Landslide geological disaster early warning pushing method and system

Abstract

The invention discloses a landslide geological disaster early warning pushing method and system, and relates to the technical field of emergency response, and the method comprises the steps: introducing a time dimension to generate an early warning pushing coefficient Awarning based on a landslide influence range Aimpact and a comprehensive risk score Rreg, and carrying out the dynamic adjustment through analyzing the change of a risk along with the time, thereby achieving the early warning pushing of a landslide geological disaster. And comparing with a preset first push threshold value F1 and a preset second push threshold value F2, and timely transmitting the risk condition of the landslide influence area. When the early warning pushing coefficient Awarning exceeds a first pushing threshold value F1, an emergency early warning mechanism is triggered immediately, first landslide information is pushed, and related personnel are informed to take necessary safety measures; and when the early warning push coefficient Awarning is between the first push threshold F1 and the second push threshold F2, second landslide information is pushed, residents are reminded to make precaution preparations, and the dynamic evaluation mechanism ensures that the early warning information can quickly and accurately reflect risk changes.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency response, and in particular to a method and system for pushing early warning of landslide geological disasters. Background Art

[0002] The landslide geological disaster early warning push method belongs to the field of natural disaster management and emergency response. With the acceleration of urbanization, construction activities in mountainous and slope areas are becoming more and more frequent, and these areas are more susceptible to geological disasters such as landslides. In this field, monitoring and early warning technologies for landslides are becoming more and more important, especially for specific landslide risk areas, and effective real-time monitoring and early warning systems are needed to protect the safety of residents.

[0003] Most of the current landslide monitoring and early warning systems rely on traditional ground monitoring methods and regular manual inspections, lacking real-time and automation. This method not only has a long response time, but also lacks sensitivity to environmental changes and cannot capture the key factors that cause landslides in a timely manner. In addition, traditional systems are difficult to achieve dynamic risk assessment in large areas, resulting in monitoring blind spots in potential risk areas, thereby increasing losses and injuries when disasters occur; due to the limitations of existing monitoring systems, early warnings of landslide disasters are often delayed, resulting in many areas lacking effective response measures when crises occur. After a disaster occurs, residents lack timely information and are often caught off guard in a crisis, resulting in property losses and personal injuries. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a landslide geological disaster early warning push method and system, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented by the following technical scheme: comprising the following steps:

[0006] S1. By setting up several detection points in the landslide area and installing an integrated sensor group in each detection point, the mountain data is collected in real time and sent to the central processing system through the wireless gateway for pre-processing to obtain the landslide impact data set;

[0007] S2, constructing the landslide impact area algorithm formula, extracting the mountain data and inputting it into the landslide impact area algorithm formula, calculating and outputting the landslide impact range Aimpact, and predicting the landslide impact area;

[0008] S3. Based on the predicted landslide-affected areas, further analyze the risk scores of different landslide-affected areas, construct a risk scoring algorithm formula, extract the landslide impact data set and input it into the risk scoring algorithm formula, calculate and output the comprehensive risk score Rreg of different landslide-affected areas;

[0009] S4. Based on the acquired landslide impact range Aimpact and the comprehensive risk score Rreg, the time dimension is introduced to generate the warning push coefficient Awarning, and the first push threshold F1 and the second push threshold F2 are preset to perform preliminary comparative evaluation with the acquired warning push coefficient Awarning to analyze the risk situation of the landslide impact area;

[0010] S5. Introduce the feedback mechanism again, build a feedback optimization formula, input feedback information and sensor error correction, input it into the feedback optimization formula, calculate and output the risk assessment adjustment coefficient △Rupdate, adjust the update frequency and scale of the risk scoring algorithm formula, and then execute S4 after adjustment to conduct a secondary assessment and analysis of the risk situation of the landslide affected area, and automatically generate the current landslide affected area number. Each landslide affected area number corresponds to the corresponding risk level and push strategy.

[0011] Preferably, said S1 includes S11, S12 and S13;

[0012] S1. By setting up several detection points in the landslide area and installing an integrated sensor group in each detection point, the mountain data is collected in real time. The integrated sensor group includes a rain gauge, a surface displacement sensor, a groundwater level sensor, a soil moisture sensor, a viscometer, a strain sensor and an anemometer;

[0013] The mountain data include rainfall Prai, surface displacement Ddis, groundwater level Ggro, soil moisture change rate Wsoi, soil viscosity Vvis, geological structure stress Sste and landslide area wind speed Vwin;

[0014] S12. Set up a LoRa wireless gateway to connect the integrated sensor group to the central processing system through a network, and then transmit the collected mountain data to the central processing system through a standard communication protocol.

[0015] Preferably, S13, receiving mountain data in real time in a central processing system, and preprocessing the mountain data to obtain a landslide impact data set, wherein the landslide impact data set includes a landslide occurrence probability Plan and a geological stress change ΔSstr;

[0016] The specific processing methods are as follows;

[0017] The landslide occurrence probability Plan is obtained by calculating and processing the rainfall Prai, surface displacement Ddis and groundwater level Ggro in the mountain data. The specific calculation formula is: Plan = f (Prai, Ddis, Ggro, Hhis), where f represents the relationship function, and Hhis represents the historical landslide probability, that is, the historical probability and pattern of landslide occurrence under similar rainfall Prai, surface displacement Ddis and groundwater level Ggro;

[0018] The geological stress change ΔSstr is obtained by calculating and processing the geological structure stress Sste in the mountain data. The specific calculation formula is: Where Sini represents the stress value of the mountain under normal conditions, which is set by the initial setting, and △t represents the time change.

[0019] Preferably, said S2 includes S21;

[0020] S21, constructing a landslide impact area algorithm formula, extracting mountain data from the central processing system and inputting it into the landslide impact area algorithm formula, calculating and outputting the landslide impact range Aimpact, and predicting the impact range of the landslide;

[0021] The landslide impact range Aimpact is calculated and outputted by the following landslide impact area algorithm formula;

[0022]

[0023] Wherein, Stratin represents the topographic constant, which is obtained through the digital elevation model DEM and represents the three-dimensional topographic characteristics of the surface. Jd represents the slope angle, which is initially set by the user. α represents the global adjustment coefficient, which is used to adjust the overall scale of the formula to ensure that the model output is within a reasonable range. β1 and β2 represent the preset weight values ​​of the surface displacement Ddis and the groundwater level Ggro, respectively. γ1 and γ2 represent the preset weight values ​​of the geological structure stress Sste and the wind speed Vwin in the landslide area, respectively. δ represents a constant, which is used to avoid the denominator being zero. The specific values ​​of β1, β2, γ1 and γ2 are set by the user. It indicates the influence of topography and slope angle, and emphasizes the direct effect of topography and slope. Steep slope will amplify the impact range of landslide. At the same time, the increase of rainfall Prai, surface displacement Ddis and groundwater level Ggro will reduce the stability of the mountain and further promote the occurrence of landslide. It represents the changes in soil physical properties and stress, mainly involving the relationship between soil physical properties and internal stress. The moisture content and viscosity of the soil directly affect the possibility of landslides. The rapid change of stress indicates the instability inside the mountain. The impact of wind speed on the surface soil is expressed in the form of a denominator, that is, the greater the wind speed, the more unstable the surface.

[0024] Preferably, said S3 includes S31;

[0025] S31. Based on the predicted landslide impact range, a risk scoring algorithm formula is constructed, the landslide impact data set is extracted, and the data is input into the risk scoring algorithm formula to calculate and output the comprehensive risk score Rreg of different landslide image areas, and analyze the risk situation of the current area;

[0026] The comprehensive risk score Rreg is calculated by the following risk score algorithm formula;

[0027] Rreg i =a1·Plan+a2·(Ppop+Pbui+Szyx)+a3·△Sstr;

[0028] In the formula, Rreg i It represents the comprehensive analysis score of the area affected by the i-th landslide, (Ppop+Pbui+Szyx) represents the impact degree of the landslide, Ppop represents the population density in the landslide area, Pbui represents the building density, Szyx represents the important infrastructure index, and its specific value is set by the user according to the actual situation of the area, a1, a2 and a3 represent the preset weight values ​​of the landslide probability Plan, the impact degree of the landslide and the geological stress change △Sstr, respectively, and a1+a2+a3=1, and its specific value is set by the user.

[0029] Preferably, said S4 includes S41 and S42;

[0030] S41, based on the current landslide impact range Aimpact and the comprehensive risk score Rreg, the information of the warning push introduced in the time dimension will be dynamically adjusted according to the change of risk over time, and the warning push coefficient Awarning will be calculated and generated;

[0031] The warning push coefficient Awarning is calculated by the following algorithm formula:

[0032]

[0033] In the formula, λ represents the adjustment factor of the warning push range. As the risk level is adjusted, Tresponse represents the response time. The higher the risk, the shorter the response time.

[0034] Preferably, S42, the staff initially presets the first push threshold F1 and the second push threshold F2, and then compares and evaluates the obtained warning push coefficient Awarning to analyze the risk situation of the landslide affected area. The specific evaluation results are as follows;

[0035] When the warning push coefficient Awarning> the first push threshold F1, it means that there is an abnormality in the current landslide affected area, and the first landslide information is pushed at this time;

[0036] When the second push threshold F2 ≤ the warning push coefficient Awarning ≤ the first push threshold F1, it indicates that there is an abnormality in the current landslide affected area, and the second landslide information is pushed;

[0037] When the warning push coefficient Awarning < the second push threshold F2, it means that the current landslide affected area is in a normal state, and the third landslide information is pushed;

[0038] And the first push threshold F1>the second push threshold F2.

[0039] Preferably, the S5 includes S51, S52 and S53;

[0040] S51, using a mobile device to provide real-time feedback of on-site information of the landslide-affected area, including but not limited to surface cracks, mountain movement, and tilted objects, and then binding the feedback information with geographic location data and uploading it to a central processing system through an application structure API, where the feedback information is summarized and calculated and output as a weight Ffeedback;

[0041] Then, by comparing the mountain data of historical landslide events collected by the integrated sensor group, the sensor error correction amount Eerror is obtained by performing difference calculation based on the mountain data of historical landslide events and the currently collected mountain data.

[0042] Preferably, S52, based on the acquired feedback information weight Ffeedback and the sensor error correction amount Eerror, calculate and output the risk assessment adjustment coefficient △Rupdate, and iteratively adjust S1 to S4;

[0043] The risk assessment adjustment coefficient △Rupdate is calculated and obtained by the following algorithm formula;

[0044]

[0045] In the formula, β represents the learning rate adjustment parameter, and Nitera represents the number of iterations;

[0046] S53, after iterative adjustment, re-execute S4 to perform secondary evaluation and comparative evaluation, obtain corresponding landslide information, and execute regional number generation and push strategy for different landslide information, the specific contents are as follows;

[0047] When the first landslide information is received, a LIZI-1 number is automatically generated, indicating that the area identified by the LIZI-1 number is assessed as a first-level dangerous area, and an emergency evacuation notice is immediately issued through a mobile communication device;

[0048] When the second landslide information is received, a LIZI-2 number is automatically generated, indicating that the area marked by the LIZI-2 number is assessed as a secondary danger area. At this time, a preventive warning notice is immediately issued through mobile communication equipment, and residents need to prepare to evacuate, but do not need to take immediate action;

[0049] When the third landslide information is received, the LIZI-3 number is automatically generated, indicating that the area marked by the LIZI-3 number is assessed as a level 3 danger area. At this time, there is no need to send an early warning message, there is no risk of landslide, and monitoring will continue.

[0050] A landslide geological disaster early warning and push system, including a mountain data acquisition module, a landslide impact area analysis module, a landslide risk analysis module, an early warning push module and a feedback optimization analysis module;

[0051] The mountain data acquisition module sets a number of detection points in the landslide area and installs an integrated sensor group in each detection point to collect mountain data in real time, and sends the data to the central processing system through a wireless gateway for preprocessing to obtain a landslide impact data set;

[0052] The landslide impact area analysis module constructs a landslide impact area algorithm formula, extracts mountain data and inputs it into the landslide impact area algorithm formula, calculates and outputs the landslide impact range Aimpact, and predicts the area affected by the landslide;

[0053] The landslide risk analysis module further analyzes the risk scores of different landslide-affected areas based on the predicted landslide-affected areas, constructs a risk scoring algorithm formula, extracts the landslide impact data set and inputs it into the risk scoring algorithm formula, calculates and outputs the comprehensive risk scores Rreg of different landslide-affected areas;

[0054] The warning push module introduces the time dimension based on the acquired landslide impact range Aimpact and the comprehensive risk score Rreg, generates a warning push coefficient Awarning, and presets a first push threshold F1 and a second push threshold F2 to perform a preliminary comparative evaluation with the acquired warning push coefficient Awarning, and analyzes the risk situation of the landslide impact area;

[0055] The feedback optimization analysis module constructs a feedback optimization formula, inputs feedback information and sensor error correction, inputs the feedback optimization formula, calculates and outputs the risk assessment adjustment coefficient △Rupdate, adjusts the update frequency and scale of the risk scoring algorithm formula, and then executes S4 after adjustment to perform a secondary assessment and analysis of the risk situation of the landslide affected area, and automatically generates the current landslide affected area number, each landslide affected area number corresponds to a corresponding risk level and push strategy.

[0056] The present invention provides a landslide geological disaster early warning push method and system. It has the following beneficial effects:

[0057] (1) This method can collect key mountain data in real time by setting up several detection points in high-risk areas of landslides and installing integrated sensor groups in each detection point, including rain gauges, surface displacement sensors and groundwater level sensors. These data, such as rainfall Prai, surface displacement Ddis and groundwater level Ggro, constitute the basic information of landslide occurrence. The data is transmitted to the central processing system through the LoRa wireless gateway for preprocessing to form a landslide impact data set, including the geological stress change △Sstr of the landslide occurrence plan. This real-time monitoring mechanism improves the ability to identify landslide risks at an early stage, provides comprehensive and accurate data support for subsequent risk assessment, makes the analysis of landslide-affected areas more scientific and effective, and effectively reduces the potential risk of casualties and property losses.

[0058] (2) This method introduces the time dimension to generate the warning push coefficient Awarning based on the landslide impact range Aimpact and the comprehensive risk score Rreg. This coefficient is dynamically adjusted by analyzing the changes in risk over time, and compared with the preset first push threshold F1 and second push threshold F2 to ensure that the risk situation of the landslide impact area is communicated in a timely manner. When the warning push coefficient Awarning exceeds the first push threshold F1, the emergency warning mechanism is immediately triggered, the first landslide information is pushed, and the relevant personnel are informed to take necessary safety measures; when Awarning is between the first push threshold F1 and the second push threshold F2, the second landslide information is pushed to remind residents to make precautionary preparations. This dynamic evaluation mechanism not only ensures that the warning information can quickly and accurately reflect the risk changes, but also provides the necessary basis for decision makers to respond quickly to potential landslide threats and effectively reduce casualties and property losses.

[0059] (3) This method introduces a feedback mechanism and uses mobile devices to provide real-time feedback of on-site information in the landslide-affected area, such as surface cracks and mountain movement. The feedback information is bound to the geographic location data and uploaded to the central processing system through the application. Based on this feedback information, the system can calculate the feedback information weight Ffeedback and compare it with historical data to obtain the sensor error correction value Eerror. This process not only improves the accuracy of the data, but also makes the calculation of the risk assessment adjustment coefficient △Rupdate more scientific. Through iterative adjustment, the system can update the risk scoring algorithm in a timely manner to ensure that the early warning strategy can adapt to the ever-changing landslide risk. This feedback mechanism effectively improves the accuracy and response efficiency of the early warning system, can cope with the complexity of different landslide events in actual disaster management, and provide a reliable basis for relevant departments to ensure public safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of a method for pushing early warning of landslide geological disasters according to the present invention;

[0061] Figure 2 The present invention is a schematic diagram of the steps of a landslide geological disaster early warning and push system. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Example 1

[0064] See also Figure 1 The present invention provides a landslide geological disaster early warning push method. To achieve the above purpose, the present invention is implemented through the following technical scheme: comprising the following steps:

[0065] S1. By setting up several detection points in the landslide area and installing an integrated sensor group in each detection point, the mountain data is collected in real time and sent to the central processing system through the wireless gateway for pre-processing to obtain the landslide impact data set;

[0066] S2, constructing the landslide impact area algorithm formula, extracting the mountain data and inputting it into the landslide impact area algorithm formula, calculating and outputting the landslide impact range Aimpact, and predicting the landslide impact area;

[0067] S3. Based on the predicted landslide-affected areas, further analyze the risk scores of different landslide-affected areas, construct a risk scoring algorithm formula, extract the landslide impact data set and input it into the risk scoring algorithm formula, calculate and output the comprehensive risk score Rreg of different landslide-affected areas;

[0068] S4. Based on the acquired landslide impact range Aimpact and the comprehensive risk score Rreg, the time dimension is introduced to generate the warning push coefficient Awarning, and the first push threshold F1 and the second push threshold F2 are preset to perform preliminary comparative evaluation with the acquired warning push coefficient Awarning to analyze the risk situation of the landslide impact area;

[0069] S5. Introduce the feedback mechanism again, build a feedback optimization formula, input feedback information and sensor error correction, input it into the feedback optimization formula, calculate and output the risk assessment adjustment coefficient △Rupdate, adjust the update frequency and scale of the risk scoring algorithm formula, and then execute S4 after adjustment to conduct a secondary assessment and analysis of the risk situation of the landslide affected area, and automatically generate the current landslide affected area number. Each landslide affected area number corresponds to the corresponding risk level and push strategy.

[0070] In this embodiment, the method realizes the real-time collection of mountain data by setting multiple detection points and installing an integrated sensor group in the landslide area, and sends the data to the central processing system for preprocessing through a wireless gateway. This process ensures the rapid formation of the landslide impact data set and improves the response speed to potential landslide risks. Then, the constructed landslide impact area algorithm formula converts the mountain data into the landslide impact range Aimpact, making the prediction more accurate. Based on this impact range, the risk scores of different areas are further analyzed, and the comprehensive risk score Rreg is output through the risk scoring algorithm formula, so as to comprehensively evaluate the risk level of the landslide impact area. By introducing the time dimension, the generated warning push coefficient Awarning is combined with the preset push threshold to realize the real-time evaluation of the dynamic changes of landslide risks, ensuring the flexibility and timeliness of the warning mechanism. At the same time, the introduction of the feedback mechanism allows the system to be optimized according to real-time feedback and sensor correction, so that the risk assessment adjustment coefficient △Rupdate can reflect the latest geological changes in a timely manner, further improving the accuracy of risk assessment. Compared with traditional landslide monitoring technology, the advantage of this method is that it integrates a comprehensive process of real-time data collection, dynamic evaluation and feedback optimization, significantly improving the accuracy and timeliness of landslide monitoring and reducing the risk of loss of life and property. Through this innovative method, not only the ability to predict landslide disasters is enhanced, but also strong support is provided for relevant disaster prevention decisions, promoting the intelligent development of geological disaster prevention technology.

[0071] Example 2

[0072] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S1 includes S11, S12 and S13;

[0073] S1. By setting up several detection points in the landslide area and installing an integrated sensor group in each detection point, the mountain data is collected in real time. The integrated sensor group includes a rain gauge, a surface displacement sensor, a groundwater level sensor, a soil moisture sensor, a viscometer, a strain sensor and an anemometer;

[0074] Mountain data include rainfall Prai, surface displacement Ddis, groundwater level Ggro, soil moisture change rate Wsoi, soil viscosity Vvis, geological structure stress Sste and landslide area wind speed Vwin;

[0075] S12. Set up a LoRa wireless gateway to connect the integrated sensor group to the central processing system through a network, and then transmit the collected mountain data to the central processing system through a standard communication protocol.

[0076] S13, receiving mountain data in real time in the central processing system, and pre-processing the mountain data to obtain a landslide impact data set, where the landslide impact data set includes a landslide occurrence probability Plan and a geological stress change △Sstr;

[0077] The specific processing methods are as follows;

[0078] The probability of landslide occurrence Plan is obtained by calculating and processing the rainfall Prai, surface displacement Ddis and groundwater level Ggro in the mountain data. The specific calculation formula is: Plan = f (Prai, Ddis, Ggro, Hhis), where f represents the relationship function, and Hhis represents the historical landslide probability, that is, the historical probability and pattern of landslide occurrence under similar rainfall Prai, surface displacement Ddis and groundwater level Ggro;

[0079] The geological stress change △Sstr is obtained by calculating and processing the geological structure stress Sste in the mountain data. The specific calculation formula is: Where Sini represents the stress value of the mountain under normal conditions, which is set by the initial setting, and △t represents the time change.

[0080] In this embodiment, by setting up multiple detection points and installing an integrated sensor group, the method realizes comprehensive real-time monitoring of mountain data, including key parameters such as rainfall, surface displacement and groundwater level. The intelligence and automation of this data collection process improves the accuracy and real-time nature of the data. The use of LoRa wireless gateway ensures the rapid transmission of data to the central processing system, significantly improving the efficiency of information flow.

[0081] In the central processing system, mountain data is received and preprocessed in real time to generate a landslide impact data set, including the landslide probability Plan and geological stress change △Sstr. The integration and analysis of these data provide a more reliable basis for landslide risk assessment, enabling the system to dynamically adjust the early warning mechanism under changing environmental conditions. This step significantly enhances the accuracy and timeliness of landslide prediction by integrating multiple sensors, wireless communications, and real-time data processing. This comprehensive monitoring and early warning mechanism not only improves the efficiency of landslide disaster response, but also provides strong data support for decision makers, effectively reducing potential risks, thereby achieving a dual improvement in personal safety and property protection.

[0082] Example 3

[0083] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: S2 includes S21;

[0084] S21, constructing a landslide impact area algorithm formula, extracting mountain data from the central processing system and inputting it into the landslide impact area algorithm formula, calculating and outputting the landslide impact range Aimpact, and predicting the impact range of the landslide;

[0085] The landslide impact area Aimpact is calculated and output by the following landslide impact area algorithm formula;

[0086]

[0087] Wherein, Stratin represents the topographic constant, which is obtained through the digital elevation model DEM and represents the three-dimensional topographic characteristics of the surface. Jd represents the slope angle, which is initially set by the user. α represents the global adjustment coefficient, which is used to adjust the overall scale of the formula to ensure that the model output is within a reasonable range. β1 and β2 represent the preset weight values ​​of the surface displacement Ddis and the groundwater level Ggro, respectively. γ1 and γ2 represent the preset weight values ​​of the geological structure stress Sste and the wind speed Vwin in the landslide area, respectively. δ represents a constant, which is used to avoid the denominator being zero. The specific values ​​of β1, β2, γ1 and γ2 are set by the user. It indicates the influence of topography and slope angle, and emphasizes the direct effect of topography and slope. Steep slope will amplify the impact range of landslide. At the same time, the increase of rainfall Prai, surface displacement Ddis and groundwater level Ggro will reduce the stability of the mountain and further promote the occurrence of landslide. It represents the changes in soil physical properties and stress, mainly involving the relationship between soil physical properties and internal stress. The moisture content and viscosity of the soil directly affect the possibility of landslides. The rapid change of stress indicates the instability inside the mountain. The impact of wind speed on the surface soil is expressed in the form of a denominator, that is, the greater the wind speed, the more unstable the surface.

[0088] In this embodiment, the method constructs an algorithm formula for the landslide impact area, which effectively integrates the mountain data in the central processing system, calculates and predicts the landslide impact range Aimpact. This process not only takes into account the topographic features, slope angles and various environmental parameters, but also dynamically adjusts the model by setting preset weight values ​​to ensure the rationality and accuracy of the output. Compared with traditional landslide prediction methods, this algorithm can more comprehensively analyze the potential factors of landslide occurrence, such as surface displacement, groundwater level changes and wind speed, and enhances the insight into landslide risks. By accurately calculating the landslide impact range, the method provides a scientific basis for risk assessment, enabling the early warning mechanism to respond to potential landslide threats in a timely manner. This innovation not only improves the accuracy of landslide prediction and enhances emergency response capabilities, but also provides effective tools for environmental monitoring and disaster management, significantly improving the scientificity and effectiveness of disaster prevention and control, thereby better protecting people's lives and property.

[0089] Example 4

[0090] This embodiment is explained in Example 3, please refer to Figure 1 , specifically: S3 includes S31;

[0091] S31. Based on the predicted landslide impact range, a risk scoring algorithm formula is constructed, the landslide impact data set is extracted, and the data is input into the risk scoring algorithm formula to calculate and output the comprehensive risk score Rreg of different landslide image areas, and analyze the risk situation of the current area;

[0092] The comprehensive risk score Rreg is calculated using the following risk score algorithm formula;

[0093] Rreg i =a1·Plan+a2·(Ppop+Pbui+Szyx)+a3·△Sstr;

[0094] In the formula, Rreg i It represents the comprehensive analysis score of the area affected by the i-th landslide, (Ppop+Pbui+Szyx) represents the impact degree of the landslide, Ppop represents the population density in the landslide area, Pbui represents the building density, Szyx represents the important infrastructure index, and its specific value is set by the user according to the actual situation of the area, a1, a2 and a3 represent the preset weight values ​​of the landslide probability Plan, the impact degree of the landslide and the geological stress change △Sstr, respectively, and a1+a2+a3=1, and its specific value is set by the user.

[0095] In this embodiment, the method can systematically evaluate the comprehensive risk score Rreg of different landslide image areas based on the predicted landslide impact range by constructing a risk scoring algorithm formula. This process comprehensively considers the regional population density Ppop, building density Pbui and important infrastructure indicators Szyx, making the risk assessment more comprehensive and accurate. Compared with the traditional single indicator analysis, this method can dynamically adjust the influence of each factor by setting a preset weight value, so as to more realistically reflect the regional risk situation. By calculating the comprehensive risk score, the method provides effective data support for decision makers, helps identify high-risk areas, optimizes resource allocation, and formulates scientific emergency response measures. The innovation of this method is that it not only improves the accuracy of risk assessment, but also enhances the adaptability to complex environmental factors, and can better cope with the diversity of natural disasters. Finally, the method significantly improves the efficiency of landslide disaster management and provides a more powerful guarantee for protecting people's lives and property.

[0096] Example 5

[0097] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S4 includes S41 and S42;

[0098] S41, based on the current landslide impact range Aimpact and the comprehensive risk score Rreg, the information of the warning push introduced in the time dimension will be dynamically adjusted according to the change of risk over time, and the warning push coefficient Awarning will be calculated and generated;

[0099] The warning push coefficient Awarning is calculated by the following algorithm formula;

[0100]

[0101] In the formula, λ represents the adjustment factor of the warning push range. As the risk level is adjusted, Tresponse represents the response time. The higher the risk, the shorter the response time.

[0102] S42, the staff initially presets the first push threshold F1 and the second push threshold F2, and then compares and evaluates them with the obtained warning push coefficient Awarning to analyze the risk situation of the landslide affected area. The specific evaluation results are as follows;

[0103] When the warning push coefficient Awarning> the first push threshold F1, it means that there is an abnormality in the current landslide affected area, and the first landslide information is pushed at this time;

[0104] When the second push threshold F2 ≤ the warning push coefficient Awarning ≤ the first push threshold F1, it indicates that there is an abnormality in the current landslide affected area, and the second landslide information is pushed;

[0105] When the warning push coefficient Awarning < the second push threshold F2, it means that the current landslide affected area is in a normal state, and the third landslide information is pushed;

[0106] And the first push threshold F1>the second push threshold F2.

[0107] In this embodiment, the method is implemented through step S4, which effectively combines the current landslide impact range Aimpact and the comprehensive risk score Rreg, introduces the time dimension, and generates a dynamically adjusted warning push coefficient Awarning. This mechanism ensures the timeliness and pertinence of the warning information, allowing real-time response to risk changes. Compared with the traditional static warning system, the dynamic adjustment capability of this method significantly improves the accuracy and efficiency of the warning. Specifically, the calculation of the warning push coefficient Awarning and its comparison with the preset first push threshold F1 and the second push threshold F2 enable corresponding countermeasures to be taken quickly under different risk levels. This risk level-based response mechanism ensures that emergency information can be conveyed faster in high-risk situations, thereby effectively reducing potential losses. In addition, by setting a multi-level threshold, the flexibility and adaptability of the warning system are enhanced, so that areas with different risk levels can receive corresponding attention and response. Overall, this method significantly improves the response speed and effectiveness of landslide disaster warnings, providing a stronger guarantee for ensuring public safety.

[0108] Example 6

[0109] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S5 includes S51, S52 and S53;

[0110] S51, using a mobile device to provide real-time feedback of on-site information of the landslide-affected area, including but not limited to surface cracks, mountain movement, and tilted objects, and then binding the feedback information with geographic location data and uploading it to a central processing system through an application structure API, where the feedback information is summarized and calculated and output as a weight Ffeedback;

[0111] Then, by comparing the mountain data of historical landslide events collected by the integrated sensor group, the sensor error correction amount Eerror is obtained by performing difference calculation based on the mountain data of historical landslide events and the currently collected mountain data.

[0112] S52, based on the obtained feedback information weight Ffeedback and the sensor error correction amount Eerror, calculate and output the risk assessment adjustment coefficient △Rupdate, and iteratively adjust S1 to S4;

[0113] The risk assessment adjustment coefficient △Rupdate is calculated by the following algorithm formula;

[0114]

[0115] In the formula, β represents the learning rate adjustment parameter, and Nitera represents the number of iterations;

[0116] S53, after iterative adjustment, re-execute S4 to perform secondary evaluation and comparative evaluation, obtain corresponding landslide information, and execute regional number generation and push strategy for different landslide information, the specific contents are as follows;

[0117] When the first landslide information is received, a LIZI-1 number is automatically generated, indicating that the area identified by the LIZI-1 number is assessed as a first-level dangerous area, and an emergency evacuation notice is immediately issued through a mobile communication device;

[0118] When the second landslide information is received, a LIZI-2 number is automatically generated, indicating that the area marked by the LIZI-2 number is assessed as a secondary danger area. At this time, a preventive warning notice is immediately issued through mobile communication equipment, and residents need to prepare to evacuate, but do not need to take immediate action;

[0119] When the third landslide information is received, the LIZI-3 number is automatically generated, indicating that the area marked by the LIZI-3 number is assessed as a level 3 danger area. At this time, there is no need to send an early warning message, there is no risk of landslide, and monitoring will continue.

[0120] In this embodiment, the method is implemented through step S5, and the landslide early warning method significantly enhances the real-time feedback and self-optimization capabilities of the system. The real-time information feedback mechanism of the mobile device enables the field data to be quickly transmitted to the central processing system, thereby improving the monitoring accuracy of the landslide affected area. This feedback not only includes key indicators such as surface cracks and mountain movement, but also combines geographic location data to ensure the accuracy and timeliness of information. Compared with traditional landslide monitoring methods, this method introduces historical data difference calculation to correct sensor errors and improve the reliability of data analysis. The risk assessment adjustment coefficient △Rupdate based on the feedback information weight Ffeedback and the sensor error correction amount Eerror enables the system to dynamically iterate to ensure the real-time and accuracy of risk assessment. Finally, the method realizes the automatic numbering of multi-level risk areas and the corresponding push strategy, so that corresponding early warning responses can be made quickly under different risk levels. In this way, residents in different dangerous areas can receive appropriate early warning information in a timely manner, thereby effectively improving the level of public safety protection. Overall, the method has been significantly improved compared with the prior art in terms of response speed, data accuracy and early warning effectiveness, providing a more scientific and systematic solution for the prevention and response of landslide disasters.

[0121] Example 7

[0122] See also Figure 1 and Figure 2 , a landslide geological disaster early warning and push system, including a mountain data acquisition module, a landslide impact area analysis module, a landslide risk analysis module, an early warning push module and a feedback optimization analysis module;

[0123] The mountain data acquisition module sets up several detection points in the landslide area and installs an integrated sensor group in each detection point to collect mountain data in real time, and sends it to the central processing system through the wireless gateway for pre-processing to obtain the landslide impact data set;

[0124] The landslide impact area analysis module constructs the landslide impact area algorithm formula, extracts the mountain data and inputs it into the landslide impact area algorithm formula, calculates and outputs the landslide impact range Aimpact, and predicts the area affected by the landslide;

[0125] The landslide risk analysis module is based on the predicted landslide-affected areas, and further analyzes the risk scores of different landslide-affected areas. By constructing a risk scoring algorithm formula, the landslide impact data set is extracted and input into the risk scoring algorithm formula, and the comprehensive risk scores Rreg of different landslide-affected areas are calculated and output;

[0126] The warning push module introduces the time dimension based on the acquired landslide impact range Aimpact and the comprehensive risk score Rreg, generates the warning push coefficient Awarning, and presets the first push threshold F1 and the second push threshold F2 to conduct preliminary comparative evaluation with the acquired warning push coefficient Awarning, and analyzes the risk situation of the landslide impact area;

[0127] The feedback optimization analysis module constructs a feedback optimization formula, inputs feedback information and sensor error correction, and calculates and outputs the risk assessment adjustment coefficient △Rupdate. It adjusts the update frequency and scale of the risk scoring algorithm formula, and then executes S4 after adjustment to conduct a secondary assessment and analysis of the risk situation of the landslide-affected area, and automatically generates the current landslide-affected area number. Each landslide-affected area number corresponds to the corresponding risk level and push strategy.

[0128] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A landslide geological disaster early warning push method, characterized in that: The following steps are involved: S1. By setting up several detection points in the landslide area and installing an integrated sensor group in each detection point, the mountain data is collected in real time and sent to the central processing system through the wireless gateway for pre-processing to obtain the landslide impact data set; S2, constructing the landslide impact area algorithm formula, extracting the mountain data and inputting it into the landslide impact area algorithm formula, calculating and outputting the landslide impact range Aimpact, and predicting the landslide impact area; S3. Based on the predicted landslide-affected areas, further analyze the risk scores of different landslide-affected areas, construct a risk scoring algorithm formula, extract the landslide impact data set and input it into the risk scoring algorithm formula, calculate and output the comprehensive risk score Rreg of different landslide-affected areas; S4. Based on the acquired landslide impact range Aimpact and the comprehensive risk score Rreg, the time dimension is introduced to generate the warning push coefficient Awarning, and the first push threshold F1 and the second push threshold F2 are preset to perform preliminary comparative evaluation with the acquired warning push coefficient Awarning to analyze the risk situation of the landslide impact area; S5. Introduce the feedback mechanism again, build a feedback optimization formula, input feedback information and sensor error correction, input it into the feedback optimization formula, calculate and output the risk assessment adjustment coefficient △Rupdate, adjust the update frequency and scale of the risk scoring algorithm formula, and then execute S4 after adjustment to conduct a secondary assessment and analysis of the risk situation of the landslide affected area, and automatically generate the current landslide affected area number. Each landslide affected area number corresponds to the corresponding risk level and push strategy.

2. A landslide geological disaster early warning push method according to claim 1, characterized in that: Said S1 includes S11, S12 and S13; S1. By setting up several detection points in the landslide area and installing an integrated sensor group in each detection point, the mountain data is collected in real time. The integrated sensor group includes a rain gauge, a surface displacement sensor, a groundwater level sensor, a soil moisture sensor, a viscometer, a strain sensor and an anemometer; The mountain data include rainfall Prai, surface displacement Ddis, groundwater level Ggro, soil moisture change rate Wsoi, soil viscosity Vvis, geological structure stress Sste and landslide area wind speed Vwin; S12. Set up a LoRa wireless gateway to connect the integrated sensor group to the central processing system through a network, and then transmit the collected mountain data to the central processing system through a standard communication protocol.

3. A landslide geological disaster early warning push method according to claim 2, characterized in that: S13, receiving mountain data in real time in the central processing system, and preprocessing the mountain data to obtain a landslide impact data set, wherein the landslide impact data set includes a landslide occurrence probability Plan and a geological stress change ΔSstr; The specific processing methods are as follows; The landslide occurrence probability Plan is obtained by calculating and processing the rainfall Prai, surface displacement Ddis and groundwater level Ggro in the mountain data. The specific calculation formula is: Plan = f (Prai, Ddis, Ggro, Hhis), where f represents the relationship function, and Hhis represents the historical landslide probability; The geological stress change ΔSstr is obtained by calculating and processing the geological structure stress Sste in the mountain data. The specific calculation formula is: Where Sini represents the stress value of the mountain under normal conditions, which is set by the initial setting, and △t represents the time change.

4. A landslide geological disaster early warning push method according to claim 3, characterized in that: Said S2 includes S21; S21, constructing a landslide impact area algorithm formula, extracting mountain data from the central processing system and inputting it into the landslide impact area algorithm formula, calculating and outputting the landslide impact range Aimpact, and predicting the impact range of the landslide; The landslide impact range Aimpact is calculated and outputted by the following landslide impact area algorithm formula; Wherein, Sterrain represents the topographic constant, Jd represents the slope angle, α represents the global adjustment coefficient, β1 and β2 represent the preset weight values ​​of the surface displacement Ddis and the groundwater level Ggro, γ1 and γ2 represent the preset weight values ​​of the geological structure stress Sste and the wind speed Vwin in the landslide area, δ represents a constant used to avoid the denominator being zero, and the specific values ​​of β1, β2, γ1 and γ2 are set by the user. Indicates the influence of terrain and slope angle. Represents soil physical properties and stress changes.

5. A landslide geological disaster early warning push method according to claim 4, characterized in that: The S3 includes S31; S31. Based on the predicted landslide impact range, a risk scoring algorithm formula is constructed, the landslide impact data set is extracted, and the data is input into the risk scoring algorithm formula to calculate and output the comprehensive risk score Rreg of different landslide image areas, and analyze the risk situation of the current area; The comprehensive risk score Rreg is calculated by the following risk score algorithm formula; Rreg i =a1·Plan+a2·(Ppop+Pbui+Szyx)+a3·△Sstr; In the formula, Rreg i It represents the comprehensive analysis score of the area affected by the i-th landslide, (Ppop+Pbui+Szyx) represents the impact degree of the landslide, Ppop represents the population density in the landslide area, Pbui represents the building density, Szyx represents the important infrastructure index, and its specific value is set by the user according to the actual situation of the area, a1, a2 and a3 represent the preset weight values ​​of the landslide probability Plan, the impact degree of the landslide and the geological stress change △Sstr, respectively, and a1+a2+a3=1, and its specific value is set by the user.

6. A landslide geological disaster early warning push method according to claim 1, characterized in that: The S4 includes S41 and S42; S41, based on the current landslide impact range Aimpact and the comprehensive risk score Rreg, the information of the warning push introduced in the time dimension will be dynamically adjusted according to the change of risk over time, and the warning push coefficient Awarning will be calculated and generated; The warning push coefficient Awarning is calculated by the following algorithm formula: Where λ represents the adjustment factor of the warning push range, and Tresponse represents the response time as the risk level is adjusted.

7. A landslide geological disaster early warning push method according to claim 6, characterized in that: S42, the staff initially presets the first push threshold F1 and the second push threshold F2, and then compares and evaluates them with the obtained warning push coefficient Awarning to analyze the risk situation of the landslide affected area. The specific evaluation results are as follows; When the warning push coefficient Awarning> the first push threshold F1, it means that there is a landslide anomaly in the current landslide affected area, and the first landslide information is pushed at this time; When the second push threshold F2 ≤ the warning push coefficient Awarning ≤ the first push threshold F1, it indicates that there is a potential abnormality in the current landslide affected area, and the second landslide information is pushed at this time; When the warning push coefficient Awarning < the second push threshold F2, it means that the current landslide affected area is in a normal state, and the third landslide information is pushed; And the first push threshold F1>the second push threshold F2.

8. A landslide geological disaster early warning push method according to claim 6, characterized in that: The S5 includes S51, S52 and S53; S51, using a mobile device to provide real-time feedback of on-site information of the landslide-affected area, including but not limited to surface cracks, mountain movement, and tilted objects, and then binding the feedback information with geographic location data and uploading it to a central processing system through an application structure API, where the feedback information is summarized and calculated and output as a weight Ffeedback; Then, by comparing the mountain data of historical landslide events collected by the integrated sensor group, the sensor error correction amount Eerror is obtained by performing difference calculation based on the mountain data of historical landslide events and the currently collected mountain data.

9. A landslide geological disaster early warning push method according to claim 8, characterized in that: S52, based on the obtained feedback information weight Ffeedback and the sensor error correction amount Eerror, calculate and output the risk assessment adjustment coefficient △Rupdate, and iteratively adjust S1 to S4; The risk assessment adjustment coefficient △Rupdate is calculated and obtained by the following algorithm formula; In the formula, β represents the learning rate adjustment parameter, and Nitera represents the number of iterations; S53, after iterative adjustment, re-execute S4 to perform secondary evaluation and comparative evaluation, obtain corresponding landslide information, and execute regional number generation and push strategy for different landslide information, the specific contents are as follows; When the first landslide information is received, a LIZI-1 number is automatically generated, indicating that the area identified by the LIZI-1 number is assessed as a first-level dangerous area, and an emergency evacuation notice is immediately issued through a mobile communication device; When the second landslide information is received, a LIZI-2 number is automatically generated, indicating that the area marked by the LIZI-2 number is assessed as a secondary danger area. At this time, a preventive warning notice is immediately issued through mobile communication equipment, and residents need to prepare to evacuate, but do not need to take immediate action; When the third landslide information is received, the LIZI-3 number is automatically generated, indicating that the area marked by the LIZI-3 number is assessed as a level 3 danger area. At this time, there is no need to send an early warning message, there is no risk of landslide, and monitoring will continue.

10. A landslide geological disaster early warning push system, applied to a landslide geological disaster early warning push method according to any one of claims 1 to 9, characterized in that: It includes mountain data collection module, landslide impact area analysis module, landslide risk analysis module, early warning push module and feedback optimization analysis module; The mountain data acquisition module sets a number of detection points in the landslide area and installs an integrated sensor group in each detection point to collect mountain data in real time, and sends the data to the central processing system through a wireless gateway for preprocessing to obtain a landslide impact data set; The landslide impact area analysis module constructs a landslide impact area algorithm formula, extracts mountain data and inputs it into the landslide impact area algorithm formula, calculates and outputs the landslide impact range Aimpact, and predicts the area affected by the landslide; The landslide risk analysis module further analyzes the risk scores of different landslide-affected areas based on the predicted landslide-affected areas, constructs a risk scoring algorithm formula, extracts the landslide impact data set and inputs it into the risk scoring algorithm formula, calculates and outputs the comprehensive risk scores Rreg of different landslide-affected areas; The warning push module introduces the time dimension based on the acquired landslide impact range Aimpact and the comprehensive risk score Rreg, generates a warning push coefficient Awarning, and presets a first push threshold F1 and a second push threshold F2 to perform a preliminary comparative evaluation with the acquired warning push coefficient Awarning, and analyzes the risk situation of the landslide impact area; The feedback optimization analysis module constructs a feedback optimization formula, inputs feedback information and sensor error correction, inputs the feedback optimization formula, calculates and outputs the risk assessment adjustment coefficient △Rupdate, adjusts the update frequency and scale of the risk scoring algorithm formula, and then executes S4 after adjustment to perform a secondary assessment and analysis of the risk situation of the landslide affected area, and automatically generates the current landslide affected area number, each landslide affected area number corresponds to a corresponding risk level and push strategy.

Images