine inactive area is less than the first vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the mine inactive area is marked as a water body or bare soil vegetation area and removed; when the vegetation index of the mine inactive area is greater than or equal to the first vegetation index threshold in the preset vegetation index threshold set and less than the second vegetation index threshold in the preset vegetation index threshold set, the corresponding remote sensing image of the mine inactive area is marked as a sparse vegetation area; Step S324: when the vegetation index of the mine inactive area is greater than or equal to the second vegetation index threshold in the preset vegetation index threshold set and less than the third vegetation index threshold in the preset vegetation index threshold set, the corresponding mine inactive area remote sensing image is marked as a medium vegetation area; Step S325: when the vegetation index of the mine inactive area is greater than or equal to the third vegetation index threshold in the preset vegetation index threshold set, the corresponding mine inactive area remote sensing image is marked as a dense vegetation area; Based on the sparse vegetation areas, medium vegetation areas and dense vegetation areas, the dynamic analysis of vegetation changes was carried out to generate ecological change data of inactive areas.

10. The comprehensive evaluation method of mine geological disaster risk considering spatial distribution characteristics according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: dividing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area into data sets to generate a model training set and a model test set; Step S42: training the model training set by using a convolutional neural network algorithm to generate a pre-model for comprehensive evaluation of mining geological hazards; optimizing and iterating the pre-model for comprehensive evaluation of mining geological hazards by using a model test set, thereby generating a comprehensive evaluation model for mining geological hazards; Step S43: Importing the comprehensive surface deformation data of the mine active area and the environmental suitability data of the mine inactive area into the mine geological disaster comprehensive evaluation model to conduct a comprehensive evaluation of the mine geological disaster risk, and generate comprehensive evaluation data of the geological disaster risk in the mine highly complex area; Step S44: Visualize the comprehensive evaluation data of geological hazards in highly complex areas of mines, so as to generate a comprehensive evaluation report of geological hazards in highly complex areas of mines.

Images