Rainfall type landslide critical early warning method and system

Abstract

The invention relates to the technical field of geological disaster early warning, in particular to a rainfall type landslide critical early warning method and system, and the method comprises the steps: obtaining multi-source geographic data of a target region, and generating grid data through a spatial interpolation method; extracting terrain parameters and terrain humidity indexes based on a DEM model, and determining landslide susceptibility evaluation factors in combination with stratum lithology, soil types and human activity data; distributing weights by adopting an analytic hierarchy process, dividing a landslide susceptible area and positioning a prediction area; based on historical disaster data and rock-soil body permeability coefficients, landslide critical curves of different stratum lithology are dynamically fitted, and a landslide occurrence probability is output through a random forest algorithm; and multiplying the susceptibility by a probability result to generate a gridding risk value, and dividing early warning grades. The method has the effect of improving the precision and timeliness of landslide early warning analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster early warning, and in particular to a critical early warning method and system for rainfall-induced landslides. Background Art

[0002] With the influence of climate change and human activities, natural disasters are becoming more and more frequent. Among them, landslide disasters have become a type of natural disaster that cannot be ignored. Rainfall is one of the main factors that induce landslide disasters. Rainfall-induced landslides are currently the focus and hotspot of landslide disaster research at home and abroad. According to statistics, more than 80% of geological disasters in China are directly or indirectly affected by rainfall. Therefore, developing the impact mechanism and early warning of regional rainfall-induced landslide disasters is of great significance to regional disaster prevention and mitigation.

[0003] Currently, early warning of rainfall-induced landslides relies primarily on traditional monitoring methods, such as manual inspections and remote sensing. However, these methods have limitations. First, traditional manual inspections are inefficient and lack full coverage. Second, while remote sensing offers the advantage of wide coverage, it is limited by sensor precision, resulting in significant inaccuracies in landslide identification in complex terrain or areas covered by vegetation. Furthermore, some automated early warning systems exist, but they also suffer from weak multi-source data integration capabilities, inadequate threshold modeling, and poor warning timeliness and adaptability. In summary, existing technologies struggle to meet the demand for accurate early warning of landslides in complex environments, leaving room for improvement. Summary of the Invention

[0004] In order to improve the warning accuracy and timeliness of rainfall-induced landslide early warning analysis, the present application provides a rainfall-induced landslide critical early warning method and system.

[0005] In the first aspect, the above-mentioned invention object of the present application is achieved through the following technical solutions:

[0006] A critical early warning method for rainfall-induced landslides, comprising the following steps:

[0007] Acquire multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data, and human engineering activity data, and perform gridding processing on the multi-source geographic data to generate gridded data;

[0008] determining a landslide susceptibility evaluation factor based on the gridded data, generating a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determining a landslide prediction area based on the landslide susceptibility result;

[0009] Acquiring historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculating effective rainfall based on rock and soil permeability coefficient, and dynamically fitting landslide critical curves under different geological lithologies according to the effective rainfall;

[0010] Acquiring a critical rainfall parameter based on the landslide critical curve, and determining a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter;

[0011] Based on the landslide susceptibility results and the rainfall-type landslide occurrence probability results, a gridded hazard value is generated, and a landslide warning signal is generated according to the gridded hazard value.

[0012] By adopting the above technical solution, in the process of landslide early warning analysis, multi-source geographic data of the target study area are collected, wherein the multi-source geographic data include rainfall data, topography data, stratigraphic lithology data, soil type data, prepared cover data and human engineering activity data of the area. Rainfall data can be obtained in real time through meteorological stations, and the remaining data can be obtained in real time through remote sensing monitoring. The collected multi-source geographic data are gridded to generate gridded data, and the formed gridded data are used to generate landslide susceptibility evaluation factors to facilitate landslide susceptibility evaluation and analysis of the target study area. The obtained landslide susceptibility factors are used to perform hierarchical analysis to determine their weight coefficients. The landslide susceptibility evaluation is performed based on the landslide susceptibility factors and their weight coefficients to obtain landslide susceptibility results. The landslide susceptibility of the target study area can be regionally graded, so that the areas in the target study area that are prone to landslide disasters can be identified to obtain landslide prediction areas. Historical landslide disaster data are collected for the identified landslide prediction areas. Based on the historical landslide disaster data and the real-time rainfall data of the area, and combined with the area's The effective rainfall is calculated from the rock and soil permeability coefficient. The obtained effective rainfall is used to dynamically fit the critical landslide curves under different geological and lithological conditions to adapt to different strata lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warnings. By analyzing the landslide critical curves, the critical rainfall parameter is obtained. The critical rainfall parameter refers to the combined threshold of the minimum rainfall intensity and rainfall duration required to trigger a landslide disaster under different geological and lithological conditions. The rainfall-induced landslide probability results in the area are determined based on the critical rainfall parameter, which can dynamically match the landslide probability in the area and improve the response speed of rainfall-induced landslide warnings. Based on the landslide susceptibility results and rainfall-induced landslide probability results, a gridded hazard value is generated for the target study area. The gridded hazard value refers to the landslide hazard value corresponding to each grid after the target study area is gridded. The corresponding landslide warning signal is generated based on the gridded hazard value, thereby realizing the rainfall-induced landslide warning analysis process for the target study area. The entire warning analysis process integrates multi-source geographic data and performs dynamic threshold matching to improve the warning accuracy and timeliness of rainfall-induced landslide warning analysis.

[0013] In a preferred example, the present application may be further configured as follows: the landslide susceptibility evaluation factors include rainfall factors, topographic factors, hydrological environmental factors, geological factors, surface cover factors, soil factors, and human activity factors; and determining the landslide susceptibility evaluation factors based on the gridded data specifically includes:

[0014] Converting the rainfall data into a continuous gridded rainfall layer through spatial interpolation to form a rainfall factor;

[0015] Input the topographic data into a preset DEM model, extract the topographic parameters and topographic humidity index of the target study area, generate topographic factors based on the topographic parameters, and determine the hydrological environment factors based on the topographic humidity index;

[0016] Integrate stratum lithology data and soil type data to analyze stratum lithology classification, soil texture, and distance from the fault zone to form geological factors and soil factors;

[0017] Based on the vegetation cover data and human engineering activity data, the road, building and vegetation distribution maps are analyzed, the surface cover factor is determined according to the vegetation distribution map, and the distance from each grid cell in the target study area to the nearest road is calculated based on the road and building distribution map to form the human activity factor.

[0018] By adopting the above technical solution, rainfall data is obtained in real time, including real-time rainfall, historical rainfall and rainfall forecast data, and converted into gridded rainfall layers through Kriging spatial interpolation to form rainfall factors, which solves the local error problem caused by data discretization and provides high-resolution and continuous rainfall data for landslide susceptibility analysis. The terrain parameters (such as elevation, slope, curvature and other parameters) and terrain moisture index of the target study area are extracted from the terrain and geomorphology data through the DEM model to accurately quantify the surface runoff and seepage characteristics. For example, when the slope is greater than 25° and the terrain moisture index is greater than 8.5, the high-risk slope with strong seepage can be identified, providing key hydrological environment factors and terrain and geomorphology factors for landslide susceptibility analysis. Furthermore, the stratum lithology data and soil Type data, the stratigraphic lithology classification, soil texture and distance from the fault zone are parsed from the stratigraphic lithology data and soil type data, and geological factors and soil factors are constructed. For example, when the shale area has low shear strength and is less than 500m away from the fault zone, the probability of landslide susceptibility is greatly increased, which provides geological factors and soil factors for landslide susceptibility analysis. By parsing vegetation cover data and human engineering activity data, the road, building and vegetation distribution map in the target study area is obtained. According to the vegetation distribution map, the surface cover factor in the area is determined. The road distribution map and building distribution map are used to calculate the distance from each grid unit in the target study area to the nearest road. As a human activity factor, it provides a multi-source evaluation factor for landslide susceptibility analysis, thereby improving the accuracy of landslide susceptibility analysis.

[0019] In a preferred example, the present application may be further configured as follows: generating a landslide susceptibility result of a target study area according to the landslide susceptibility evaluation factor and its weight, and determining a landslide prediction area based on the landslide susceptibility result, specifically including:

[0020] The weight coefficients of each landslide susceptibility evaluation factor were assigned using the analytic hierarchy process, and the landslide susceptibility evaluation factors were normalized and weighted superimposed to calculate the landslide susceptibility results of each grid cell in the target study area.

[0021] Based on the landslide susceptibility results of each grid unit, different levels of landslide prone areas are divided to determine the landslide prediction area.

[0022] By adopting the above technical scheme, the weight coefficients of the landslide susceptibility evaluation factors are allocated through the hierarchical analysis method, which avoids the subjective bias of the traditional method and makes the weight allocation of the landslide susceptibility evaluation factors more in line with the actual geological conditions. The landslide susceptibility evaluation factors are normalized and weighted superimposed, and the multi-source factors are integrated into the same landslide susceptibility index, which solves the problem of different dimensions of multiple factors. The landslide susceptibility results of each grid unit in the target study area are calculated based on the landslide susceptibility factors after normalization and weighted superposition. According to the landslide susceptibility results of each grid unit, the target study area is divided into different levels of landslide prone areas. The landslide prediction areas of different levels are determined within the target study area using the landslide prone areas of different levels. The landslide prediction area refers to the area where rainfall-type landslides in the area are further warned and analyzed, realizing the positioning of the spatial landslide prediction area, which is conducive to focusing monitoring resources on high-risk areas and improving the efficiency of landslide warning.

[0023] In a preferred example, the present application may be further configured as follows: acquiring historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculating effective rainfall in combination with rock and soil permeability coefficient, and dynamically fitting landslide critical curves under different geological lithologies based on the effective rainfall, specifically including:

[0024] fitting an initial critical curve based on the historical landslide disaster data, and obtaining an initial critical rainfall parameter according to the initial critical curve;

[0025] Determining the permeability coefficient of the rock and soil mass according to the lithology classification of the strata in the landslide prediction area, and determining the saturation state of the rock and soil mass based on the permeability coefficient of the rock and soil mass and real-time rainfall data;

[0026] The initial critical rainfall parameter is adjusted in real time according to the saturation state of the rock and soil mass, the landslide critical rainfall threshold value under different geological lithologies is generated based on the adjusted critical rainfall parameter, and the landslide critical curve is generated according to the landslide critical rainfall threshold value.

[0027] By adopting the above technical solution, an initial critical curve is fitted through historical landslide disaster data, and a benchmark relationship between rainfall intensity and rainfall duration is established. The initial critical rainfall parameter is determined through the initial critical curve. The permeability coefficient of the rock and soil in the landslide prediction area is determined by analyzing the stratum lithology in the landslide prediction area. The differentiated permeability parameters of the rock and soil are determined by the stratum lithology classification in the landslide prediction area, such as the permeability parameter of clay is 0.8 and the permeability parameter of sand is 0.9. The saturation state of the rock and soil is determined based on the permeability coefficient and real-time rainfall data in the area, and the cumulative permeability effect of the previous rainfall in the area is quantified, thereby improving the accuracy of rainfall-induced landslide prediction analysis. The saturation state of the rock and soil is used to dynamically adjust the initial critical rainfall parameter and generate a landslide critical rainfall threshold. The corresponding landslide critical curve is generated based on the landslide critical rainfall threshold to adapt to different stratum lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warning.

[0028] In a preferred example, the present application may be further configured as follows: obtaining a critical rainfall parameter based on the landslide critical curve, and determining a rainfall-induced landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter, specifically including:

[0029] According to the landslide critical curve, critical rainfall parameters are calculated to construct a rainfall landslide data set;

[0030] Based on the rainfall-type landslide dataset, a random forest algorithm is used to combine the terrain parameters and terrain humidity index of the landslide prediction area to output the probability result of rainfall-type landslide occurrence in the landslide prediction area.

[0031] By adopting the above technical solution, all critical rainfall parameters are counted according to the landslide critical curve and integrated to form a rainfall-type landslide data set. Using the random forest algorithm, combined with terrain parameters and terrain humidity index, a probabilistic landslide warning model is constructed, and the probability results of rainfall-type landslide occurrence are output, realizing the landslide warning prediction and analysis function. Through dynamic adaptation of geological parameters and multi-factor probability modeling, the accuracy and reliability of rainfall-type landslide warning are significantly improved.

[0032] In a preferred example, the present application may be further configured as follows: generating a gridded hazard value based on the landslide susceptibility result and the rainfall-induced landslide probability result, and generating a landslide warning signal according to the gridded hazard value, specifically including:

[0033] The landslide susceptibility result and the rainfall-induced landslide probability result of each grid cell in the landslide prediction area are multiplied to obtain the gridded hazard value;

[0034] Different levels of landslide warning signals are divided according to the gridded hazard values. Based on the landslide warning signals of the same level, adjacent grid units are merged to form a landslide warning area.

[0035] By adopting the above technical solution, the landslide susceptibility result of each grid unit is multiplied by the probability of rainfall-type landslide to obtain a gridded hazard value, realizing a two-way coupling of geological static conditions and dynamic rainfall processes, accurately quantifying the comprehensive risk, avoiding misjudgment caused by a single indicator, and reducing the false alarm rate of landslide warnings. According to the gridded hazard value, landslide warning signals of different levels are divided, and adjacent grid units of the same level of warning are merged to form a continuous landslide warning area. Through hazard fusion and spatial warning, the accuracy of landslide warnings and the efficiency of emergency response are significantly improved.

[0036] In a preferred example, the present application may be further configured as follows: after generating a gridded hazard value based on the landslide susceptibility result and the rainfall-type landslide occurrence probability result, and generating a landslide warning signal according to the gridded hazard value, the rainfall-type landslide critical warning method may further include:

[0037] Collect landslide sign data reported by the public in real time, and pre-process the landslide sign data to obtain valid data;

[0038] Based on the Bayesian network model, the effective data and the gridded hazard value are fused to obtain a modified landslide warning signal, an emergency response signal is triggered according to the modified landslide warning signal, and a directional warning notification is sent to the target area.

[0039] By adopting the above technical solution, a mobile application is used to receive landslide sign data reported by the public. The landslide sign data includes a description of landslide precursor phenomena, geographic location, timestamp and multimedia evidence. The landslide sign data is preprocessed to obtain valid data, including verifying whether the reported location is within the landslide prediction area through GPS positioning, analyzing the uploaded multimedia evidence using an image recognition algorithm, identifying ground cracks, vegetation tilt or surface displacement characteristics, and comparing real-time sensor data. If the soil moisture or displacement monitoring value in the area is consistent with the reported phenomenon, it is marked as valid data. The valid data and the gridded hazard value are fused using a Bayesian network model to obtain a revised landslide warning signal. The emergency response signal is triggered according to the revised landslide warning signal, and a targeted warning notification is sent to the target area. Combined with public data, the monitoring blind spots are filled, significantly improving the accuracy and real-time performance of landslide warnings in complex terrain.

[0040] Secondly, the above-mentioned invention objectives of this application are achieved through the following technical solutions:

[0041] A rainfall-induced landslide critical warning system, comprising:

[0042] A multi-source data processing module is used to obtain multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data and human engineering activity data, and perform grid processing on the multi-source geographic data to generate gridded data;

[0043] a landslide susceptibility analysis module, configured to determine a landslide susceptibility evaluation factor based on the gridded data, generate a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determine a landslide prediction area based on the landslide susceptibility result;

[0044] a critical curve generation module, configured to obtain historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculate effective rainfall based on the rock and soil permeability coefficient, and dynamically fit landslide critical curves under different geological lithologies according to the effective rainfall;

[0045] A landslide probability prediction module is used to obtain a critical rainfall parameter based on the landslide critical curve, and determine a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter;

[0046] The landslide warning signal generating module is used to generate a gridded hazard value based on the landslide susceptibility result and the rainfall-type landslide occurrence probability result, and generate a landslide warning signal according to the gridded hazard value.

[0047] By adopting the above technical solution, in the process of landslide early warning analysis, multi-source geographic data of the target study area are collected, wherein the multi-source geographic data include rainfall data, topography data, stratigraphic lithology data, soil type data, prepared cover data and human engineering activity data of the area. Rainfall data can be obtained in real time through meteorological stations, and the remaining data can be obtained in real time through remote sensing monitoring. The collected multi-source geographic data are gridded to generate gridded data, and the formed gridded data are used to generate landslide susceptibility evaluation factors to facilitate landslide susceptibility evaluation and analysis of the target study area. The obtained landslide susceptibility factors are used to perform hierarchical analysis to determine their weight coefficients. The landslide susceptibility evaluation is performed based on the landslide susceptibility factors and their weight coefficients to obtain landslide susceptibility results. The landslide susceptibility of the target study area can be regionally graded, so that the areas in the target study area that are prone to landslide disasters can be identified to obtain landslide prediction areas. Historical landslide disaster data are collected for the identified landslide prediction areas. Based on the historical landslide disaster data and the real-time rainfall data of the area, and combined with the area's The effective rainfall is calculated from the rock and soil permeability coefficient. The obtained effective rainfall is used to dynamically fit the critical landslide curves under different geological and lithological conditions to adapt to different strata lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warnings. By analyzing the landslide critical curves, the critical rainfall parameter is obtained. The critical rainfall parameter refers to the combined threshold of the minimum rainfall intensity and rainfall duration required to trigger a landslide disaster under different geological and lithological conditions. The rainfall-induced landslide probability results in the area are determined based on the critical rainfall parameter, which can dynamically match the landslide probability in the area and improve the response speed of rainfall-induced landslide warnings. Based on the landslide susceptibility results and rainfall-induced landslide probability results, a gridded hazard value is generated for the target study area. The gridded hazard value refers to the landslide hazard value corresponding to each grid after the target study area is gridded. The corresponding landslide warning signal is generated based on the gridded hazard value, thereby realizing the rainfall-induced landslide warning analysis process for the target study area. The entire warning analysis process integrates multi-source geographic data and performs dynamic threshold matching to improve the warning accuracy and timeliness of rainfall-induced landslide warning analysis.

[0048] Thirdly, the above-mentioned purpose of this application is achieved through the following technical solutions:

[0049] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned critical early warning method for rainfall-induced landslides are implemented.

[0050] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0051] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned rainfall-induced landslide critical warning method.

[0052] In summary, this application includes at least one of the following beneficial technical effects:

[0053] 1. In the process of landslide early warning analysis, by collecting multi-source geographic data of the target study area, wherein the multi-source geographic data includes rainfall data, topography data, stratigraphic lithology data, soil type data, preparation coverage data and human engineering activity data of the area, the collected multi-source geographic data are processed into grid data, and the formed grid data is used to generate a landslide susceptibility evaluation factor, so as to facilitate the landslide susceptibility evaluation analysis of the target study area, and the obtained landslide susceptibility factor is used to determine its weight coefficient by the hierarchical analysis method, and the landslide susceptibility evaluation is carried out according to the landslide susceptibility factor and its weight coefficient to obtain the landslide susceptibility result, which can be used to evaluate the landslide in the target study area. The susceptibility of landslides is divided into regional grades, so that the areas in the target study area that are prone to landslide disasters can be identified and the landslide prediction areas can be obtained. The historical landslide disaster data of the identified landslide prediction areas are collected. Based on the historical landslide disaster data and the rainfall data of the area, the critical rainfall parameters under different geological lithologies in the area are calculated. The probability results of rainfall-induced landslides in the area are determined based on the critical rainfall parameters. The probability of landslides in the area can be dynamically matched, and the response speed of rainfall-induced landslide warnings can be improved. Based on the landslide susceptibility results and the rainfall-induced landslide probability results, the gridded hazard value of the target study area is generated, and the corresponding landslide warning signal is generated based on the gridded hazard value.

[0054] 2. By acquiring rainfall data in real time, including real-time rainfall, historical rainfall and rainfall forecast data, and generating a gridded rainfall layer through Kriging spatial interpolation to form a rainfall factor, the local error problem caused by data discretization is solved, and high-resolution and continuous rainfall data is provided for landslide susceptibility analysis. The terrain parameters (such as elevation, slope, curvature and other parameters) and terrain moisture index of the target study area are extracted from the terrain and geomorphology data through the DEM model, and the surface runoff and seepage characteristics are accurately quantified. For example, when the slope is greater than 25° and the terrain moisture index is greater than 8.5, a high-risk slope with strong seepage can be identified, providing key hydrological environment factors and terrain and geomorphology factors for landslide susceptibility analysis. Furthermore, the stratum lithology data and soil type data are integrated. The stratum lithology classification, soil texture, and distance from the fault zone are analyzed from the stratum lithology data and soil type data to construct geological factors and soil factors. For example, in shale areas with low shear strength and less than 500m from the fault zone, the probability of landslide susceptibility is greatly increased, providing geological factors and soil factors for landslide susceptibility analysis. By analyzing vegetation cover data and human engineering activity data, the road, building, and vegetation distribution map in the target study area is obtained. The surface cover factor in the area is determined based on the vegetation distribution map. The road distribution map and building distribution map are used to calculate the distance from each grid cell in the target study area to the nearest road. This is used as a human activity factor to provide a multi-source evaluation factor for landslide susceptibility analysis, thereby improving the accuracy of landslide susceptibility analysis.

[0055] 3. By fitting the initial critical curve with historical landslide disaster data, a benchmark relationship between rainfall intensity and rainfall duration was established. The initial critical rainfall parameter was determined through the initial critical curve. The permeability coefficient of the rock and soil in the landslide prediction area was determined by analyzing the stratum lithology in the landslide prediction area. Differentiated rock and soil permeability parameters were determined by stratum lithology classification in the landslide prediction area, such as the permeability parameter of clay is 0.8 and the permeability parameter of sand is 0.9. The saturation state of the rock and soil was determined based on the permeability coefficient and real-time rainfall data in the area, and the cumulative permeability effect of previous rainfall in the area was quantified, thereby improving the accuracy of rainfall-induced landslide prediction analysis. The saturation state of the rock and soil was used to dynamically adjust the initial critical rainfall parameter and generate a landslide critical rainfall threshold. The corresponding landslide critical curve was generated based on the landslide critical rainfall threshold to adapt to different stratum lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warning.

[0056] 4. Use mobile applications to receive landslide sign data reported by the public. Landslide sign data includes descriptions of landslide precursor phenomena, geographic location, timestamps, and multimedia evidence. Data preprocessing is performed on the landslide sign data to obtain valid data, including verifying whether the reported location is within the landslide prediction area through GPS positioning. Image recognition algorithms are used to analyze the uploaded multimedia evidence to identify ground cracks, vegetation tilt, or surface displacement characteristics. Real-time sensor data is compared. If the soil moisture or displacement monitoring value in the area is consistent with the reported phenomenon, it is marked as valid data. The valid data and gridded hazard value are fused using a Bayesian network model to obtain a revised landslide warning signal. The emergency response signal is triggered based on the revised landslide warning signal, and a targeted warning notification is sent to the target area. Combined with public data, monitoring blind spots are filled, significantly improving the accuracy and real-time performance of landslide warnings in complex terrain. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0058] Figure 2 This is a flowchart for implementing step S20 in a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0059] Figure 3 This is another implementation flow chart of step S20 in a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0060] Figure 4 This is a flowchart for implementing step S30 in a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0061] Figure 5 This is a flowchart for implementing step S40 in a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0062] Figure 6 This is a flowchart for implementing step S50 in a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0063] Figure 7 This is another implementation flow chart of a critical early warning method for rainfall-induced landslides in one embodiment of the present application;

[0064] Figure 8 This is a principle block diagram of a rainfall-induced landslide critical warning system in one embodiment of the present application;

[0065] Figure 9 It is a schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0066] The present application is further described in detail below with reference to the accompanying drawings.

[0067] In one embodiment, if Figure 1 As shown, the present application discloses a critical early warning method for rainfall-induced landslides, which specifically includes the following steps:

[0068] S10: Acquire multi-source geographic data of the target study area, wherein the multi-source geographic data includes rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data, and human engineering activity data, and perform gridding processing on the multi-source geographic data to generate gridded data.

[0069] Specifically, in the process of landslide early warning analysis, rainfall data is obtained in real time through meteorological stations, and topographic data, stratigraphic lithology data, soil type data, prepared cover data and human engineering activity data are obtained in real time through remote sensing monitoring. The collected multi-source geographic data are gridded to generate gridded data, and the formed gridded data is used to generate landslide susceptibility evaluation factors to facilitate landslide susceptibility evaluation and analysis of the target study area.

[0070] Furthermore, by integrating multi-source geographic data such as rainfall, topography, geology, soil, vegetation and human activities (such as terrain moisture index, stratigraphic lithology, distance from fault zone, etc.), a multi-factor evaluation system was constructed to solve the problem of single data in traditional early warning models and improve the accuracy of landslide warnings.

[0071] S20: Determine a landslide susceptibility evaluation factor based on the gridded data, generate a landslide susceptibility result of a target study area according to the landslide susceptibility evaluation factor and its weight, and determine a landslide prediction area based on the landslide susceptibility result.

[0072] Specifically, the obtained landslide susceptibility factors are used to perform hierarchical analysis to determine their weight coefficients, such as the slope weight accounts for 25%, the stratum lithology weight accounts for 20%, and the rainfall weight accounts for 18%. The landslide susceptibility evaluation is carried out according to the landslide susceptibility factors and their weight coefficients to obtain the landslide susceptibility results. The landslide susceptibility of the target study area can be divided into regional levels, so that the areas in the target study area that are prone to landslide disasters can be identified and the landslide prediction area can be obtained.

[0073] S30: Acquire historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculate effective rainfall in combination with rock and soil permeability coefficient, and dynamically fit landslide critical curves under different geological lithologies based on the effective rainfall.

[0074] Specifically, the effective rainfall is calculated based on historical landslide disaster data and real-time rainfall data in the area, combined with the permeability coefficient of the rock and soil in the area. The obtained effective rainfall is used to dynamically fit the landslide critical curves under different geological lithologies to adapt to different stratum lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warnings.

[0075] S40: Acquire a critical rainfall parameter based on the landslide critical curve, and determine a rainfall-induced landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter.

[0076] Specifically, the critical rainfall parameter refers to the combined threshold of the minimum rainfall intensity and rainfall duration required to trigger a landslide disaster under different geological and lithological conditions. The probability of rainfall-induced landslides in the area is determined based on the critical rainfall parameter, which can dynamically match the probability of landslides in the area and improve the response speed of rainfall-induced landslide warnings.

[0077] S50: Based on the landslide susceptibility result and the rainfall-induced landslide occurrence probability result, a gridded hazard value is generated, and a landslide warning signal is generated according to the gridded hazard value.

[0078] Specifically, based on the landslide susceptibility results and the rainfall-induced landslide probability results, a gridded hazard value for the target study area is generated. The gridded hazard value refers to the hazard value of landslide occurrence corresponding to each grid after the target study area is rasterized. The corresponding landslide warning signal is generated based on the gridded hazard value.

[0079] In this embodiment, during the landslide early warning analysis process, multi-source geographic data of the target study area is collected, wherein the multi-source geographic data includes rainfall data, topography data, stratigraphic lithology data, soil type data, prepared cover data and human engineering activity data of the area. Rainfall data can be obtained in real time through a meteorological station, and the remaining data can be obtained in real time through remote sensing monitoring. The collected multi-source geographic data are gridded to generate gridded data, and a landslide susceptibility evaluation factor is generated using the formed gridded data to facilitate the landslide susceptibility evaluation and analysis of the target study area. The obtained landslide susceptibility factor is subjected to a hierarchical analysis method to determine its weight coefficient. The landslide susceptibility is evaluated based on the landslide susceptibility factor and its weight coefficient to obtain a landslide susceptibility result. The landslide susceptibility of the target study area can be regionally graded, so that areas in the target study area that are prone to landslide disasters can be identified to obtain landslide prediction areas. Historical landslide disaster data is collected for the identified landslide prediction areas. Based on the historical landslide disaster data and the real-time rainfall data of the area, and combined with the rock and soil of the area, the landslide susceptibility evaluation factor is generated. The effective rainfall is calculated based on the volume permeability coefficient. The obtained effective rainfall is used to dynamically fit the critical landslide curves under different geological and lithological conditions to adapt to different strata lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warnings. The critical rainfall parameter is obtained by analyzing the landslide critical curve. The critical rainfall parameter refers to the combined threshold of the minimum rainfall intensity and rainfall duration required to trigger a landslide disaster under different geological and lithological conditions. The rainfall-induced landslide probability results in the area are determined based on the critical rainfall parameter, which can dynamically match the landslide probability in the area and improve the response speed of rainfall-induced landslide warnings. The gridded hazard value for the target study area is generated based on the landslide susceptibility results and the rainfall-induced landslide probability results. The gridded hazard value refers to the landslide hazard value corresponding to each grid after the target study area is gridded. The corresponding landslide warning signal is generated based on the gridded hazard value, thereby realizing the rainfall-induced landslide warning analysis process for the target study area. The entire warning analysis process integrates multi-source geographic data and performs dynamic threshold matching to improve the warning accuracy and timeliness of rainfall-induced landslide warning analysis.

[0080] In one embodiment, if Figure 2 As shown, in step S20, the landslide susceptibility evaluation factors include rainfall factor, topographic factor, hydrological environment factor, geological factor, surface cover factor, soil factor and human activity factor. The landslide susceptibility evaluation factors are determined based on the grid data, specifically including:

[0081] S11: The rainfall data is converted into a continuous gridded rainfall layer through spatial interpolation to form a rainfall factor.

[0082] Specifically, real-time rainfall data is obtained from meteorological stations, including real-time rainfall, historical rainfall and rainfall forecast data. The discrete station data is converted into a spatially continuous 1km×1km grid rainfall layer through the Kriging spatial interpolation method to form a rainfall factor, which solves the local error problem caused by data discretization and provides high-resolution and continuous rainfall data for landslide susceptibility analysis.

[0083] S12: Input the topographic data into a preset DEM model, extract the topographic parameters and topographic humidity index of the target study area, generate topographic factors based on the topographic parameters, and determine the hydrological environment factors according to the topographic humidity index.

[0084] Specifically, the DEM model is used to extract the terrain parameters (such as elevation, slope, curvature, etc.) and terrain moisture index of the target study area from the terrain and geomorphological data, and accurately quantify the surface runoff and seepage characteristics. For example, when the slope is greater than 25° and the terrain moisture index is greater than 8.5, high-seepage and high-risk slopes can be identified, providing key hydrological environment factors and terrain and geomorphological factors for landslide susceptibility analysis.

[0085] S13: Integrate stratum lithology data and soil type data, analyze stratum lithology classification, soil texture and distance from the fault zone, and form geological factors and soil factors.

[0086] Specifically, by integrating stratum lithology data and soil type data, the stratum lithology classification, soil texture and distance from the fault zone are analyzed from the stratum lithology data and soil type data, and geological factors and soil factors are constructed. For example, when the shale area has low shear strength and is less than 500m from the fault zone, the probability of landslide susceptibility is greatly increased, which provides geological factors and soil factors for landslide susceptibility analysis.

[0087] S14: Analyze the road, building, and vegetation distribution maps based on the vegetation cover data and the human engineering activity data, determine the surface cover factor according to the vegetation distribution map, and calculate the distance between each grid cell in the target study area and the nearest road based on the road and building distribution map to form a human activity factor.

[0088] Specifically, the vegetation cover data and human engineering activity data were analyzed to obtain the distribution maps of roads, buildings and vegetation in the target study area. The surface cover factor in the area was determined based on the vegetation distribution map. The road distribution map and building distribution map were used to calculate the distance between each grid unit in the target study area and the nearest road as the human activity factor.

[0089] In one embodiment, if Figure 3As shown, in step S20, the landslide susceptibility results of the target study area are generated according to the landslide susceptibility evaluation factors and their weights, and the landslide prediction area is determined based on the landslide susceptibility results, which specifically includes:

[0090] S21: The weight coefficients of each landslide susceptibility evaluation factor are assigned using the hierarchical analysis method, and the landslide susceptibility evaluation factors are normalized and weighted superimposed to calculate the landslide susceptibility results of each grid unit in the target study area.

[0091] Specifically, the weight coefficients of landslide susceptibility evaluation factors are allocated by the hierarchical analysis method to avoid the subjective bias of traditional methods and make the weight distribution of landslide susceptibility evaluation factors more in line with actual geological conditions. The landslide susceptibility evaluation factors are normalized and weighted superimposed, and the multi-source factors are integrated into the same landslide susceptibility index. Based on the normalized weighted superposition of the landslide susceptibility factors, the landslide susceptibility results of each grid unit in the target study area are calculated:

[0092]

[0093] Where a represents the weight coefficient, f represents the evaluation factor of landslide susceptibility, and n represents the number of evaluation factors.

[0094] S22: Dividing the landslide-prone areas into different levels based on the landslide susceptibility results of each grid unit to determine the landslide prediction area.

[0095] Specifically, the target study area is divided into different levels of landslide-prone areas according to the landslide susceptibility results of each grid unit, such as high-susceptibility areas (F>0.7), medium-susceptibility areas (F=0.4-0.7), and low-susceptibility areas (F<0.4). The landslide prediction areas of different levels are determined within the target study area. The landslide prediction area refers to the area where further early warning analysis of rainfall-type landslides in the area is carried out, realizing the spatial positioning of the landslide prediction area, which is conducive to focusing monitoring resources on high-risk areas and improving the efficiency of landslide early warning.

[0096] In one embodiment, if Figure 4 As shown, in step S30, historical landslide disaster data and real-time rainfall data of the landslide prediction area are obtained, effective rainfall is calculated in combination with the rock and soil permeability coefficient, and landslide critical curves under different geological lithologies are dynamically fitted based on the effective rainfall, specifically including:

[0097] S31: fitting an initial critical curve based on the historical landslide disaster data, and obtaining initial critical rainfall parameters according to the initial critical curve.

[0098] Specifically, the ID threshold model was used to analyze the critical threshold using historical landslide disaster data. Taking the day of the landslide disaster as the starting point, the continuous rainfall duration before the landslide was used as the continuous rainfall duration. Combined with the effective rainfall intensity at the time of the landslide disaster, the initial landslide critical curve was fitted to establish a benchmark relationship between rainfall intensity and rainfall duration:

[0099] I=c+α·D β ;

[0100] Where I is the effective rainfall intensity, D is the rainfall duration, α and β are statistical parameters, and c ≥ 0, which is a parameter statistically calculated from historical landslide disaster data.

[0101] S32: Determine the permeability coefficient of the rock and soil mass according to the lithology classification in the landslide prediction area, and determine the saturation state of the rock and soil mass based on the permeability coefficient of the rock and soil mass and real-time rainfall data.

[0102] Specifically, by classifying the strata and lithology within the landslide prediction area, we determined differentiated rock and soil permeability parameters. For example, the permeability parameter for clay is 0.8, and the permeability parameter for sand is 0.9. Using these rock and soil permeability parameters and real-time rainfall data in the area, we quantified the rock and soil saturation state and the cumulative permeability effect of previous rainfall in the area, thereby improving the accuracy of rainfall-induced landslide prediction analysis.

[0103]

[0104] Among them, S t is the rock and soil saturation at time t, k is the permeability coefficient, R i is the rainfall on the i-th day, and λ is the attenuation coefficient.

[0105] S33: adjusting the initial critical rainfall parameter in real time according to the saturation state of the rock and soil mass, generating landslide critical rainfall thresholds under different geological lithologies based on the adjusted critical rainfall parameter, and generating a landslide critical curve according to the landslide critical rainfall threshold.

[0106] Specifically, the initial critical rainfall parameters are dynamically adjusted using the saturated state of the rock and soil mass, and a critical rainfall threshold for landslides is generated. Based on the critical rainfall threshold for landslides, a corresponding critical landslide curve is generated to adapt to different strata and lithologies, thereby improving the accuracy and reliability of rainfall-induced landslide warnings.

[0107] In one embodiment, if Figure 5 As shown, in step S40, critical rainfall parameters are obtained based on the landslide critical curve, and the probability of rainfall-induced landslide in the landslide prediction area is determined according to the critical rainfall parameters, which specifically includes:

[0108] S41: Calculating critical rainfall parameters according to the landslide critical curve to construct a rainfall-type landslide dataset.

[0109] S42: Outputting a rainfall-type landslide occurrence probability result in the landslide prediction area by using a random forest algorithm based on the rainfall-type landslide dataset and combining the terrain parameters and terrain humidity index of the landslide prediction area.

[0110] Specifically, all critical rainfall parameters are counted according to the landslide critical curve and integrated to form a rainfall-type landslide data set. The random forest algorithm is used, combined with terrain parameters and terrain humidity index, to construct a probabilistic landslide warning model, output the probability results of rainfall-type landslides, and realize the landslide warning prediction and analysis function. Through dynamic adaptation of geological parameters and multi-factor probability modeling, the accuracy and reliability of rainfall-type landslide warnings are significantly improved.

[0111] In one embodiment, if Figure 6 As shown, in step S50, based on the landslide susceptibility result and the rainfall-induced landslide probability result, a gridded hazard value is generated, and a landslide warning signal is generated according to the gridded hazard value, specifically including:

[0112] S51: Multiply the landslide susceptibility result and the rainfall-induced landslide occurrence probability result of each grid cell in the landslide prediction area to obtain the gridded hazard value.

[0113] Specifically, the landslide susceptibility result of each grid unit is multiplied by the probability of rainfall-type landslide to obtain the gridded hazard value: R = P × F, where R represents the gridded hazard value, P is the probability of rainfall-type landslide, and F is the landslide susceptibility result. This achieves a two-way coupling of static geological conditions and dynamic rainfall processes, accurately quantifies the comprehensive risk, avoids misjudgment caused by a single indicator, and reduces the false alarm rate of landslide warnings.

[0114] S52: Divide the landslide warning signals into different levels according to the gridded hazard values, and merge adjacent grid cells based on the landslide warning signals of the same level to form a landslide warning area.

[0115] Specifically, five different levels of landslide warning signals are divided according to the gridded hazard values: extremely low (0.0-0.2), low (0.2-0.4), medium (0.4-0.6), high (0.6-0.8) and extremely high (0.8-1.0), and adjacent grid units of the same level of warning are merged to form a continuous landslide warning area. Through hazard fusion and spatial warning, the accuracy of landslide warning and emergency response efficiency have been significantly improved.

[0116] In one embodiment, if Figure 7 As shown, after step S50, that is, after generating a gridded hazard value based on the landslide susceptibility result and the rainfall-type landslide occurrence probability result, and generating a landslide warning signal according to the gridded hazard value, the rainfall-type landslide critical warning method further includes:

[0117] S60: collecting landslide sign data reported by the public in real time, and performing data preprocessing on the landslide sign data to obtain valid data.

[0118] Specifically, a mobile application is used to receive landslide sign data reported by the public. The landslide sign data includes a description of landslide precursor phenomena, geographic location, timestamp and multimedia evidence. The landslide sign data is preprocessed to obtain valid data, including GPS positioning to verify whether the reported location is within the landslide prediction area. The uploaded multimedia evidence is analyzed using an image recognition algorithm to identify ground cracks, vegetation tilt or surface displacement characteristics, and compared with real-time sensor data. If the soil moisture or displacement monitoring values ​​in the area are consistent with the reported phenomena, they are marked as valid data. Combined with the public data, the monitoring blind spots are filled, significantly improving the accuracy and real-time performance of landslide warnings in complex terrain.

[0119] S70: Based on the Bayesian network model, the valid data and the gridded hazard value are integrated to obtain a modified landslide warning signal, an emergency response signal is triggered according to the modified landslide warning signal, and a targeted warning notification is sent to the target area.

[0120] Specifically, the effective data and gridded hazard values ​​are fused using the Bayesian network model to obtain a revised landslide warning signal. When the revised warning level reaches "extremely high", the emergency response signal is triggered and a targeted warning notification is sent to the target area.

[0121] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0122] In one embodiment, a rainfall-induced landslide critical warning system is provided, which corresponds one-to-one with the rainfall-induced landslide critical warning method in the above embodiment. Figure 8 As shown in Figure 1, the rainfall-induced landslide critical warning system includes a multi-source data processing module, a landslide susceptibility analysis module, a critical curve generation module, a landslide probability prediction module, and a landslide warning signal generation module. The functional modules are described in detail as follows:

[0123] A multi-source data processing module is used to obtain multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data and human engineering activity data, and perform grid processing on the multi-source geographic data to generate gridded data;

[0124] a landslide susceptibility analysis module, configured to determine a landslide susceptibility evaluation factor based on the gridded data, generate a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determine a landslide prediction area based on the landslide susceptibility result;

[0125] a critical curve generation module, configured to obtain historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculate effective rainfall based on the rock and soil permeability coefficient, and dynamically fit landslide critical curves under different geological lithologies according to the effective rainfall;

[0126] A landslide probability prediction module is used to obtain a critical rainfall parameter based on the landslide critical curve, and determine a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter;

[0127] The landslide warning signal generating module is used to generate a gridded hazard value based on the landslide susceptibility result and the rainfall-type landslide occurrence probability result, and generate a landslide warning signal according to the gridded hazard value.

[0128] The specific definitions of the rainfall-induced landslide critical warning system can be found in the definitions of the rainfall-induced landslide critical warning method above and will not be further elaborated here. Each module in the aforementioned rainfall-induced landslide critical warning system can be implemented in whole or in part via software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor within an electronic device in hardware form, or stored in memory within the electronic device in software form, allowing the processor to call and execute the corresponding operations of each module.

[0129] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 9 As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a database. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a critical early warning method for rainfall-type landslides is implemented.

[0130] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0131] Acquire multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data, and human engineering activity data, and perform gridding processing on the multi-source geographic data to generate gridded data;

[0132] determining a landslide susceptibility evaluation factor based on the gridded data, generating a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determining a landslide prediction area based on the landslide susceptibility result;

[0133] Acquiring historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculating effective rainfall based on rock and soil permeability coefficient, and dynamically fitting landslide critical curves under different geological lithologies according to the effective rainfall;

[0134] Acquiring a critical rainfall parameter based on the landslide critical curve, and determining a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter;

[0135] Based on the landslide susceptibility results and the rainfall-type landslide occurrence probability results, a gridded hazard value is generated, and a landslide warning signal is generated according to the gridded hazard value.

[0136] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0137] Acquire multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data, and human engineering activity data, and perform gridding processing on the multi-source geographic data to generate gridded data;

[0138] determining a landslide susceptibility evaluation factor based on the gridded data, generating a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determining a landslide prediction area based on the landslide susceptibility result;

[0139] Acquiring historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculating effective rainfall based on rock and soil permeability coefficient, and dynamically fitting landslide critical curves under different geological lithologies according to the effective rainfall;

[0140] Acquiring a critical rainfall parameter based on the landslide critical curve, and determining a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter;

[0141] Based on the landslide susceptibility results and the rainfall-type landslide occurrence probability results, a gridded hazard value is generated, and a landslide warning signal is generated according to the gridded hazard value.

[0142] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0143] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0144] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A critical early warning method for rainfall-induced landslides, characterized in that: The critical early warning method for rainfall-induced landslides comprises the following steps: Acquire multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data, and human engineering activity data, and perform gridding processing on the multi-source geographic data to generate gridded data; determining a landslide susceptibility evaluation factor based on the gridded data, generating a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determining a landslide prediction area based on the landslide susceptibility result; Acquiring historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculating effective rainfall based on rock and soil permeability coefficient, and dynamically fitting landslide critical curves under different geological lithologies according to the effective rainfall; Acquiring a critical rainfall parameter based on the landslide critical curve, and determining a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter; Based on the landslide susceptibility results and the rainfall-type landslide occurrence probability results, a gridded hazard value is generated, and a landslide warning signal is generated according to the gridded hazard value.

2. A critical early warning method for rainfall-induced landslide according to claim 1, characterized in that: The landslide susceptibility evaluation factors include rainfall factors, topographic factors, hydrological environment factors, geological factors, surface cover factors, soil factors and human activity factors. The landslide susceptibility evaluation factors determined based on the gridded data specifically include: Converting the rainfall data into a continuous gridded rainfall layer through spatial interpolation to form a rainfall factor; Input the topographic data into a preset DEM model, extract the topographic parameters and topographic humidity index of the target study area, generate topographic factors based on the topographic parameters, and determine the hydrological environment factors based on the topographic humidity index; Integrate stratum lithology data and soil type data to analyze stratum lithology classification, soil texture, and distance from the fault zone to form geological factors and soil factors; Based on the vegetation cover data and human engineering activity data, the road, building and vegetation distribution maps are analyzed, the surface cover factor is determined according to the vegetation distribution map, and the distance from each grid cell in the target study area to the nearest road is calculated based on the road and building distribution map to form the human activity factor.

3. A critical early warning method for rainfall-induced landslide according to claim 1, characterized in that: Generating a landslide susceptibility result of a target study area according to the landslide susceptibility evaluation factors and their weights, and determining a landslide prediction area based on the landslide susceptibility result, specifically includes: The weight coefficients of each landslide susceptibility evaluation factor were assigned using the analytic hierarchy process, and the landslide susceptibility evaluation factors were normalized and weighted superimposed to calculate the landslide susceptibility results of each grid cell in the target study area. Based on the landslide susceptibility results of each grid unit, different levels of landslide prone areas are divided to determine the landslide prediction area.

4. A critical early warning method for rainfall-induced landslide according to claim 1, characterized in that: The method of obtaining historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculating effective rainfall based on rock and soil permeability coefficient, and dynamically fitting landslide critical curves under different geological lithologies according to the effective rainfall specifically includes: fitting an initial critical curve based on the historical landslide disaster data, and obtaining an initial critical rainfall parameter according to the initial critical curve; Determining the permeability coefficient of the rock and soil mass according to the lithology classification of the strata in the landslide prediction area, and determining the saturation state of the rock and soil mass based on the permeability coefficient of the rock and soil mass and real-time rainfall data; The initial critical rainfall parameter is adjusted in real time according to the saturation state of the rock and soil mass, the landslide critical rainfall threshold value under different geological lithologies is generated based on the adjusted critical rainfall parameter, and the landslide critical curve is generated according to the landslide critical rainfall threshold value.

5. The critical early warning method for rainfall-induced landslide according to claim 1, characterized in that: The step of obtaining a critical rainfall parameter based on the landslide critical curve and determining a rainfall-induced landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter specifically includes: According to the landslide critical curve, critical rainfall parameters are calculated to construct a rainfall landslide data set; Based on the rainfall-type landslide dataset, a random forest algorithm is used to combine the terrain parameters and terrain humidity index of the landslide prediction area to output the probability result of rainfall-type landslide occurrence in the landslide prediction area.

6. A critical early warning method for rainfall-induced landslide according to claim 1, characterized in that: Generating a gridded hazard value based on the landslide susceptibility result and the rainfall-induced landslide occurrence probability result, and generating a landslide warning signal according to the gridded hazard value specifically includes: The landslide susceptibility result and the rainfall-induced landslide probability result of each grid cell in the landslide prediction area are multiplied to obtain the gridded hazard value; Different levels of landslide warning signals are divided according to the gridded hazard values. Based on the landslide warning signals of the same level, adjacent grid units are merged to form a landslide warning area.

7. A critical early warning method for rainfall-induced landslide according to claim 1, characterized in that: After generating a gridded hazard value based on the landslide susceptibility result and the rainfall-type landslide occurrence probability result, and generating a landslide warning signal according to the gridded hazard value, the rainfall-type landslide critical warning method further includes: Collect landslide sign data reported by the public in real time, and pre-process the landslide sign data to obtain valid data; Based on the Bayesian network model, the effective data and the gridded hazard value are fused to dynamically correct the landslide warning signal, trigger an emergency response signal according to the corrected landslide warning signal, and send a targeted warning notification to the target area.

8. A rainfall-induced landslide critical warning system, characterized in that: The rainfall-induced landslide critical early warning system includes: A multi-source data processing module is used to obtain multi-source geographic data of the target study area, the multi-source geographic data including rainfall data, topography data, stratigraphic lithology data, soil type data, vegetation cover data and human engineering activity data, and perform grid processing on the multi-source geographic data to generate gridded data; a landslide susceptibility analysis module, configured to determine a landslide susceptibility evaluation factor based on the gridded data, generate a landslide susceptibility result for a target study area according to the landslide susceptibility evaluation factor and its weight, and determine a landslide prediction area based on the landslide susceptibility result; a critical curve generation module, configured to obtain historical landslide disaster data and real-time rainfall data in the landslide prediction area, calculate effective rainfall based on the rock and soil permeability coefficient, and dynamically fit landslide critical curves under different geological lithologies according to the effective rainfall; A landslide probability prediction module is used to obtain a critical rainfall parameter based on the landslide critical curve, and determine a rainfall-type landslide occurrence probability result in the landslide prediction area according to the critical rainfall parameter; The landslide warning signal generating module is used to generate a gridded hazard value based on the landslide susceptibility result and the rainfall-type landslide occurrence probability result, and generate a landslide warning signal according to the gridded hazard value.

9. A rainfall-induced landslide critical warning system according to claim 8, characterized in that: The landslide probability prediction module includes: An effective rainfall generation module is used to determine the rock and soil permeability coefficient according to the stratum lithology classification in the landslide prediction area, and obtain the effective rainfall in the effective landslide prediction area based on the rock and soil permeability coefficient and rainfall data; Landslide critical curve generation module, used to fit landslide critical curves of different strata and lithologies based on historical landslide hazard data and effective rainfall; The landslide occurrence probability generation module is used to fit the landslide critical curves of different strata and lithologies based on historical landslide disaster data and effective rainfall.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the critical early warning method for rainfall-induced landslide as described in any one of claims 1 to 7 are implemented.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the critical early warning method for rainfall-induced landslides as claimed in any one of claims 1 to 7 are implemented.

Images