Landslide geological disaster monitoring and early warning system based on multi-means fusion

Abstract

The invention relates to the technical field of geological disaster monitoring, in particular to a landslide geological disaster monitoring and early warning system based on multi-means fusion, which comprises a data acquisition module, a data fusion module, a landslide prediction module, a landslide disaster intelligent partition and response module and an early warning transmitting module, the data acquisition module acquires landslide related data in real time; the data fusion module is used for fusing landslide related data from different sources; the landslide prediction module is used for predicting the occurrence probability of the landslide; the landslide disaster intelligent partition and response module combines landslide related data and geologic structures monitored in real time, dynamically adjusts post-disaster response measures, and generates early warning information; and the early warning signal sending module automatically sends an early warning signal based on the generated early warning information. According to the invention, potential risks can be found in time in the early stage of landslide occurrence, and the accuracy and timeliness of disaster early warning are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular to a landslide geological disaster monitoring and early warning system based on multi-means fusion. Background Art

[0002] Landslide is a common geological disaster, and its occurrence is usually closely related to multiple factors such as geology, meteorology, and environment. Landslide disasters are sudden and destructive, often leading to serious consequences such as road interruption, building damage, casualties, etc., which have a great impact on social production and people's lives. Therefore, timely monitoring and early warning of landslide disasters, accurate assessment of the impact range of disasters and optimization of emergency response are important means to reduce losses and protect people's lives and property. With the development of science and technology, various monitoring technologies have been gradually applied to the early warning and prevention of landslide disasters, but how to efficiently and accurately obtain and process multi-source data is still a challenge in current technology.

[0003] Existing landslide monitoring and early warning technologies mainly rely on a single data source, such as real-time monitoring of soil moisture, precipitation or displacement data, but these methods have some shortcomings in practical applications. First, a single data source cannot fully reflect the entire process of landslide occurrence, and is prone to misjudgment or omission, especially in areas with complex geological and meteorological conditions. Second, most existing technologies rely on manual interpretation and simple model prediction, lack intelligent data fusion and analysis methods, and cannot fully utilize the advantages of different data sources. Third, traditional emergency response strategies are usually unable to dynamically adjust the risk levels of different regions, which can easily lead to unreasonable resource allocation and low response efficiency. Overall, existing technologies are difficult to cope with the real-time, accuracy and dynamic requirements of complex geological environments and landslide disasters.

[0004] The present invention provides a landslide geological disaster monitoring and early warning system based on the integration of multiple means, which can not only improve the early warning capability and accuracy of landslide disasters, but also optimize the emergency response process, improve the efficiency and effectiveness of disaster prevention and control, and ultimately provide scientific and accurate technical support for the prevention and control of landslide disasters. Summary of the invention

[0005] The invention provides a landslide geological disaster monitoring and early warning system based on multi-means fusion.

[0006] The landslide geological disaster monitoring and early warning system based on multi-means fusion includes data acquisition module, data fusion module, landslide prediction module, landslide disaster intelligent zoning and response module and early warning signaling module, among which;

[0007] The data acquisition module collects landslide-related data in real time, including soil moisture, precipitation, and displacement;

[0008] The data fusion module fuses the landslide-related data from different sources;

[0009] The landslide prediction module predicts the probability of landslide occurrence based on the fused landslide related data;

[0010] The landslide disaster intelligent zoning and response module intelligently identifies the affected area of ​​the landslide disaster based on the predicted results of the probability of landslide occurrence, combined with the real-time monitored landslide-related data and geological structure, and dynamically adjusts the post-disaster response measures to generate early warning information, including:

[0011] Identification of landslide-affected areas: Based on the probability prediction results of landslide occurrence, combined with real-time collected landslide-related data and geological structure information, the area affected by landslide disasters is determined;

[0012] Risk assessment and priority sorting: Based on the results of the division of the area affected by landslide hazards, the landslide hazard risks in different areas are divided into risk levels, and the priorities of each area are sorted according to the risk level;

[0013] Dynamic response adjustment: Dynamically adjust post-disaster response measures based on the results of risk assessment and priority sorting to optimize the allocation of post-disaster response resources;

[0014] Warning information generation: Generate warning information based on the results of landslide impact area identification, risk assessment and priority sorting, and dynamic response adjustment;

[0015] The early warning signal sending module automatically sends out an early warning signal based on the generated early warning information through a wireless communication device (SMS, APP push, broadcast) or an alarm device, and notifies relevant personnel and residents in a timely manner.

[0016] Optionally, the data acquisition module includes:

[0017] Soil moisture collection: Soil moisture sensors are used to measure the moisture changes in the soil in the landslide area in real time and monitor the fluctuations in soil moisture content;

[0018] Precipitation monitoring: Real-time monitoring of precipitation data in the landslide monitoring area through precipitation sensors;

[0019] Displacement detection: The displacement of the landslide monitoring area is detected in real time through displacement sensors.

[0020] Optionally, the data fusion module includes:

[0021] Data standardization: standardize the landslide-related data from different sensors and convert the data in different units into a unified standard measurement;

[0022] Weighted average calculation: The weighted average method is used to fuse the standardized landslide-related data to form comprehensive data. .

[0023] Optionally, the landslide prediction module includes:

[0024] Data input: The integrated data As input features ;

[0025] Prediction model establishment: The prediction model is established through the logistic regression algorithm. When training the prediction model, the log-likelihood function is used for optimization to obtain the optimal model parameters;

[0026] Landslide probability prediction: The trained prediction model is used to predict the probability of landslide based on the integrated data. .

[0027] Optionally, the landslide impact area identification includes:

[0028] Landslide probability threshold setting: The landslide probability obtained by calculation , based on the preset risk threshold Determine the landslide area. , then the area is judged as a landslide risk area;

[0029] Calculation of geological risk index: The comprehensive data is integrated with geological structure information, and the slope factor is considered to calculate the geological risk index through a weighted average algorithm. ;

[0030] Delineation of landslide affected areas: Based on the probability of landslide occurrence and geological risk index , determine the landslide disaster impact area through weighted calculation ;

[0031] Determination and dynamic adjustment of regional scope: Based on the calculated impact area, the boundaries of the affected area are dynamically adjusted, and the regional division is updated according to the changes in real-time landslide-related data to generate real-time landslide impact area information.

[0032] Optionally, the area range determination and dynamic adjustment include:

[0033] Defining the preliminary scope of the landslide affected area: Based on the probability of landslide occurrence and geological risk index , preliminarily determine the scope of the landslide affected area ;

[0034] Dynamically adjust the boundaries of the region: dynamically adjust the boundaries of the affected region based on changes in real-time landslide-related data (precipitation, soil moisture, displacement) within the landslide monitoring area;

[0035] Calculate the impact area boundary adjustment: based on the calculated impact area change, update the area boundary;

[0036] Real-time regional division: Based on the updated regional boundaries, the entire landslide monitoring area is divided in real time.

[0037] Optionally, the risk assessment and prioritization includes:

[0038] Risk level classification: Based on the classification results of landslide-affected areas, the probability of landslide occurrence is used and geological risk index , the risk score is calculated by a weighted algorithm ;

[0039] Risk level classification: Based on the calculated risk score , the landslide-affected areas are divided into several risk levels, including low risk, medium risk and high risk. When When When the landslide impact area is low risk

[0040] Prioritization: After completing the risk classification, the landslide-affected areas are prioritized according to their risk levels, with high-risk areas being given priority.

[0041] Optionally, the dynamic response adjustment includes:

[0042] Real-time assessment and update: Real-time monitoring of post-disaster developments, regular updates of risk levels and priorities for each landslide-affected area;

[0043] Dynamically adjust response strategies: Adjust post-disaster response strategies based on updated risk levels and priority rankings, including:

[0044] Resource scheduling optimization: According to the latest risk level of each region, the emergency resource allocation plan is adjusted in real time to give priority to ensuring the support of materials, personnel and equipment in high-risk areas;

[0045] Adjustment of rescue teams: Dynamically arrange the deployment of rescue teams based on the priority of each area, so that high-risk areas receive support as soon as possible;

[0046] Transportation and communication support: For high-risk areas with poor transportation or communication interruptions, timely adjustments will be made to the development of transportation channels and the repair of communication facilities.

[0047] Optionally, the generating of the warning information includes:

[0048] Generate landslide disaster impact area warning information: According to the landslide impact area identification results, determine the scope of the disaster impact area;

[0049] Generate risk level and response measures information: Based on the results of risk assessment and priority sorting, generate corresponding disaster risk levels and response measures for each area;

[0050] Post-disaster response plan integration and early warning notification: Based on the results of dynamic response adjustments, emergency response measures are integrated and final early warning information is generated, including disaster expansion prediction, resource scheduling, and personnel support plans.

[0051] Beneficial effects of the present invention:

[0052] The present invention can accurately identify the risk areas of landslides through the fusion and intelligent processing of multi-source landslide-related data. By collecting real-time data such as soil moisture, precipitation and displacement, combined with efficient data fusion and prediction models, it can timely discover potential risks in the early stages of landslides, greatly improving the accuracy and timeliness of disaster warnings.

[0053] The present invention realizes the accurate identification of the landslide disaster-affected areas through the fusion of landslide-related data, prediction results and geological structure information, and optimizes the allocation of post-disaster response measures through risk assessment and priority sorting. The system ensures that high-risk areas get priority in resources and personnel support by dynamically adjusting the response strategy, reduces the time delay of post-disaster emergency response, and optimizes the efficiency of rescue resource utilization. In addition, the risk level and priority are updated in real time, and the emergency response is continuously adjusted in combination with the post-disaster development situation, which can flexibly respond to changes in the disaster situation and significantly improve the post-disaster recovery capability.

[0054] The present invention, through the early warning information generation system of landslide-affected area identification, risk assessment, priority sorting and dynamic response adjustment, can timely generate early warning information for specific areas, and quickly transmit it to relevant personnel and residents through wireless communication devices or alarm devices, effectively ensuring the early warning time before the landslide disaster occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1A schematic diagram of system function modules according to an embodiment of the present invention;

[0057] Figure 2 Schematic diagram of intelligent landslide hazard zoning and response module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0059] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0060] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0061] like Figure 1-Figure 2 As shown, the landslide geological disaster monitoring and early warning system based on multi-means fusion includes a data acquisition module, a data fusion module, a landslide prediction module, a landslide disaster intelligent zoning and response module, and an early warning signaling module, wherein;

[0062] The data acquisition module collects landslide-related data in real time, including soil moisture, precipitation, and displacement;

[0063] The data fusion module fuses the landslide-related data from different sources;

[0064] The landslide prediction module predicts the probability of landslide occurrence based on the fused landslide-related data;

[0065] The landslide disaster intelligent zoning and response module intelligently identifies the affected areas of landslide disasters based on the predicted results of the probability of landslide occurrence, combined with the real-time monitored landslide-related data and geological structure, and dynamically adjusts the post-disaster response measures to generate early warning information, including:

[0066] Identification of landslide-affected areas: Based on the probability prediction results of landslide occurrence, combined with real-time collected landslide-related data and geological structure information, the area affected by landslide disasters is determined;

[0067] Risk assessment and priority sorting: Based on the results of the division of the area affected by landslide hazards, the landslide hazard risks in different areas are divided into risk levels, and the priorities of each area are sorted according to the risk level;

[0068] Dynamic response adjustment: Dynamically adjust post-disaster response measures based on the results of risk assessment and priority sorting to optimize the allocation of post-disaster response resources;

[0069] Warning information generation: Generate warning information based on the results of landslide impact area identification, risk assessment and priority sorting, and dynamic response adjustment;

[0070] The early warning signaling module automatically sends out early warning signals based on the generated early warning information through wireless communication devices (SMS, APP push, broadcast) or alarm devices, and notifies relevant personnel and residents in a timely manner;

[0071] Through the above contents, accurate monitoring, real-time warning and efficient emergency response of landslide disasters are achieved. It can comprehensively analyze multi-source data, intelligently identify disaster-affected areas, and dynamically adjust post-disaster response measures, thereby significantly improving the accuracy of landslide disaster warning and emergency response efficiency, reducing errors caused by human factors, especially in predicting disasters in complex terrain and unknown risk areas. The system has strong adaptability, real-time and reliability, and can provide scientific and accurate support for the prevention and control of landslide disasters.

[0072] The data acquisition module includes:

[0073] Soil moisture collection: Soil moisture sensors are used to measure the moisture changes in the soil in the landslide area in real time and monitor the fluctuations in soil moisture content;

[0074] Precipitation monitoring: Real-time monitoring of precipitation data in the landslide monitoring area through precipitation sensors;

[0075] Displacement detection: The displacement of the landslide monitoring area is detected in real time through the displacement sensor;

[0076] Through the above content, key environmental changes in landslide occurrence areas can be captured comprehensively and accurately. Not only can the fluctuations in soil moisture and precipitation be monitored in a timely manner to provide basic data for landslide risk assessment, but ground deformation can also be accurately detected through displacement sensors to help detect potential signs of landslides in advance.

[0077] The data fusion module includes:

[0078] Data standardization: The landslide-related data from different sensors are standardized and the data in different units are converted into a unified standard measurement, expressed as:

[0079] ;

[0080] in, is the original data, is the mean of the data, is the standard deviation of the data, is the standardized data;

[0081] Weighted average calculation: The weighted average method is used to fuse the standardized landslide-related data to form comprehensive data. , expressed as:

[0082] ;

[0083] in, , , are the standardized soil moisture, precipitation and displacement data, , , are the corresponding weights, is the integrated data after fusion;

[0084] Through the above content, it is ensured that various types of data can be compared and processed under the same standard, thereby eliminating the differences and errors between different sensors. By assigning different weights according to the reliability and accuracy of the data source, the advantages of each sensor can be fully utilized to improve the accuracy of data fusion, which not only optimizes the integration effect of multi-source data, but also enhances the system's prediction ability and stability for landslide risks.

[0085] The landslide prediction module includes:

[0086] Data input: The integrated data As input features ;

[0087] Prediction model establishment: The prediction model is established through the logistic regression algorithm. When training the prediction model, the log-likelihood function is used for optimization to obtain the optimal model parameters, which is expressed as:

[0088] ;

[0089] in, is the prediction function of the logistic regression algorithm, are model parameters, is the transpose of the model parameters, is the true label, is the input feature, is the log-likelihood function, is the number of training samples;

[0090] Landslide probability prediction: The trained prediction model is used to predict the probability of landslide based on the integrated data. , expressed as:

[0091] ;

[0092] in, is the integrated data after fusion. are the trained parameters, is the bias term, is the probability of landslide occurrence;

[0093] Through the above content, the probability of landslide occurrence can be predicted efficiently and accurately. Combining a variety of real-time monitoring data (soil moisture, precipitation, displacement), it can comprehensively reflect the various potential factors of landslide occurrence, enhance the accuracy and reliability of the prediction, and optimize the model parameters by maximizing the log-likelihood function. It can adaptively adjust the prediction strategy under different geological conditions, thereby improving its applicability in complex environments.

[0094] Identification of landslide affected areas includes:

[0095] Landslide probability threshold setting: The landslide probability obtained by calculation , based on the preset risk threshold Determine the landslide area. , then the area is judged as a landslide risk area;

[0096] Calculation of geological risk index: The comprehensive data is integrated with geological structure information, and the slope factor is considered to calculate the geological risk index through a weighted average algorithm. , expressed as:

[0097] ;

[0098] in, is the slope, For geological structure information (such as rock and soil types, etc.), , , are the corresponding weight coefficients respectively;

[0099] Delineation of landslide affected areas: Based on the probability of landslide occurrence and geological risk index , determine the landslide disaster impact area through weighted calculation , expressed as:

[0100] ;

[0101] in, For the The probability of landslide occurrence at a point, For the The geological risk index of the point, is the total number of data points in the landslide monitoring area;

[0102] Determination and dynamic adjustment of regional scope: Based on the calculated impact area, the boundaries of the affected area are dynamically adjusted, and the regional division is updated according to the changes in real-time landslide-related data to generate real-time landslide impact area information;

[0103] Risk Threshold The settings include:

[0104] 1. Analyze historical data and event patterns: By collecting data on landslide events in the past few years, analyze the relationship between them and monitoring data (such as precipitation, displacement, etc.) and the probability of landslide occurrence, and calculate the probability distribution of landslides under different risk conditions;

[0105] 2. Set preliminary risk threshold: Based on historical landslide data, geology, and meteorology, preliminarily set the risk threshold for the probability of landslide occurrence , assign different thresholds to different risk areas, and the risk threshold for high-risk areas The risk threshold for medium-risk areas is 0.7. 0.5, the risk threshold for low-risk areas is 0.3;

[0106] 3. Dynamically adjust the risk threshold: Based on real-time monitoring data and changes, the risk threshold is adjusted by weighted average method, expressed as:

[0107] ;

[0108] in, is the dynamically adjusted risk threshold, is the initial risk threshold, is the weight coefficient of the monitoring point, It is The probability of landslide occurrence at each monitoring point is is the number of monitoring points, and is the adjustment factor;

[0109] Through the above content, based on real-time monitoring data and probability prediction results of landslides, the impact range of landslide disasters can be intelligently identified and dynamically updated, thereby providing more accurate disaster response. By combining geological structure and real-time data, the boundaries of the affected areas can be adjusted in time under complex terrain and changing environmental conditions, so that the system can respond to possible changes in the landslide process in real time, optimize post-disaster response measures and resource scheduling, improve the accuracy of early warning and the efficiency of response, thereby minimizing the losses caused by landslide disasters and ensuring the safety of residents.

[0110] Regional scope determination and dynamic adjustment include:

[0111] Defining the preliminary scope of the landslide affected area: Based on the probability of landslide occurrence and geological risk index , preliminarily determine the scope of the landslide affected area ;

[0112] Dynamically adjust the regional boundaries: According to the changes in real-time landslide-related data (precipitation, soil moisture, displacement) in the landslide monitoring area, the boundaries of the affected area are dynamically adjusted, expressed as:

[0113] ;

[0114] in, It is the amount of change in the affected area, indicating the area that needs to be redefined after the current area is affected by the new data. is the weight coefficient, and are the real-time changes in landslide probability and geological risk index, is the number of monitoring points in the landslide monitoring area;

[0115] Calculate the impact area boundary adjustment: Based on the calculated impact area change, update the area boundary, expressed as:

[0116] ;

[0117] in, is the original boundary, is the adjusted boundary;

[0118] Real-time regional division: Based on the updated regional boundaries, the entire landslide monitoring area is divided in real time, expressed as:

[0119] ;

[0120] in, To finally determine the landslide affected area, the adjusted boundary Integrate to obtain;

[0121] Through the above content, the demarcation of landslide disaster affected areas can be updated in real time based on real-time collected data and prediction results, combined with dynamically changing landslide probability and geological risk index. The dynamic adjustment of regional boundaries can respond quickly before, during and after landslide disasters, and provide more accurate early warning information and post-disaster response plans. This adjustment strategy based on real-time data effectively avoids the lag of traditional methods and improves the real-time and accuracy of the early warning system.

[0122] Risk assessment and prioritization includes:

[0123] Risk level classification: Based on the classification results of landslide-affected areas, the probability of landslide occurrence is used and geological risk index , the risk score is calculated by a weighted algorithm , expressed as:

[0124] ;

[0125] in, It is The risk score of the region, It is The probability of landslides in a region, It is The geological risk index of the region, are the weight coefficients of the corresponding factors;

[0126] Risk level classification: Based on the calculated risk score , the landslide-affected areas are divided into several risk levels, including low risk, medium risk and high risk. When When When , the landslide-affected area is at low risk;

[0127] Prioritization: After the risk level classification is completed, the landslide-affected areas are prioritized according to their risk levels, with high-risk areas given priority to ensure that emergency resources are allocated to the areas most in need;

[0128] Through the above content, an accurate classification of landslide disaster risks in different regions is provided. By quantifying the probability of landslides and geological conditions, the deviation of subjective judgment is avoided. Prioritizing each region based on risk level helps to optimize the allocation of emergency resources, prioritize limited resources in high-risk areas, ensure rapid response, and reduce potential losses from landslide disasters.

[0129] Dynamic response adjustments include:

[0130] Real-time assessment and update: Real-time monitoring of post-disaster developments, regular updates of risk levels and priorities for each landslide-affected area;

[0131] Dynamically adjust response strategies: Adjust post-disaster response strategies based on updated risk levels and priority rankings, including:

[0132] Resource scheduling optimization: According to the latest risk level of each region, the emergency resource allocation plan is adjusted in real time to give priority to ensuring the support of materials, personnel and equipment in high-risk areas;

[0133] Adjustment of rescue teams: Dynamically arrange the deployment of rescue teams based on the priority of each area, so that high-risk areas receive support as soon as possible;

[0134] Transportation and communication support: timely adjust the opening of transportation channels and repair of communication facilities in high-risk areas with poor transportation or communication interruption;

[0135] Through the above content, it is possible to ensure the efficient configuration and deployment of emergency resources and rescue teams, maximize the efficiency and effectiveness of rescue, and through the continuous updating of the risk level and priority of the landslide-affected area, it is possible to identify the high-risk areas that need assistance most in real time, give priority to supporting materials, personnel and equipment, avoid waste of resources and reduce response delays. In addition, timely adjustments to transportation and communication support can ensure that rescue operations can proceed smoothly, and the operation of key links can be quickly restored even in the event of traffic obstruction or communication interruption. It can effectively cope with the complex changes in disasters, improve the accuracy and flexibility of rescue response, thereby significantly improving post-disaster rescue efficiency and reducing disaster losses.

[0136] Warning information generation includes:

[0137] Generate landslide disaster impact area warning information: According to the landslide impact area identification results, determine the scope of the disaster impact area;

[0138] Generate risk level and response measures information: Based on the results of risk assessment and priority sorting, generate corresponding disaster risk levels and response measures for each area;

[0139] Post-disaster response plan integration and early warning: Based on the results of dynamic response adjustments, emergency response measures are integrated and final early warning information is generated, including disaster expansion prediction, resource dispatch, and personnel support plan;

[0140] Through the above content, accurate identification and risk assessment of landslide disaster-affected areas can be carried out to ensure timely and accurate determination of the disaster impact scope and risk level, and tailor-made response measures for each area. By integrating the dynamic response adjustment results, not only can the disaster expansion be predicted, but also resource scheduling and personnel support plans can be optimized, thereby improving post-disaster response efficiency. Comprehensive early warning information can be generated in real time to ensure that relevant personnel and residents can obtain accurate disaster warnings and emergency guidance at the first time, thereby effectively reducing the losses caused by disasters and improving the flexibility and accuracy of emergency responses.

[0141] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0142] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The landslide geological disaster monitoring and early warning system based on multi-means integration is characterized by: It includes data acquisition module, data fusion module, landslide prediction module, landslide disaster intelligent zoning and response module and early warning signaling module, among which; The data acquisition module collects landslide-related data in real time, including soil moisture, precipitation, and displacement; The data fusion module fuses the landslide-related data from different sources; The landslide prediction module predicts the probability of landslide occurrence based on the fused landslide related data; The landslide disaster intelligent zoning and response module intelligently identifies the affected area of ​​the landslide disaster based on the predicted results of the probability of landslide occurrence, combined with the real-time monitored landslide-related data and geological structure, and dynamically adjusts the post-disaster response measures to generate early warning information, including: Identification of landslide-affected areas: Based on the probability prediction results of landslide occurrence, combined with real-time collected landslide-related data and geological structure information, the area affected by landslide disasters is determined; Risk assessment and priority sorting: Based on the results of the division of the area affected by landslide hazards, the landslide hazard risks in different areas are divided into risk levels, and the priorities of each area are sorted according to the risk level; Dynamic response adjustment: Dynamically adjust post-disaster response measures based on the results of risk assessment and priority sorting to optimize the allocation of post-disaster response resources; Warning information generation: Generate warning information based on the results of landslide impact area identification, risk assessment and priority sorting, and dynamic response adjustment; The warning signaling module automatically sends out a warning signal through a wireless communication device or an alarm device based on the generated warning information, and notifies relevant personnel and residents in a timely manner; The landslide prediction module comprises: Data input: The integrated data As input features ; Prediction model establishment: The prediction model is established through the logistic regression algorithm. When training the prediction model, the log-likelihood function is used for optimization to obtain the optimal model parameters; Landslide probability prediction: The trained prediction model is used to predict the probability of landslide based on the integrated data. ; The identification of landslide affected areas includes: Landslide probability threshold setting: The landslide probability obtained by calculation , based on the preset risk threshold Determine the landslide area. , then the area is judged as a landslide risk area; Calculation of geological risk index: The comprehensive data is integrated with geological structure information, and the slope factor is considered to calculate the geological risk index through a weighted average algorithm. ; Delineation of landslide affected areas: Based on the probability of landslide occurrence and geological risk index , determine the landslide disaster impact area through weighted calculation ; Determination and dynamic adjustment of regional scope: Based on the calculated impact area, the boundaries of the affected area are dynamically adjusted, and the regional division is updated according to the changes in real-time landslide-related data to generate real-time landslide impact area information; The area range determination and dynamic adjustment include: Defining the preliminary scope of the landslide affected area: Based on the probability of landslide occurrence and geological risk index , preliminarily determine the scope of the landslide affected area ; Dynamically adjust the regional boundaries: dynamically adjust the boundaries of the affected area according to the changes in real-time landslide-related data in the landslide monitoring area; Calculate the impact area boundary adjustment: based on the calculated impact area change, update the area boundary; Real-time regional division: Based on the updated regional boundaries, the entire landslide monitoring area is divided in real time.

2. The landslide geological disaster monitoring and early warning system based on multi-means fusion according to claim 1 is characterized in that: The data acquisition module comprises: Soil moisture collection: Soil moisture sensors are used to measure the moisture changes in the soil in the landslide area in real time and monitor the fluctuations in soil moisture content; Precipitation monitoring: Real-time monitoring of precipitation data in the landslide monitoring area through precipitation sensors; Displacement detection: The displacement of the landslide monitoring area is detected in real time through displacement sensors.

3. The landslide geological disaster monitoring and early warning system based on multi-means fusion according to claim 1 is characterized in that: The data fusion module comprises: Data standardization: standardize the landslide-related data from different sensors and convert the data in different units into a unified standard measurement; Weighted average calculation: The weighted average method is used to fuse the standardized landslide-related data to form comprehensive data. .

4. The landslide geological disaster monitoring and early warning system based on multi-means fusion according to claim 1 is characterized in that: The risk assessment and prioritization includes: Risk level classification: Based on the classification results of landslide-affected areas, the probability of landslide occurrence is used and geological risk index , the risk score is calculated by a weighted algorithm ; Risk level classification: Based on the calculated risk score , the landslide-affected areas are divided into several risk levels, including low risk, medium risk and high risk. When When When , the landslide-affected area is at low risk; Prioritization: After completing the risk classification, the landslide-affected areas are prioritized according to their risk levels, with high-risk areas being given priority.

5. The landslide geological disaster monitoring and early warning system based on multi-means fusion according to claim 4 is characterized in that: The dynamic response adjustment includes: Real-time assessment and update: Real-time monitoring of post-disaster developments, regular updates of risk levels and priorities for each landslide-affected area; Dynamically adjust response strategies: Adjust post-disaster response strategies based on updated risk levels and priority rankings, including: Resource scheduling optimization: According to the latest risk level of each region, the emergency resource allocation plan is adjusted in real time to give priority to ensuring the support of materials, personnel and equipment in high-risk areas; Adjustment of rescue teams: Dynamically arrange the deployment of rescue teams based on the priority of each area, so that high-risk areas receive support as soon as possible; Transportation and communication support: For high-risk areas with poor transportation or communication interruptions, timely adjustments will be made to the development of transportation channels and the repair of communication facilities.

6. The landslide geological disaster monitoring and early warning system based on multi-means fusion according to claim 5 is characterized in that: The generation of the early warning information includes: Generate landslide disaster impact area warning information: According to the landslide impact area identification results, determine the scope of the disaster impact area; Generate risk level and response measures information: Based on the results of risk assessment and priority sorting, generate corresponding disaster risk levels and response measures for each area; Post-disaster response plan integration and early warning notification: Based on the results of dynamic response adjustments, emergency response measures are integrated and final early warning information is generated, including disaster expansion prediction, resource scheduling, and personnel support plans.

Images