Geological disaster monitoring analysis method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of geological disasters, and discloses a geological disaster monitoring analysis method and device, electronic equipment and a storage medium. The method comprises the following steps: deploying a sensor in a drill hole in a target geological area; acquiring an output signal of the sensor, and processing the output signal to obtain an acquired digital signal with a unified format; analyzing according to the acquired digital signals to obtain karst development characteristic data, karst dynamic change data and ground subsidence data; performing calculation according to the acquired digital signals, the karst development characteristic data and the karst dynamic change data through a karst disaster prediction model to obtain karst disaster risk index data; calculating correlation between the land subsidence data and the acquired digital signals to obtain land subsidence correlation data; and displaying the karst disaster risk index data and the land subsidence correlation data in a preset visual mode. According to the method, geological disasters are accurately monitored, and efficient geological disaster data analysis and risk assessment are realized.

Description

Technical Field

[0001] This application relates to the technical field of geological disasters, and in particular, to a method, device, electronic device, and storage medium for monitoring and analyzing geological disasters. Background Art

[0002] In the field of geological disasters, traditional technologies for monitoring karst development and land subsidence mainly carry out parameter monitoring through sensors. For example, a water level gauge is used to regularly measure the change in the groundwater level to reflect hydrodynamic conditions, a level measurement or GPS device is used to obtain surface displacement data, or discrete exploration means such as core drilling and ground penetrating radar are used to obtain static information on karst development. Data collection relies on manual regular inspections or offline storage, with low frequency and the need for manual summary and processing. Monitoring points are mostly deployed as single points or in local areas, and data from different types of sensors work independently, lacking cross-device collaboration. Summary of the Invention

[0003] The main technical problem to be solved by the embodiments of this application is the single parameter and lack of real-time nature in traditional karst development and land subsidence monitoring.

[0004] To solve the above technical problem, the first technical solution adopted by the embodiments of this application is: to provide a method for monitoring and analyzing geological disasters, including: deploying different types of sensors at different depths inside a first number of boreholes preset in a target geological area, where the sensors cover different geological horizons penetrated by the boreholes; collecting in real time the output analog signals or digital signals of different types of the sensors, performing signal conversion processing on the analog signals, and performing signal adaptation processing on the digital signals to obtain the collected digital signals in a preset unified format; analyzing based on the preprocessed collected digital signals to obtain karst development characteristic data, karst dynamic change data, and land subsidence data; calculating, through a preset karst disaster prediction model, based on the preprocessed collected digital signals, the karst development characteristic data, and the karst dynamic change data to obtain karst disaster risk index data; using a preset data analysis algorithm to calculate the correlation between the land subsidence data and the collected digital signals to obtain land subsidence correlation data; and displaying the karst disaster risk index data and the land subsidence correlation data on a preset visualization platform through a preset visualization method.

[0005] Optionally, the step of collecting in real time the output analog or digital signals of different types of the sensors includes: monitoring in real time, by a microseismic sensor, the microseismic signal data generated by the rock fractures in different geological horizons; measuring in real time, by a strain sensor, the strain data of the rock on the borehole wall of the borehole, and measuring, by an inclinometer, the inclination degree data of the borehole at different depth positions; monitoring in real time, by a water level sensor, the water level change data of the groundwater, monitoring in real time, by a temperature sensor, the temperature information data of the groundwater, and detecting in real time, by a conductivity sensor, the conductivity data of the groundwater, and calculating the change data of the solute content of the groundwater according to the conductivity data.

[0006] Optionally, after the step of deploying different types of sensors at different depths inside a first number of boreholes preset in the target geological area, the method further includes: setting a preset second number of leveling points in different sub-areas in the target geological area, where at least one leveling point is set in each of the different sub-areas; establishing a horizontal line according to the data of a preset third number of level instruments in the target geological area; taking a reference point with a known elevation as a starting point, and sequentially measuring the height difference data between each of the leveling points according to the horizontal line and a preset route, where the height difference is measured by a leveling staff arranged at the current leveling point; calculating the elevation data of the leveling points according to the height difference data, and performing data analysis according to the height difference data and the elevation data to obtain the ground settlement data of the target geological area.

[0007] Optionally, the step of analyzing the preprocessed collected digital signals to obtain karst development characteristic data and karst dynamic change data includes: performing spectrum analysis on the microseismic signal data, and extracting the rock change characteristic data in the target geological area from the strain data of the rock on the borehole wall and the inclination degree data; performing simulation calculation according to the spectrum analysis result data and the rock change characteristic data to obtain the karst development characteristic data; analyzing the flow direction, flow velocity change, recharge and dissipation data of the karst water according to the water level change data, the temperature information data and the conductivity data; and generating the karst dynamic change data by using the flow direction, flow velocity change, recharge and dissipation data.

[0008] Optionally, the step of calculating, by means of a preset karst disaster prediction model, karst disaster risk index data based on the preprocessed collected digital signals, the karst development characteristic data, and the karst dynamic change data includes: normalizing the collected digital signals, the karst development characteristic data, and the karst dynamic change data by means of a preset data standardization rule to obtain data to be analyzed and predicted; extracting geological characteristic data of various preset characteristic measurement dimensions from the data to be analyzed and predicted, and fusing the geological characteristic data of various types into a geological comprehensive characteristic vector; obtaining historical karst disaster data within the target geological area, and adjusting the parameters of the karst disaster prediction model according to the historical karst disaster data; inputting the geological comprehensive characteristic vector into the adjusted karst disaster prediction model, and calculating through the model algorithm of the karst disaster prediction model to obtain the karst disaster risk index data.

[0009] Optionally, the step of calculating the correlation between the ground settlement data and the collected digital signals by means of a preset data analysis algorithm to obtain ground settlement correlation data includes: screening out ground settlement associated signals from the collected digital signals according to a preset data screening rule, and performing normalized data preprocessing on the ground settlement associated signals; performing data feature extraction processing on the preprocessed ground settlement associated signals to obtain a ground settlement associated feature vector; calculating a correlation value by means of a preset correlation algorithm using the ground settlement data and the ground settlement associated feature vector, and performing data analysis according to the correlation value to obtain a correlation analysis result.

[0010] Optionally, after the step of performing data analysis according to the correlation value to obtain a correlation analysis result, the method further includes: establishing a ground settlement prediction model according to the correlation analysis result, and setting different weight coefficients corresponding to different ground settlement associated signals in the model; dividing the obtained historical ground settlement data into a training data set and a validation data set, training the ground settlement prediction model using the training data set, and optimizing the weight coefficients according to the training results; validating the optimized ground settlement prediction model using the validation data set, and calculating evaluation index data for the optimized ground settlement prediction model. If the evaluation index data is within a preset evaluation index threshold range, a trained ground settlement prediction model is obtained; sending the collected digital signals collected in real time to the trained ground settlement prediction model to obtain ground settlement prediction data for the target geological area.

[0011] To solve the above technical problems, the second technical solution adopted in the embodiments of the present application is: to provide a geological disaster monitoring and analysis device, including: a sensor deployment module, configured to deploy different types of sensors at different depths inside a first number of boreholes preset in a target geological area, wherein the sensors cover different geological horizons penetrated by the boreholes; a signal real-time acquisition module, configured to real-time acquire the output analog signals or digital signals of different types of the sensors, perform signal conversion processing on the analog signals, and perform signal adaptation processing on the digital signals to obtain acquired digital signals in a preset unified format; a signal data analysis module, configured to analyze based on the preprocessed acquired digital signals to obtain karst development characteristic data, karst dynamic change data, and ground settlement data; a risk index data module, configured to calculate karst disaster risk index data through a preset karst disaster prediction model according to the preprocessed acquired digital signals, the karst development characteristic data, and the karst dynamic change data; a ground settlement data module, configured to calculate the correlation between the ground settlement data and the acquired digital signals using a preset data analysis algorithm to obtain ground settlement correlation data; a visualization display module, configured to display the karst disaster risk index data and the ground settlement correlation data on a preset visualization platform through a preset visualization method.

[0012] To solve the above technical problems, the third technical solution adopted in the embodiments of the present application is: to provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the geological disaster monitoring and analysis method as described above.

[0013] To solve the above technical problems, the fourth technical solution adopted in the embodiments of the present application is: to provide a non-volatile computer-readable storage medium storing computer-executable instructions, and when the computer-executable instructions are executed by an electronic device, the electronic device is enabled to execute the geological disaster monitoring and analysis method as described above.

[0014] Different from the related technologies, in this application, various types of sensors are deployed at different depths in the boreholes of the target geological area to comprehensively collect geological signals, unify the formats of analog and digital signals, and then deeply analyze to obtain key data such as karst development, dynamic changes, and ground settlement. The risk index of karst disasters is calculated using a preset model, and the correlation of ground settlement is analyzed. Finally, the data is visually presented on a visualization platform, realizing multi-dimensional and refined monitoring and analysis of geological disasters, enabling accurate assessment of disaster risks in advance, providing data basis for disaster prevention and mitigation and regional rational planning, and effectively making up for the deficiencies of traditional technologies in terms of monitoring comprehensiveness, analysis accuracy, and data visualization applications. Brief Description of the Drawings

[0015] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations do not limit the embodiments. Elements with the same reference numerals in the drawings represent similar elements. Unless otherwise stated, the figures in the drawings do not constitute a scale limitation.

[0016] Figure 1 It is a schematic diagram of the operating environment of the geological disaster monitoring and analysis method provided by the embodiment of this application.

[0017] Figure 2 It is a schematic diagram of the execution process of the geological disaster monitoring and analysis method provided by the embodiment of this application.

[0018] Figure 3 It is a schematic diagram of the execution process of obtaining ground settlement data in the geological disaster monitoring and analysis method provided by the embodiment of this application.

[0019] Figure 4 It is a schematic diagram of the execution process of obtaining karst disaster risk index data in the geological disaster monitoring and analysis method provided by the embodiment of this application.

[0020] Figure 5 It is a schematic diagram of the system structure of the geological disaster monitoring and analysis device provided by the embodiment of this application.

[0021] Figure 6 It is a schematic diagram of the hardware structure of the electronic device for executing the geological disaster monitoring and analysis method provided by the embodiment of this application. Detailed Description of the Embodiments

[0022] In order to make the purpose, technical solutions, and advantages of this application clearer, the following further details this application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0023] It should be noted that if there is no conflict, the various features in the embodiments of the present application can be combined with each other, and all are within the protection scope of the present application. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division from that in the device schematic diagram or a different order from that in the flowchart.

[0024] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not used to limit this application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0025] For ease of understanding of this embodiment, first, a geological disaster monitoring and analysis method disclosed in the embodiments of the present application will be introduced in detail. Please refer to Figure 1 , Figure 1 which is a schematic diagram of the operating environment of the geological disaster monitoring and analysis method provided by the embodiments of the present application. As shown in Figure 1 , in the target address area where geological disaster monitoring and analysis are required, a preset number of boreholes are set. Different types of sensors are respectively set at different depths of the boreholes. The output data of the sensors is uploaded to the computer device through the network, and the computer device can also control the sensors in the boreholes through the network. In some possible implementation manners, the geological disaster monitoring and analysis method can be implemented by the processor calling the computer-readable instructions stored in the memory. Among them, Figure 1 the computer device in Figure 1 can be a server. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. It can be understood that

[0026] Please continue to refer to Figure 2 , Figure 2 which is a schematic diagram of the execution process of the geological disaster monitoring and analysis method provided by the embodiments of the present application. As shown in Figure 2 , it includes the following steps:

[0027] S1. Deploy different types of sensors at different depths inside a preset first number of boreholes in the target geological area, where the sensors cover different geological horizons penetrated by the boreholes.

[0028] As an alternative implementation, please continue to refer to Figure 3 , Figure 3 which is a schematic diagram of the execution process for obtaining ground settlement data in the geological disaster monitoring and analysis method provided by the embodiments of the present application. As shown in Figure 3 , it may include the following steps S11 to S14.

[0029] S11. Set a preset second number of level points in different sub-regions within the target geological area, where at least one level point is set in each different sub-region.

[0030] Among them, step S11 constructs a foundation for subsequent measurements. The distribution of level points in different sub-regions can comprehensively cover the entire target geological area, ensuring that the ground elevation changes in each part can be monitored, laying a foundation for accurately obtaining ground settlement information.

[0031] S12. Establish a horizontal line based on the data of a preset third number of level instruments within the target geological area.

[0032] Among them, the level instrument can provide a horizontal line of sight. The horizontal line established using the data of multiple level instruments is an important benchmark for subsequent measurement of height differences, ensuring that the measurement is carried out on a unified horizontal reference plane, improving the accuracy and reliability of the measurement results.

[0033] S13. Take a reference point with a known elevation as the starting point, and sequentially measure the height difference data between each level point according to the horizontal line and a preset route, where the height difference is measured by a leveling staff set at the current level point.

[0034] Among them, the process of step S13 is the key to gradually advancing the measurement. By comparing with the reference point, the relative height differences between each level point are measured, providing core data support for subsequent calculation of elevation data.

[0035] S14. Calculate the elevation data of the level points based on the height difference data, and perform data analysis based on the height difference data and the elevation data to obtain the ground settlement data of the target geological area.

[0036] Through the above steps S11 to S14, level points are reasonably set in the target geological area, an accurate horizontal line is established with a level instrument, the height differences between level points are measured based on this and the elevation is calculated, and then the ground settlement data is analyzed, which can comprehensively and accurately monitor the ground settlement status of the target area, provide key data support for the prevention and response to geological disasters, help take measures in advance, and reduce the losses that may be brought by the disasters.

[0037] S2. Real-time collect the output analog signals or digital signals of different types of sensors, perform signal conversion processing on the analog signals, and perform signal adaptation processing on the digital signals to obtain the collected digital signals in a preset unified format.

[0038] As an alternative implementation, the process of real-time collecting the output analog signals or digital signals of different types of sensors in step S2 may include the following sub-steps S21 to S23.

[0039] S21. Real-time monitor the microseismic signal data generated by rock fractures in different geological horizons through microseismic sensors.

[0040] Among them, in the geological environment, when rocks are stressed and fractured, tiny vibrations will be generated. These microseismic signals contain rich geological information. By real-time monitoring these signals, the changes in the internal structure of rocks can be detected in a timely manner, the stability of the geological horizons can be understood, and important clues can be provided for predicting possible geological disasters such as earthquakes and collapses.

[0041] S22. Real-time measure the strain data of the rock on the borehole wall through a strain sensor and the inclination degree data of the borehole at different depth positions through an inclination sensor.

[0042] Among them, when the surrounding geological environment changes, such as affected by factors such as pressure and temperature, the rock on the borehole wall will generate strain. By measuring these strain data, the mechanical state and deformation of the rock can be understood. The inclination sensor is used to measure the inclination degree data of the borehole at different depth positions. The inclination of the borehole may reflect the changes in the underground geological structure or the movement of the strata, and these data are of great significance for judging geological stability and potential geological disaster risks.

[0043] S23. Real-time monitor the water level change data of groundwater through a water level sensor, the temperature information data of groundwater through a temperature sensor, and the conductivity data of groundwater through a conductivity sensor, and calculate the change data of the solute content of groundwater according to the conductivity data.

[0044] Among them, the change of the groundwater level is related to various factors such as geological conditions, precipitation, and human activities. Its abnormal change may indicate the change of the geological structure or an impending geological disaster. The temperature sensor real-time monitors the temperature information data of groundwater. The change of groundwater temperature may be related to factors such as underground heat sources and geological activities. The conductivity sensor real-time detects the conductivity data of groundwater and calculates the change data of the solute content of groundwater according to the conductivity data. The change of the solute content of groundwater can reflect information such as the dissolution of geological horizons, the source and path of water flow, and is of great value for studying the geological structure and the occurrence mechanism of geological disasters.

[0045] Through the above steps S21 to S23, by comprehensively using various types of sensors to collect different types of geological data in real time, it is possible to comprehensively and meticulously understand the geological conditions of the target geological area, covering aspects such as vibrations, deformations, inclinations, water levels, temperatures, and solute contents of geological layers, providing rich information for the monitoring and analysis of geological disasters. Through in-depth analysis of these data, abnormal changes in the geological environment can be detected in a timely manner, and potential geological disasters such as earthquakes, collapses, and land subsidence can be predicted in advance. At the same time, these data also contribute to the study of the occurrence mechanisms and development laws of geological disasters, providing data support for formulating scientific and reasonable geological disaster prevention and control measures, thereby effectively reducing the losses caused by geological disasters.

[0046] S3. Analyze the collected digital signals after preprocessing to obtain karst development characteristic data, karst dynamic change data, and land subsidence data.

[0047] As an optional implementation method, the process of obtaining karst development characteristic data and karst dynamic change data in step S3 may include the following sub-steps S31 to S34.

[0048] S31. Conduct spectral analysis on the microseismic signal data, and extract rock change characteristic data within the target geological area from the borehole wall rock strain data and inclination degree data.

[0049] Among them, the microseismic signal data contains rich frequency information. Conducting spectral analysis on it can identify geological phenomena corresponding to different frequency components, such as characteristic frequencies generated by rock fractures of different scales. And extracting rock change characteristic data within the target geological area from the borehole wall rock strain data and inclination degree data can understand the stress and deformation conditions of the rock and the geological structure changes reflected by the borehole inclination, such as whether the rock has displacement, extrusion, etc. These data can provide a basic basis for subsequent judgment of karst development.

[0050] S32. Perform simulation calculations based on the spectral analysis result data and rock change characteristic data to obtain karst development characteristic data.

[0051] Among them, based on the spectral analysis result data and rock change characteristic data obtained in step S31, relevant geological models and algorithms are used for simulation calculations. By simulating the change process of rocks and the microseismic generation mechanism under different geological conditions, the characteristics of karst development, such as the scale, distribution, and development stage of karst caves, are inferred, thereby obtaining karst development characteristic data.

[0052] S33. Analyze the water level change data, temperature information data, and conductivity data to obtain the flow direction, flow velocity change, recharge, and dissipation data of karst water.

[0053] Among them, the water level change data can reflect the increase or decrease of the water storage capacity of the karst water. The temperature information data can help judge whether there is a mixture of different water sources in the karst water or whether it is affected by underground heat sources. The conductivity data is related to the solute content in the water and can reflect the degree of interaction between the karst water and the surrounding rocks. By comprehensively analyzing these three types of data, the flow direction of the karst water can be inferred. For example, the water level difference can indicate the water flow direction. The flow velocity change can be analyzed by combining the rate of water level change with the geological structure information. The recharge and dissipation of the karst water can be judged based on the comprehensive changes in water level, temperature, and conductivity at different times.

[0054] S34. Generate karst dynamic change data using the flow direction, flow velocity change, and recharge and dissipation data.

[0055] Through the above steps S31 to S34, the development status and dynamic changes of karst in the target geological area can be comprehensively and deeply understood. The karst development characteristic data helps to master the basic structure and potential risks of the karst system. For example, large karst caves that may exist can be discovered in advance, providing basic data for engineering construction and geological disaster prevention, and avoiding engineering site selection in unstable karst areas. The karst dynamic change data can reflect the activities of karst water in real time, which is of great significance for predicting geological disasters and environmental problems such as karst collapse and groundwater pollution diffusion. Combining these two types of data can provide a scientific basis for the early warning and prevention of geological disasters and the sustainable development of the region, and improve the ability to respond to geological disasters.

[0056] S4. Calculate the karst disaster risk index data through a preset karst disaster prediction model based on the preprocessed collected digital signals, karst development characteristic data, and karst dynamic change data.

[0057] As an alternative implementation manner, please continue to refer to Figure 4 , Figure 4 is a schematic flowchart of the execution process for obtaining the karst disaster risk index data in the geological disaster monitoring and analysis method provided by the embodiment of the present application. As shown in Figure 4 , it may include the following sub-steps S41 to S44.

[0058] S41. Normalize the collected digital signals, karst development characteristic data, and karst dynamic change data through preset data standardization rules to obtain the data to be analyzed and predicted.

[0059] For example, different types of collected digital signals, such as microseismic, strain, water level and other data, as well as karst development characteristic data (such as cave scale, distribution, etc.) and karst dynamic change data (such as water flow velocity, recharge situation), have different numerical ranges and dimensions respectively. By performing normalization processing through preset data standardization rules, that is, unifying these data into a specific numerical interval, such as [0, 1] or [-1, 1], it can eliminate the influence brought by the differences in data dimensions and value ranges, making the weights of various types of data more reasonable during subsequent analysis and model calculations, avoiding a certain data range being too large and dominating the model results, laying a foundation for accurate analysis and prediction, and the data to be analyzed and predicted obtained has consistency and comparability.

[0060] S42. Extract geological feature data of various preset feature measurement dimensions from the data to be analyzed and predicted, and fuse various geological feature data into a geological comprehensive feature vector.

[0061] Among them, the preset feature measurement dimensions are determined based on historical research and experience on the formation mechanism of karst disasters. For example, from the data to be analyzed and predicted, extract features such as peak frequency and energy for microseismic data; extract features such as cave connectivity and density from karst development characteristic data; extract features such as water flow direction change rate and recharge quantity change trend for karst dynamic change data. Then, combine these various geological feature data extracted from different data sources and different types of data together in a certain way to form a geological comprehensive feature vector. This vector comprehensively reflects the geological conditions of the target geological area and provides richer and more comprehensive input information for the karst disaster prediction model.

[0062] S43. Obtain historical karst disaster data within the target geological area, and adjust the parameters of the karst disaster prediction model according to the historical karst disaster data.

[0063] For example, the historical karst disaster data within the target geological area contains various information when karst disasters occurred in this area in the past, such as disaster type, occurrence time, location, severity, and the corresponding geological conditions at that time. Based on these historical data, it can be understood under what geological conditions karst disasters are more likely to occur, and which geological factors are more closely related to the severity of the disasters. Based on this information, adjust the parameters of the karst disaster prediction model, such as adjusting the weight coefficients corresponding to different geological features in the model, so that the model better fits the actual geological disaster occurrence law of this area and improves the accuracy of model prediction.

[0064] S44. Input the geological comprehensive feature vector into the adjusted karst disaster prediction model, and through the model algorithm calculation of the karst disaster prediction model, obtain karst disaster risk index data.

[0065] Among them, the model internally contains specific model algorithms. For example, the neural network algorithm performs complex connections and operations between neurons, or the logistic regression algorithm calculates based on the logical relationship between input features and the probability of disaster occurrence. The model comprehensively analyzes and operates on various geological factors using these algorithms according to the input comprehensive geological feature vector, and finally outputs quantified karst disaster risk index data, such as the occurrence probability of karst collapse, the possible level of land subsidence, etc.

[0066] Through the above steps S41 to S44, the standardization, feature extraction and fusion, model parameter tuning, and final calculation of geological disaster-related data can more accurately evaluate the karst disaster risk of the target geological area. Data standardization enables various types of data to play a balanced role in model calculations and improves the quality of the model input data. Extracting multi-dimensional geological features and fusing them into a comprehensive vector comprehensively presents the geological conditions and provides sufficient and valuable information for the model. Adjusting the model parameters based on historical karst disaster data makes the model more adaptable to the actual situation of the target area and enhances the pertinence and accuracy of the model. The finally obtained accurate karst disaster risk index data can provide a key basis for formulating scientific and reasonable geological disaster prevention and control strategies. For example, in high-risk areas, the monitoring frequency can be increased in advance and emergency plans can be formulated, and high-risk areas can be avoided during planning and construction, so as to effectively reduce the casualties and property losses caused by karst disasters.

[0067] S5. Calculate the correlation between the land subsidence data and the collected digital signals using a preset data analysis algorithm to obtain land subsidence correlation data.

[0068] As an optional implementation method, the above step S5 may further include the following sub-steps S51 to S53.

[0069] S51. Screen out the land subsidence associated signals from the collected digital signals according to the preset data screening rules, and perform normalized data preprocessing on the land subsidence associated signals.

[0070] Among them, among the large number of collected digital signals, not all signals are closely related to land subsidence. The preset data screening rules are formulated based on professional knowledge of the influencing factors of land subsidence. For example, according to historical research and empirical data, it is clear that signals such as changes in groundwater level and soil layer stress and strain may be related to land subsidence. After screening out the land subsidence associated signals according to this rule, since these signals may come from different types of sensors and there are differences in their numerical ranges, dimensions, etc., performing normalized data preprocessing to unify them into a standard numerical interval can eliminate the interference of data differences on subsequent analysis and ensure the comparability and effectiveness of the data.

[0071] S52. Extract data features from the preprocessed ground settlement correlation signals to obtain ground settlement correlation feature vectors.

[0072] For example, through data feature extraction, representative and distinguishable features are mined from the ground settlement correlation signals. For instance, features such as the rate of water level change and the fluctuation period are extracted from the groundwater level signals, and features such as the stress change amplitude and the strain growth trend are extracted from the soil layer stress-strain signals. Combining the extracted features into ground settlement correlation feature vectors can concisely and accurately describe the signal features related to ground settlement, providing key inputs for subsequent correlation analysis.

[0073] S53. Use a preset correlation algorithm to calculate the correlation value using the ground settlement data and the ground settlement correlation feature vectors, and perform data analysis based on the correlation value to obtain the correlation analysis result.

[0074] For example, apply a preset distance algorithm to calculate the distance between the ground settlement data and the ground settlement correlation feature vectors. The distance value reflects the degree of correlation tightness between the two in a quantitative form. By analyzing this distance value, the key factors affecting ground settlement can be identified, providing a basis for subsequent in-depth study of the formation mechanism of ground settlement and prediction of ground settlement trends.

[0075] Through the above steps S51 to S53, the correlation between the ground settlement data and the collected digital signals can be systematically and effectively analyzed. Data screening and normalization preprocessing improve the quality and usability of the data, avoiding interference from irrelevant data and data differences on the analysis results. Feature extraction processing converts complex signals into concise feature vectors, facilitating subsequent calculations and analysis. Analyzing the distance value can clearly reveal the key factors affecting ground settlement, helping relevant personnel better understand the occurrence mechanism of ground settlement. In practical applications, these results can be used to establish a more accurate ground settlement prediction model and take targeted measures in advance for the prevention and control of ground settlement, such as adjusting the groundwater extraction strategy and optimizing the engineering construction plan, thereby reducing the hazards caused by ground settlement.

[0076] As another alternative implementation, a ground settlement prediction data model can be established after obtaining the correlation analysis result. Specifically, it can include the following steps S54 to S.

[0077] S54. Establish a ground settlement prediction model based on the correlation analysis result and set different weight coefficients for different ground settlement correlation signals in the model.

[0078] Among them, the correlation analysis results represent the degree of association between different ground settlement associated signals and ground settlement. Based on this result, establishing a ground settlement prediction model essentially means constructing a mathematical expression or algorithm framework to describe the relationship between these associated signals and ground settlement. For example, if the correlation analysis shows that the changes in groundwater level and soil layer stress are highly correlated with ground settlement height, then these two factors will be emphasized in the model. Setting different weight coefficients for different ground settlement associated signals is to reflect the importance of their impacts on ground settlement. For example, if the change in groundwater level has a greater impact on ground settlement, a higher weight will be assigned to this signal of groundwater level change.

[0079] S55. Divide the obtained historical ground settlement data into a training data set and a validation data set, use the training data set to train the ground settlement prediction model, and optimize the weight coefficients according to the training results.

[0080] For example, divide the obtained historical ground settlement data into a training data set and a validation data set according to a certain ratio (such as the common 7:3 or 8:2). The training data set is used to train the ground settlement prediction model. Just like students learn knowledge by doing exercises, the model adjusts its own parameters (mainly weight coefficients) by continuously processing the inputs (ground settlement associated signals) and corresponding outputs (ground settlement data) in the training data set. For example, during multiple training processes, the model dynamically optimizes the weight coefficients according to the difference between the prediction results and the actual ground settlement data, making the prediction results closer and closer to the true values.

[0081] S56. Use the validation data set to verify the optimized ground settlement prediction model, and calculate the evaluation index data for the optimized ground settlement prediction model. If the evaluation index data is within the preset evaluation index threshold range, the trained ground settlement prediction model is obtained.

[0082] Among them, use the validation data set to verify the optimized ground settlement prediction model and calculate the evaluation index data for the optimized ground settlement prediction model. Common evaluation indexes include mean square error, mean absolute error, etc. The mean square error measures the average of the squares of the errors between the predicted values and the true values. The smaller the error, the more accurate the model prediction. If the evaluation index data is within the preset evaluation index threshold range, it indicates that the prediction ability of the model meets the expected requirements, and at this time, the trained ground settlement prediction model is obtained.

[0083] S57. Send the collected digital signals collected in real time to the trained ground settlement prediction model to obtain the ground settlement prediction data of the target geological area.

[0084] Specifically, the trained land subsidence prediction model will process and analyze the collected real-time signals according to the previously learned rules, so as to obtain the land subsidence prediction data of the target geological area. For example, when real-time signals such as the current change in groundwater level and the change in soil layer stress are collected, the model can predict the possible land subsidence situation in the target geological area in the future for a period of time.

[0085] Through the above steps S54 to S57, a land subsidence prediction data model is established, which can effectively predict the land subsidence situation of the target geological area. Establishing the model and setting the weight coefficients based on the correlation analysis results ensure that the model can focus on the key influencing factors. Using historical data for training and verification, continuously optimizing the parameters of the model, and improving the accuracy and reliability of the model. Finally, the real-time collected signals can obtain the land subsidence prediction data through the trained model, providing data support for the early warning and prevention of geological disasters.

[0086] S6. Display the karst disaster risk index data and the land subsidence correlation data on a preset visualization platform through a preset visualization method.

[0087] Specifically, the karst development characteristic data, land subsidence data, karst collapse risk data, etc. obtained after a series of processing and analysis are presented in the form of intuitive and easy-to-understand charts, maps and other preset visualizations on the visualization platform. For example, using heat maps of different colors to display the high and low distribution areas of karst disaster risks, and presenting the change trend of land subsidence over time through line charts, so that relevant personnel can clearly and intuitively understand the real-time situation of karst development, land subsidence and karst collapse. At the same time, the system pre-sets the risk thresholds for land subsidence or karst collapse. Once the relevant risk data is predicted to exceed the threshold, the early warning system will issue an alarm in a timely manner. Relevant personnel can quickly take corresponding preventive and response measures according to the early warning information, such as evacuating residents in high-risk areas in a timely manner to ensure life safety, strengthening the buildings that may be affected to reduce losses, and adjusting the groundwater level by reasonably regulating groundwater extraction and other means, so as to effectively prevent the occurrence of geological disasters or reduce their harm.

[0088] The geological disaster monitoring and analysis method provided by the embodiments of this application comprehensively collects digital signals covering various aspects such as geological layer vibration, deformation, water level, and temperature by deploying various types of sensors at different depths inside the boreholes in the target geological area, preprocesses and deeply analyzes them to obtain karst development characteristic data, karst dynamic change data, ground settlement data, and correlation data, etc. It calculates karst disaster risk index data by means of a preset model, can also construct a ground settlement prediction model, and finally displays the data on a visualization platform and sets up an early warning mechanism, which can monitor the geological conditions comprehensively and accurately, deeply understand the occurrence mechanism of geological disasters, provide data support for geological disaster early warning, prevention, and regional planning and construction, greatly improve the ability to respond to geological disasters, and effectively reduce the casualties and property losses caused by disasters.

[0089] Please continue to refer to Figure 5 , Figure 5 which is a schematic system structure diagram of the geological disaster monitoring and analysis device provided by the embodiments of this application. As Figure 5 shown, the geological disaster monitoring and analysis device 50 includes: a sensor deployment module 51, a signal real-time acquisition module 52, a signal data analysis module 53, a risk index data module 54, a ground settlement data module 55, and a visualization display module 56.

[0090] The sensor deployment module 51 is specifically used to deploy different types of sensors at different depths inside a preset first number of boreholes in the target geological area, where the sensors cover different geological horizons penetrated by the boreholes.

[0091] The signal real-time acquisition module 52 is specifically used to real-time collect the output analog signals or digital signals of different types of the sensors, perform signal conversion processing on the analog signals, and perform signal adaptation processing on the digital signals to obtain the collected digital signals in a preset unified format.

[0092] The signal data analysis module 53 is specifically used to analyze based on the preprocessed collected digital signals to obtain karst development characteristic data, karst dynamic change data, and ground settlement data.

[0093] The risk index data module 54 is specifically used to calculate karst disaster risk index data through a preset karst disaster prediction model according to the preprocessed collected digital signals, the karst development characteristic data, and the karst dynamic change data.

[0094] The ground settlement data module 55 is specifically used to calculate the correlation between the ground settlement data and the collected digital signals using a preset data analysis algorithm to obtain ground settlement correlation data.

[0095] The visualization display module 56 is specifically configured to display the karst disaster risk index data and the land subsidence correlation data on a preset visualization platform by using a preset visualization method.

[0096] As an alternative implementation, the signal real-time acquisition module 52 is further specifically configured to: monitor in real time the microseismic signal data generated by the rock fractures in different geological horizons through a microseismic sensor; measure in real time the strain data of the rock on the borehole wall of the borehole and the inclination degree data of the borehole at different depth positions through a strain sensor and an inclination sensor respectively; monitor in real time the water level change data of the groundwater through a water level sensor, the temperature information data of the groundwater through a temperature sensor, and the conductivity data of the groundwater through a conductivity sensor, and calculate the change data of the solute content of the groundwater according to the conductivity data.

[0097] As an alternative implementation, the sensor deployment module 51 is further specifically configured to: set a preset second number of leveling points in different sub-regions within the target geological area, where at least one leveling point is set in each different sub-region; establish a horizontal line according to the data of a preset third number of level instruments within the target geological area; take a reference point with a known elevation as the starting point, and sequentially measure the elevation difference data between each of the leveling points according to the horizontal line and a preset route, where the elevation difference is measured by a leveling staff arranged at the current leveling point; calculate the elevation data of the leveling points according to the elevation difference data, and perform data analysis based on the elevation difference data and the elevation data to obtain the land subsidence data of the target geological area.

[0098] As an alternative implementation, the signal data analysis module 53 is further specifically configured to: perform spectral analysis on the microseismic signal data, and extract the rock change characteristic data within the target geological area from the borehole wall rock strain data and the inclination degree data; perform simulation calculations according to the spectral analysis result data and the rock change characteristic data to obtain the karst development characteristic data; analyze the flow direction, flow velocity change, recharge and dissipation data of the karst water according to the water level change data, the temperature information data and the conductivity data; generate the karst dynamic change data by using the flow direction, flow velocity change, recharge and dissipation data.

[0099] As an alternative implementation, the risk index data module 54 is further specifically configured to normalize the collected digital signals, the karst development characteristic data, and the karst dynamic change data through a preset data normalization rule to obtain data to be analyzed and predicted; extract geological characteristic data of various preset characteristic measurement dimensions from the data to be analyzed and predicted, and fuse various types of the geological characteristic data into a geological comprehensive characteristic vector; obtain historical karst disaster data within the target geological area, and adjust the parameters of the karst disaster prediction model according to the historical karst disaster data; input the geological comprehensive characteristic vector into the adjusted karst disaster prediction model, and calculate through the model algorithm of the karst disaster prediction model to obtain the karst disaster risk index data.

[0100] As an alternative implementation, the land subsidence data module 55 is further specifically configured to screen out land subsidence associated signals from the collected digital signals according to a preset data screening rule, and perform normalized data preprocessing on the land subsidence associated signals; perform data feature extraction processing on the preprocessed land subsidence associated signals to obtain a land subsidence associated feature vector; calculate a correlation value using the land subsidence data and the land subsidence associated feature vector through a preset correlation algorithm, and perform data analysis according to the correlation value to obtain a correlation analysis result.

[0101] As an alternative implementation, the land subsidence data module 55 is further specifically configured to establish a land subsidence prediction model according to the correlation analysis result, and set different weight coefficients corresponding to different land subsidence associated signals in the model; divide the obtained historical land subsidence data into a training data set and a validation data set, use the training data set to train the land subsidence prediction model, and optimize the weight coefficients according to the training results; use the validation data set to validate the optimized land subsidence prediction model, and calculate evaluation index data for the optimized land subsidence prediction model. If the evaluation index data is within a preset evaluation index threshold range, the trained land subsidence prediction model is obtained; send the real-time collected collected digital signals to the trained land subsidence prediction model to obtain land subsidence prediction data for the target geological area.

[0102] It should be noted that the above geological disaster monitoring and analysis device can execute the geological disaster monitoring and analysis method provided in the embodiments of the present application, and has corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in the embodiments of the geological disaster monitoring and analysis device can be found in the geological disaster monitoring and analysis method provided in the embodiments of the present application.

[0103] Figure 6FIG. 0 is a schematic hardware structure diagram of an electronic device 600 for implementing the geological disaster monitoring and analysis method provided by an embodiment of the present application. As Figure 6 shown, the electronic device 600 includes:

[0104] One or more processors 610 and a memory 620. Figure 6 Here, one processor 610 is taken as an example.

[0105] The processor 610 and the memory 620 can be connected through a bus or other means. Figure 6 Here, connection through a bus is taken as an example.

[0106] The memory 620, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions / modules corresponding to the geological disaster monitoring and analysis method in the embodiments of the present application. The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 620, that is, implements the geological disaster monitoring and analysis method in the above method embodiments.

[0107] The memory 620 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the geological disaster monitoring and analysis device, etc. In addition, the memory 620 may include a high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 620 may optionally include a memory remotely set relative to the processor 610, and these remote memories can be connected to the geological disaster monitoring and analysis device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] The one or more modules are stored in the memory 620 and, when executed by the one or more processors 610, execute the geological disaster monitoring and analysis method in any of the above method embodiments. For example, execute the Figure 2 method steps S1 to S6 described above, Figure 3 method steps S11 to S14 described above, Figure 4 method steps S41 to S44 described above, and implement the Figure 5 functions of modules 51-56 described above.

[0109] The above product can execute the method provided by the embodiments of the present application, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided by the embodiments of the present application.

[0110] An embodiment of the present application provides a non-volatile computer-readable storage medium storing computer-executable instructions, which are executed by one or more processors, such as Figure 6 one of the processors 610 among them, enabling the above one or more processors to execute the geological disaster monitoring and analysis method in any of the above method embodiments. For example, execute the Figure 2 method steps S1 to S6 described above in Figure 3 method steps S11 to S14 in Figure 4 method steps S41 to S44 in Figure 5 to implement the functions of the modules 51-56 in

[0111] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by the electronic device, the electronic device can execute the geological disaster monitoring and analysis method in any of the above method embodiments. For example, execute the Figure 2 method steps S1 to S6 described above in Figure 3 method steps S11 to S14 in Figure 4 method steps S41 to S44 in Figure 5 to implement the functions of the modules 51-56 in

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] Through the description of the above embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes of implementing the above embodiment methods can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; under the idea of the present application, the technical features in the above embodiments or different embodiments can also be combined, and the steps can be implemented in any order, and there are many other changes in different aspects of the present application as described above. For the sake of brevity, they are not provided in detail; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

Claims

1. A geological disaster monitoring and analysis method, characterized in that: include: Deploy different types of sensors at different depths inside a first number of boreholes preset in a target geological area, wherein the sensors cover different geological layers penetrated by the boreholes; Collecting the output analog signals or digital signals of different types of sensors in real time, performing signal conversion processing on the analog signals, and performing signal adaptation processing on the digital signals, to obtain the collected digital signals in a preset unified format; Analyze the collected digital signals after preprocessing to obtain karst development characteristic data, karst dynamic change data and ground subsidence data; The karst disaster risk index data is obtained by calculating the pre-processed collected digital signal, the karst development characteristic data and the karst dynamic change data through a preset karst disaster prediction model; Calculate the correlation between the ground subsidence data and the collected digital signal using a preset data analysis algorithm to obtain ground subsidence correlation data; The karst disaster risk index data and the ground subsidence correlation data are displayed on a preset visualization platform in a preset visualization manner.

2. The geological disaster monitoring and analysis method according to claim 1, characterized in that: The step of real-time acquisition of output analog signals or digital signals of different types of sensors comprises: Real-time monitoring of microseismic signal data generated by rock fractures in different geological layers by microseismic sensors; The rock strain data of the borehole wall is measured in real time by a strain sensor, and the inclination degree data of the borehole at different depths is measured by an inclination sensor; The water level sensor monitors the groundwater level change data in real time, the temperature sensor monitors the groundwater temperature information data in real time, and the conductivity sensor detects the groundwater conductivity data in real time, and the groundwater solute content change data is calculated based on the conductivity data.

3. The geological disaster monitoring and analysis method according to claim 1, characterized in that: After the step of deploying different types of sensors at different depths inside a preset first number of boreholes in the target geological area, the method further includes: Setting a preset second number of leveling points in different sub-areas within the target geological area, wherein at least one leveling point is set for each of the different sub-areas; Establishing a horizontal line according to data of a third number of leveling instruments preset in the target geological area; Taking a reference point of known elevation as a starting point, measuring the elevation difference data between each level point in turn according to the horizontal line and the preset route, wherein the elevation difference is measured by a leveling rod set at the current level point; The elevation data of the level point is calculated based on the elevation difference data, and data analysis is performed based on the elevation difference data and the elevation data to obtain the ground subsidence data of the target geological area.

4. The geological disaster monitoring and analysis method according to claim 2, characterized in that: The step of analyzing the collected digital signals after preprocessing to obtain karst development characteristic data and karst dynamic change data comprises: Performing spectrum analysis on the microseismic signal data, and extracting rock change characteristic data in the target geological area from the borehole wall rock strain data and the inclination data; Perform simulation calculation based on the spectrum analysis result data and the rock change characteristic data to obtain the karst development characteristic data; Analyze and obtain the flow direction, flow velocity change, recharge and escape data of karst water according to the water level change data, the temperature information data and the conductivity data; The karst dynamic change data are generated using the flow direction, flow velocity change, recharge and escape data.

5. The geological disaster monitoring and analysis method according to claim 1, characterized in that: The step of obtaining karst disaster risk index data by calculating the pre-processed collected digital signals, the karst development characteristic data and the karst dynamic change data through a preset karst disaster prediction model includes: Normalizing the collected digital signals, the karst development characteristic data and the karst dynamic change data according to preset data normalization rules to obtain the prediction data to be analyzed; Extracting various geological characteristic data of preset characteristic measurement dimensions from the predicted data to be analyzed, and fusing the various geological characteristic data into a geological comprehensive characteristic vector; Acquiring historical karst disaster data in the target geological area, and adjusting parameters of the karst disaster prediction model according to the historical karst disaster data; The geological comprehensive characteristic vector is input into the adjusted karst disaster prediction model, and the karst disaster risk index data is obtained through calculation by the model algorithm of the karst disaster prediction model.

6. The geological disaster monitoring and analysis method according to claim 1, characterized in that: The step of using a preset data analysis algorithm to calculate the correlation between the ground subsidence data and the collected digital signal to obtain ground subsidence correlation data includes: Filtering the collected digital signals to obtain ground subsidence related signals according to preset data screening rules, and performing normalized data preprocessing on the ground subsidence related signals; Performing data feature extraction processing on the pre-processed ground subsidence related signal to obtain a ground subsidence related feature vector; The ground subsidence data and the ground subsidence associated feature vector are used to calculate a correlation value through a preset correlation algorithm, and data analysis is performed based on the correlation value to obtain a correlation analysis result.

7. The geological disaster monitoring and analysis method according to claim 6, characterized in that: After the step of performing data analysis according to the correlation value to obtain the correlation analysis result, the method further includes: Establishing a land subsidence prediction model according to the correlation analysis results, and setting different weight coefficients corresponding to different land subsidence related signals in the model; Dividing the acquired historical land subsidence data into a training data set and a validation data set, using the training data set to train the land subsidence prediction model, and optimizing the weight coefficient according to the training result; Using the validation data set to validate the optimized land subsidence prediction model, and calculating evaluation index data for the optimized land subsidence prediction model, if the evaluation index data is within a preset evaluation index threshold range, the trained land subsidence prediction model is obtained; The collected digital signal collected in real time is sent to the trained ground subsidence prediction model to obtain ground subsidence prediction data of the target geological area.

8. A geological disaster monitoring and analysis device, characterized in that: include: A sensor deployment module, configured to deploy different types of sensors at different depths inside a first number of boreholes preset in a target geological area, wherein the sensors cover different geological layers penetrated by the boreholes; A signal real-time acquisition module is used to acquire the output analog signals or digital signals of different types of sensors in real time, perform signal conversion processing on the analog signals, and perform signal adaptation processing on the digital signals to obtain the acquired digital signals in a preset unified format; A signal data analysis module, used to analyze the collected digital signals after preprocessing to obtain karst development characteristic data, karst dynamic change data and ground subsidence data; A risk index data module is used to calculate the karst disaster risk index data by using a preset karst disaster prediction model according to the pre-processed collected digital signal, the karst development characteristic data and the karst dynamic change data; A ground subsidence data module, used to calculate the correlation between the ground subsidence data and the collected digital signal using a preset data analysis algorithm to obtain ground subsidence correlation data; A visualization display module is used to display the karst disaster risk indicator data and the ground subsidence correlation data on a preset visualization platform in a preset visualization manner.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the geological disaster monitoring and analysis method described in any one of claims 1-7.

10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by an electronic device, the electronic device executes the geological disaster monitoring and analysis method described in any one of claims 1-7.

Images