Geological static and mining disturbance dynamic factor coupling disaster-causing risk prediction method

Abstract

The invention discloses a geological static and mining disturbance dynamic factor coupling disaster-causing risk prediction method, and relates to the technical field of geological risk prediction methods. The method comprises the following steps of S01, geological static factor analysis, S02, mining disturbance dynamic factor analysis, S03, coupling disaster-causing risk prediction model construction, S04, risk assessment and early warning system development, S05, early warning mechanism establishment, S06, model verification and S07, risk management and decision support. The accuracy of geological disaster risk prediction is remarkably improved; according to the method, a comprehensive risk prediction model is constructed by quantifying the complexity of a geological structure, such as an area coefficient, a structural area loss coefficient and the like, and combining ground stress changes and underground water level changes caused by mining activities; the data-driven method can accurately predict the occurrence probability of geological disasters, provides more scientific decision support for mine safety management, and effectively reduces the occurrence risk of geological disasters.

Description

Technical Field

[0001] The present invention relates to the technical field of geological risk prediction methods, and in particular to a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors. Background Art

[0002] With the rapid development of industrialization and urbanization, the mining of mineral resources has become increasingly frequent, which has had a significant impact on the geological environment. Geological static factors, such as geological structure, stratum inclination and thickness, and mining disturbance dynamic factors, such as changes in ground stress and groundwater level, are key factors affecting the stability and safety of mining areas. In order to effectively predict and prevent geological disasters, a disaster risk prediction method that can comprehensively consider geological static and mining disturbance dynamic factors is needed.

[0003] Existing geological hazard risk assessment methods often focus on the analysis of a single factor, such as only considering the stability of geological structures or the impact of mining activities, while ignoring the interaction and coupling effects between these factors. In addition, traditional assessment methods often lack the ability to monitor and dynamically update in real time, making it difficult to adapt to the rapid changes in the geological environment. Furthermore, due to the lack of efficient data processing and analysis tools, existing methods are inefficient in processing large amounts of complex data, making it difficult to achieve accurate risk assessment.

[0004] To this end, the present invention proposes a disaster risk prediction method that constructs a coupling of geological static and mining disturbance dynamic factors, thereby improving the accuracy and reliability of risk assessment. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for predicting disaster risks by coupling geological static factors with mining disturbance dynamic factors, which solves the problem of incomplete assessment caused by single factor analysis in the prior art mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for predicting disaster risk by coupling geological static factors with mining disturbance dynamic factors, the method is as follows:

[0007] S01. Analysis of geological static factors:

[0008] Identify and analyze geological structures, including faults, folds, lithology, stratum dip and thickness;

[0009] Assess the complexity and activity of geological structures, as well as the deformation-metamorphic characteristics of coal seams;

[0010] Consider the initial state of the geological environment, including groundwater level and ground stress state;

[0011] S02. Analysis of dynamic factors of mining disturbance:

[0012] Analyze the impact of mining activities on the geological environment, including changes in ground stress, fracture development, and groundwater level caused by mining;

[0013] Consider dynamic changes in the mining process, such as mining speed, mining depth, and mining layout;

[0014] Assess the impact of mining activities on the stability of geological structures, such as ground subsidence and rock fracture caused by mining;

[0015] S03. Construction of coupled disaster risk prediction model:

[0016] Use numerical simulation techniques, such as the finite element method, to simulate the coupling effects of geological static factors and mining disturbance dynamic factors;

[0017] Combined with historical geological disaster data, the contribution of different factors to disaster risk is determined through statistical analysis;

[0018] Use machine learning methods, such as random forest and support vector machine, to build disaster risk prediction models;

[0019] S04. Risk assessment and early warning system development:

[0020] Based on the GIS platform, integrate multiple sources of data including geology, mining, and environment to develop a geological disaster risk assessment and early warning system;

[0021] Implement real-time monitoring and data analysis to dynamically update risk assessment results;

[0022] S05. Establish an early warning mechanism:

[0023] When the risk assessment results exceed the preset threshold, an early warning will be issued in a timely manner;

[0024] S06. Model Validation:

[0025] Select representative mines as cases and collect relevant geological and mining data;

[0026] Apply the constructed risk prediction model to analyze cases and verify the accuracy and applicability of the model;

[0027] Adjust and optimize the model based on the model prediction results and actual geological disaster events;

[0028] S07.Risk management and decision support:

[0029] Develop reasonable mining plans and risk management measures based on risk assessment results;

[0030] Provide decision support to help mine managers optimize resource development and environmental protection while ensuring safety.

[0031] Preferably, in S01, the complexity of the geological structure is quantitatively evaluated by a mathematical model, and the structural layers of the mathematical model for quantitative evaluation include:

[0032] Data layer: collects and organizes data related to geological structures, including but not limited to faults, folds, lithology, stratum dip and thickness; this layer is the basis of the model and provides raw input data for subsequent analysis;

[0033] Index layer: defines and calculates specific evaluation indicators, including area coefficient (A), structural area loss coefficient (S), fault density coefficient (M), fault strength index (F), and coal seam floor inclination variation coefficient (R); the indicators are extracted from the data layer through mathematical formulas and statistical methods, and quantify the specific characteristics of the geological structure;

[0034] Model layer: Construct mathematical models to integrate and process the data of the index layer, including the calculation of the structural isotope block comprehensive index (ZG); the model layer includes multiple sub-models, including the area index (ZGm) model, the small structure index (ZGx) model and the anomaly index (ZGy) model;

[0035] Evaluation layer: Use the output of the model layer to conduct a comprehensive evaluation to determine the complexity level of the geological structure; this layer converts the output of the model layer into specific evaluation results, which include medium, relatively complex, complex and extremely complex;

[0036] Decision support layer: Based on the results of the assessment layer, it provides decision support, including the selection of mining methods and the formulation of risk management strategies. This layer applies the assessment results to actual geological engineering decisions, providing a scientific basis for geological engineers and decision makers.

[0037] Uncertainty assessment layer: quantify the uncertainty of the model and evaluate the accuracy and reliability of the model; this layer uses statistical simulation and information entropy methods to evaluate the uncertainty of the model to ensure the accuracy of the evaluation results;

[0038] Optimization and update layer: Based on the feedback from the uncertainty assessment layer, the model is optimized and updated to improve its accuracy and applicability; this layer ensures that the model can adapt to new data and changing geological conditions, and maintains the timeliness and effectiveness of the model.

[0039] Preferably, the structural area loss coefficient (S) is expressed as:

[0040]

[0041] Among them, S1 is the coal-bearing area of ​​structural loss, and S0 is the block area; the statistics of this indicator use the contour map of the coal seam floor and the values ​​are obtained according to the mathematical models of the indicators;

[0042] The fault strength index (F) is mathematically expressed as:

[0043] τ s =μ(σ n -p f )=μσ′ n

[0044] Among them, τ s is the shear stress on the fault, μ is the friction coefficient, σ n is the normal stress on the fault, p f is the pore pressure, σ′ n is the effective normal stress, the calculation of which combines geomechanical and geophysical observations;

[0045] The coefficient of variation of the coal seam floor inclination (R) is expressed mathematically as follows:

[0046]

[0047] Where s is the standard deviation of the inclination, is the average inclination angle, x i is the inclination angle of the observation point, and n is the number of observation points.

[0048] Preferably, S04 needs to integrate multi-source data including geology, mining, and environment, including but not limited to topography, stratigraphic structure, lithology, fault distribution, groundwater level, and geological data of ground stress state, as well as historical and current data of mining activities, such as mining depth, mining method, and mining speed.

[0049] Preferably, the early warning method in S05 is:

[0050] Set dynamic thresholds: Use machine learning to analyze historical data, set and dynamically adjust risk thresholds;

[0051] Real-time data access: Integrate real-time monitoring data, such as earthquakes, rainfall, and surface displacement, and update them in real time through automated systems;

[0052] Risk assessment: Calculate risk indicators in real time and compare them with preset thresholds;

[0053] Automatic warning: When the threshold is exceeded, the system automatically sends a warning through the preset channel (SMS, application push);

[0054] Early warning classification: Set different early warning levels according to the risk level and clarify the response measures.

[0055] Preferably, the geological disaster data in S03 include the type, scale, impact range, occurrence frequency of geological disasters, and related geological, environmental, and human activity factors.

[0056] Preferably, the structure of constructing the coupled disaster risk prediction model in S03 is:

[0057] Data preprocessing layer: including spatial data processing, construction of spatial database of information indicators, and extraction of disaster-causing factors; this layer is responsible for converting the original geological data into a format suitable for model input; spatial data analysis and processing through GIS technology, and data cleaning and feature engineering using Python;

[0058] Model input layer: including data of geological static factors and mining disturbance dynamic factors. After being processed by the preprocessing layer, the data is used as the input of the model, including boundary conditions and initial conditions of displacement, velocity, and pressure physical quantities in the finite element method;

[0059] Numerical simulation layer: using finite element method to simulate the coupling effect of geological static factors and mining disturbance dynamic factors;

[0060] Statistical analysis layer: Combined with historical geological disaster data, statistical analysis is used to determine the contribution of different factors to disaster risk, and correlation analysis and regression analysis statistical methods are used to evaluate the importance of each factor;

[0061] Machine learning layer: Use machine learning methods, such as random forest and support vector machine, to build disaster risk prediction models, including model training and parameter optimization, as well as model verification and testing;

[0062] Risk assessment layer: Based on the output of the machine learning model, risk assessment and early warning are carried out, including the calculation of risk index and the classification of early warning levels;

[0063] Decision support layer: Provides decision support, including disaster prevention measures and emergency response plans; this layer converts the results of risk assessment into practical decision recommendations;

[0064] Model optimization layer: optimizes and adjusts the model according to its performance in actual applications, including monitoring model performance and adjusting model parameters;

[0065] Visualization and output layer: The model's prediction results and risk assessment conclusions are presented to users in an intuitive manner, such as through GIS maps, charts, and reports.

[0066] Preferably, the correlation analysis of the statistical analysis layer measures the linear correlation between two variables by calculating the correlation coefficient:

[0067]

[0068] Among them, x i and i are the observed values ​​of the two sets of data, and is their average value. The correlation coefficient ranges from -1 to 1. Values ​​close to 1 or -1 indicate strong correlation, and values ​​close to 0 indicate no correlation.

[0069] The present invention provides a method for predicting disaster risk by coupling geological static factors with mining disturbance dynamic factors. It has the following beneficial effects:

[0070] (1) The present invention significantly improves the accuracy of geological disaster risk prediction by coupling geological static factors with mining disturbance dynamic factors; the method quantifies the complexity of geological structures, such as area coefficient, structural area loss coefficient, etc., and combines the changes in ground stress and groundwater level caused by mining activities to construct a comprehensive risk prediction model; this data-driven method can accurately predict the probability of geological disasters, provide more scientific decision-making support for mine safety management, and effectively reduce the risk of geological disasters.

[0071] (2) The present invention realizes real-time monitoring and dynamic updating of the risk assessment and early warning system. By integrating multi-source data, such as geological, mining, and environmental data, the system can receive and process data in real time and dynamically update the risk assessment results. This real-time performance enables the system to respond quickly to changes in the geological environment and issue early warnings in a timely manner, providing mine managers with valuable time to take preventive measures, thereby reducing potential economic losses and environmental damage.

[0072] (3) The present invention utilizes the GIS platform and machine learning technology to greatly improve the efficiency of data processing and the accuracy of risk assessment. By constructing a spatial database and information indicators, the system can process and analyze a large amount of geological and mining data to achieve an accurate assessment of geological disaster risks. This method not only improves the efficiency of risk assessment, but also enhances the reliability of the assessment results, helping mine managers to optimize resource development and environmental protection and achieve sustainable development while ensuring safety. Through this method, the accuracy of geological disaster warning in mines has increased by 30%, and the time for risk assessment has been shortened by 50%, providing strong technical support for mine safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] See also Figure 1 The embodiment of the present invention provides a technical solution: a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors, the method is as follows:

[0076] S01. Analysis of geological static factors: Identify and analyze geological structures, including faults, folds, lithology, stratum dip and thickness; assess the complexity and activity of geological structures, as well as the deformation-metamorphic characteristics of coal seams; consider the initial state of the geological environment, including groundwater level and ground stress state;

[0077] S02. Analysis of dynamic factors of mining disturbance: Analyze the impact of mining activities on the geological environment, including changes in ground stress, crack development, and groundwater level caused by mining; consider dynamic changes in the mining process, such as mining speed, mining depth, and mining layout; evaluate the impact of mining activities on the stability of geological structures, such as ground subsidence and rock mass rupture caused by mining;

[0078] S03. Construction of coupled disaster risk prediction model: Use numerical simulation technology, such as finite element method, to simulate the coupling effect of geological static factors and mining disturbance dynamic factors; Combine historical geological disaster data and determine the contribution of different factors to disaster risk through statistical analysis; Use machine learning methods, such as random forest and support vector machine, to build a disaster risk prediction model;

[0079] S04. Risk assessment and early warning system development: Based on the GIS platform, integrate multiple sources of data including geology, mining, and environment to develop a geological disaster risk assessment and early warning system; implement real-time monitoring and data analysis, and dynamically update risk assessment results;

[0080] S05. Establish an early warning mechanism: when the risk assessment results exceed the preset threshold, issue an early warning in a timely manner;

[0081] S06. Model verification: Select representative mines as cases and collect relevant geological and mining data; apply the constructed risk prediction model to analyze the cases and verify the accuracy and applicability of the model; adjust and optimize the model according to the model prediction results and actual geological disaster events;

[0082] S07. Risk management and decision support: Based on the risk assessment results, formulate reasonable mining plans and risk management measures; provide decision support to help mine managers optimize resource development and environmental protection while ensuring safety.

[0083] In S01, the complexity of the geological structure is quantitatively evaluated by a mathematical model, and the structural layers of the mathematical model for quantitative evaluation include:

[0084] Data layer: collects and organizes data related to geological structures, including but not limited to faults, folds, lithology, stratum dip and thickness; this layer is the basis of the model and provides raw input data for subsequent analysis;

[0085] Index layer: defines and calculates specific evaluation indicators, including area coefficient (A), structural area loss coefficient (S), fault density coefficient (M), fault strength index (F), and coal seam floor inclination variation coefficient (R); the indicators are extracted from the data layer through mathematical formulas and statistical methods, and quantify the specific characteristics of the geological structure;

[0086] Model layer: Construct mathematical models to integrate and process the data of the index layer, including the calculation of the structural isotope block comprehensive index (ZG); the model layer includes multiple sub-models, including the area index (ZGm) model, the small structure index (ZGx) model and the anomaly index (ZGy) model;

[0087] Evaluation layer: Use the output of the model layer to conduct a comprehensive evaluation to determine the complexity level of the geological structure; this layer converts the output of the model layer into specific evaluation results, which include medium, relatively complex, complex and extremely complex;

[0088] Decision support layer: Based on the results of the assessment layer, it provides decision support, including the selection of mining methods and the formulation of risk management strategies. This layer applies the assessment results to actual geological engineering decisions, providing a scientific basis for geological engineers and decision makers.

[0089] Uncertainty assessment layer: quantify the uncertainty of the model and evaluate the accuracy and reliability of the model; this layer uses statistical simulation and information entropy methods to evaluate the uncertainty of the model to ensure the accuracy of the evaluation results;

[0090] Optimization and update layer: Based on the feedback from the uncertainty assessment layer, the model is optimized and updated to improve its accuracy and applicability; this layer ensures that the model can adapt to new data and changing geological conditions, and maintains the timeliness and effectiveness of the model.

[0091] The structural area loss coefficient (S) is mathematically expressed as:

[0092]

[0093] Among them, S1 is the coal-bearing area of ​​structural loss, and S0 is the block area; the statistics of this indicator use the contour map of the coal seam floor and the values ​​are obtained according to the mathematical models of the indicators;

[0094] The fault strength index (F) is mathematically expressed as:

[0095] τ s =μ(σ n -pf)=μσ′ n

[0096] Among them, τ s is the shear stress on the fault, μ is the friction coefficient, σ n is the normal stress on the fault, p f is the pore pressure, σ′ n is the effective normal stress, the calculation of which combines geomechanical and geophysical observations;

[0097] The coefficient of variation of the coal seam floor inclination (R) is expressed mathematically as follows:

[0098]

[0099] Where s is the standard deviation of the inclination, is the average inclination angle, x i is the inclination angle of the observation point, and n is the number of observation points.

[0100] The S04 needs to integrate multi-source data including geology, mining and environment, including but not limited to topography, stratigraphic structure, lithology, fault distribution, groundwater level, geological data of ground stress status, as well as historical and current data of mining activities, such as mining depth, mining method and mining speed.

[0101] The early warning method in S05 is: setting a dynamic threshold: using machine learning to analyze historical data, setting and dynamically adjusting the risk threshold;

[0102] Real-time data access: Integrate real-time monitoring data, such as earthquakes, rainfall, and surface displacement, and update them in real time through automated systems;

[0103] Risk assessment: Calculate risk indicators in real time and compare them with preset thresholds;

[0104] Automatic warning: When the threshold is exceeded, the system automatically sends a warning through the preset channel (SMS, application push);

[0105] Early warning classification: Set different early warning levels according to the risk level and clarify the response measures.

[0106] The geological disaster data in S03 include the type, scale, impact range, occurrence frequency of geological disasters, and related geological, environmental, and human activity factors.

[0107] The structure of the coupled disaster risk prediction model constructed in S03 is:

[0108] Data preprocessing layer: including spatial data processing, construction of spatial database of information indicators, and extraction of disaster-causing factors; this layer is responsible for converting the original geological data into a format suitable for model input; spatial data analysis and processing through GIS technology, and data cleaning and feature engineering using Python;

[0109] Model input layer: including data of geological static factors and mining disturbance dynamic factors. After being processed by the preprocessing layer, the data is used as the input of the model, including boundary conditions and initial conditions of displacement, velocity, and pressure physical quantities in the finite element method;

[0110] Numerical simulation layer: using finite element method to simulate the coupling effect of geological static factors and mining disturbance dynamic factors;

[0111] Statistical analysis layer: Combined with historical geological disaster data, statistical analysis is used to determine the contribution of different factors to disaster risk, and correlation analysis and regression analysis statistical methods are used to evaluate the importance of each factor;

[0112] Machine learning layer: Use machine learning methods, such as random forest and support vector machine, to build disaster risk prediction models, including model training and parameter optimization, as well as model verification and testing;

[0113] Risk assessment layer: Based on the output of the machine learning model, risk assessment and early warning are carried out, including the calculation of risk index and the classification of early warning levels;

[0114] Decision support layer: Provides decision support, including disaster prevention measures and emergency response plans; this layer converts the results of risk assessment into practical decision recommendations;

[0115] Model optimization layer: optimizes and adjusts the model according to its performance in actual applications, including monitoring model performance and adjusting model parameters;

[0116] Visualization and output layer: The model's prediction results and risk assessment conclusions are presented to users in an intuitive manner, such as through GIS maps, charts, and reports.

[0117] In order to specifically demonstrate the significant improvement of this solution in geological disaster risk prediction, this embodiment conducted a series of comparative experiments. Table 1 lists in detail the key indicators of this solution and traditional methods in terms of prediction accuracy. These data not only cover the prediction accuracy and warning timeliness, but also include the number of geological disasters, the number of false alarms and the number of missed alarms, thereby comprehensively evaluating the effectiveness of this solution;

[0118] Table 1: Comparison of geological disaster risk prediction accuracy

[0119]

[0120] Table 1 shows that this scheme improves the prediction accuracy by 30%, the warning timeliness by 87.5%, and significantly reduces the number of geological disasters, as well as the number of false alarms and missed alarms.

[0121] Table 2: Comparison of data processing and system response efficiency

[0122]

[0123] In Table 2, these data not only show the significant reduction in processing time and system response time, but also include a significant increase in data throughput and concurrent processing capabilities, as well as improved system availability; these two tables intuitively demonstrate the significant advantages of this solution in risk prediction accuracy and data processing efficiency through specific data descriptions, reflecting its beneficial effects.

[0124] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0125] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors, characterized in that: The method is as follows: S01. Analysis of geological static factors: Identify and analyze geological structures, including faults, folds, lithology, stratum dip and thickness; Assess the complexity and activity of geological structures, as well as the deformation-metamorphic characteristics of coal seams; Consider the initial state of the geological environment, including groundwater level and ground stress state; S02. Analysis of dynamic factors of mining disturbance: Analyze the impact of mining activities on the geological environment, including changes in ground stress, fracture development, and groundwater level caused by mining; Consider dynamic changes in the mining process, such as mining speed, mining depth, and mining layout; Assess the impact of mining activities on the stability of geological structures, such as ground subsidence and rock fracture caused by mining; S03. Construction of coupled disaster risk prediction model: Use numerical simulation techniques, such as the finite element method, to simulate the coupling effects of geological static factors and mining disturbance dynamic factors; Combined with historical geological disaster data, the contribution of different factors to disaster risk is determined through statistical analysis; Use machine learning methods, such as random forest and support vector machine, to build disaster risk prediction models; S04. Risk assessment and early warning system development: Based on the GIS platform, integrate multiple sources of data including geology, mining, and environment to develop a geological disaster risk assessment and early warning system; Implement real-time monitoring and data analysis to dynamically update risk assessment results; S05. Establish an early warning mechanism: When the risk assessment results exceed the preset threshold, an early warning will be issued in a timely manner; S06. Model Validation: Select representative mines as cases and collect relevant geological and mining data; Apply the constructed risk prediction model to analyze cases and verify the accuracy and applicability of the model; Adjust and optimize the model based on the model prediction results and actual geological disaster events; S07.Risk management and decision support: Develop reasonable mining plans and risk management measures based on risk assessment results; Provide decision support to help mine managers optimize resource development and environmental protection while ensuring safety.

2. According to claim 1, a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors, characterized in that: In S01, the complexity of the geological structure is quantitatively evaluated by a mathematical model, and the structural layers of the mathematical model for quantitative evaluation include: Data layer: collects and organizes data related to geological structures, including but not limited to faults, folds, lithology, stratum dip and thickness; this layer is the basis of the model and provides raw input data for subsequent analysis; Index layer: defines and calculates specific evaluation indicators, including area coefficient (A), structural area loss coefficient (S), fault density coefficient (M), fault strength index (F), and coal seam floor inclination variation coefficient (R); the indicators are extracted from the data layer through mathematical formulas and statistical methods, and quantify the specific characteristics of the geological structure; Model layer: Construct mathematical models to integrate and process the data of the index layer, including the calculation of the structural isotope block comprehensive index (ZG); the model layer includes multiple sub-models, including the area index (ZGm) model, the small structure index (ZGx) model and the anomaly index (ZGy) model; Evaluation layer: Use the output of the model layer to conduct a comprehensive evaluation to determine the complexity level of the geological structure; this layer converts the output of the model layer into specific evaluation results, which include medium, relatively complex, complex and extremely complex; Decision support layer: Based on the results of the assessment layer, it provides decision support, including the selection of mining methods and the formulation of risk management strategies. This layer applies the assessment results to actual geological engineering decisions, providing a scientific basis for geological engineers and decision makers. Uncertainty assessment layer: quantify the uncertainty of the model and evaluate the accuracy and reliability of the model; this layer uses statistical simulation and information entropy methods to evaluate the uncertainty of the model to ensure the accuracy of the evaluation results; Optimization and update layer: Based on the feedback from the uncertainty assessment layer, the model is optimized and updated to improve its accuracy and applicability; this layer ensures that the model can adapt to new data and changing geological conditions, and maintains the timeliness and effectiveness of the model.

3. According to claim 1, a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors is characterized by: The structural area loss coefficient (S) is mathematically expressed as: Among them, S1 is the coal-bearing area of ​​structural loss, and S0 is the block area; the statistics of this indicator use the contour map of the coal seam floor and the values ​​are obtained according to the mathematical models of the indicators; The fault strength index (F) is mathematically expressed as: t s =μ(σ n -p f )=μσ′ n Among them, τ s is the shear stress on the fault, μ is the friction coefficient, σ n is the normal stress on the fault, p f is the pore pressure, σ′ n is the effective normal stress, the calculation of which combines geomechanical and geophysical observations; The coefficient of variation of the coal seam floor inclination (R) is expressed mathematically as follows: Where s is the standard deviation of the inclination, is the average inclination angle, x i is the inclination angle of the observation point, and n is the number of observation points.

4. According to claim 1, a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors is characterized by: The S04 needs to integrate multi-source data including geology, mining and environment, including but not limited to topography, stratigraphic structure, lithology, fault distribution, groundwater level, geological data of ground stress status, as well as historical and current data of mining activities, such as mining depth, mining method and mining speed.

5. According to claim 1, a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors, characterized in that: The early warning method in S05 is: Set dynamic thresholds: Use machine learning to analyze historical data, set and dynamically adjust risk thresholds; Real-time data access: Integrate real-time monitoring data, such as earthquakes, rainfall, and surface displacement, and update them in real time through automated systems; Risk assessment: Calculate risk indicators in real time and compare them with preset thresholds; Automatic warning: When the threshold is exceeded, the system automatically sends a warning through the preset channel (SMS, application push); Early warning classification: Set different early warning levels according to the risk level and clarify the response measures.

6. According to claim 1, a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors is characterized by: The geological disaster data in S03 include the type, scale, impact range, occurrence frequency of geological disasters, and related geological, environmental, and human activity factors.

7. According to claim 1, a method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors is characterized by: The structure of the coupled disaster risk prediction model constructed in S03 is: Data preprocessing layer: including spatial data processing, construction of spatial database of information indicators, and extraction of disaster-causing factors; this layer is responsible for converting the original geological data into a format suitable for model input; spatial data analysis and processing through GIS technology, and data cleaning and feature engineering using Python; Model input layer: including data of geological static factors and mining disturbance dynamic factors. After being processed by the preprocessing layer, the data is used as the input of the model, including boundary conditions and initial conditions of displacement, velocity, and pressure physical quantities in the finite element method; Numerical simulation layer: using finite element method to simulate the coupling effect of geological static factors and mining disturbance dynamic factors; Statistical analysis layer: Combined with historical geological disaster data, statistical analysis is used to determine the contribution of different factors to disaster risk, and correlation analysis and regression analysis statistical methods are used to evaluate the importance of each factor; Machine learning layer: Use machine learning methods, such as random forest and support vector machine, to build disaster risk prediction models, including model training and parameter optimization, as well as model verification and testing; Risk assessment layer: Based on the output of the machine learning model, risk assessment and early warning are carried out, including the calculation of risk index and the classification of early warning levels; Decision support layer: providing decision support, including disaster prevention measures and emergency response plans; This layer converts the results of risk assessment into practical decision-making recommendations; Model optimization layer: optimizes and adjusts the model according to its performance in actual applications, including monitoring model performance and adjusting model parameters; Visualization and output layer: The model's prediction results and risk assessment conclusions are presented to users in an intuitive manner, such as through GIS maps, charts, and reports.

8. The method for predicting disaster risk caused by coupling geological static factors with mining disturbance dynamic factors according to claim 7, characterized in that: The correlation analysis at the statistical analysis layer measures the degree of linear correlation between two variables by calculating the correlation coefficient: Among them, x i and i are the observed values ​​of the two sets of data, and is their average value. The correlation coefficient ranges from -1 to 1. Values ​​close to 1 or -1 indicate strong correlation, and values ​​close to 0 indicate no correlation.

Images