Rainfall mass occurrence landslide risk assessment method and device, and computer equipment

Abstract

The invention relates to a rainfall mass occurrence landslide risk assessment method and device and computer equipment. The method comprises the following steps: acquiring historical rainfall group occurrence landslide data of a historical heavy rainfall event, and constructing landslide sample data; based on the landslide attribute parameters and the rainfall mass-texting landslide data distribution information of the landslide sample data, analyzing to obtain landslide development characteristics; according to landslide geographic features and landslide geometric features, analyzing a landslide generation background rule by adopting landslide sample data and a plurality of candidate landslide influence indexes, and establishing a landslide risk evaluation index system; and performing correlation analysis on the plurality of candidate landslide influence indexes to determine a target landslide influence index, and combining the target landslide influence index and the landslide risk evaluation index system to obtain a landslide risk evaluation model constructed based on an automatic machine learning framework. By adopting the method, the risk assessment efficiency of the rainfall group landslide can be improved, and the risk assessment precision of the rainfall group landslide is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for assessing the hazard of landslides caused by rainfall clusters. Background Art

[0002] In the field of geological disaster prevention and control, landslide disasters induced by rainfall are an issue that needs to be paid special attention to. At present, qualitative or quantitative methods are usually used to evaluate the landslide hazard.

[0003] Among the related technologies, the traditional qualitative method relies on the experience and judgment of experts and has subjective errors. The traditional quantitative method is to analyze the landslide mechanism through physical models to predict landslides, but it requires a large number of rock and soil parameters as model input, which limits its application in large-scale areas. Moreover, as the model becomes more complex in structure and technology, the professional and technical background requirements for users are getting higher and higher, which affects the efficiency of rainfall-induced landslide hazard assessment and results in poor assessment results. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for rainfall-induced landslide hazard assessment that can improve the efficiency and effectiveness of rainfall-induced landslide hazard assessment in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for assessing the hazard of landslides caused by rainfall clusters, comprising:

[0006] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0007] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0008] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0009] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0010] In one embodiment, the step of obtaining historical rainfall group landslide data of historical heavy rainfall events and constructing landslide sample data includes:

[0011] According to the satellite images of the historical heavy rainfall events, the historical rainfall cluster landslide data are obtained;

[0012] By performing data verification and data supplementation processing on the historical rainfall-induced landslide data, landslide sample data including the distribution of rainfall-induced landslide data are obtained.

[0013] In one embodiment, the analyzing of the landslide attribute parameters and the distribution information of the landslide data caused by rainfall clusters based on the landslide sample data to obtain the landslide development characteristics includes:

[0014] Based on the distribution information of rainfall-induced landslide data of the landslide sample data, the distribution pattern of rainfall-induced landslide data in geographic space is obtained, and landslide density parameters and landslide geometric parameters are determined as the landslide attribute parameters;

[0015] The landslide fluidity of the landslide sample data is analyzed according to the landslide attribute parameters to obtain the landslide geographical features and the landslide geometric features as the landslide development features.

[0016] In one embodiment, the landslide hazard evaluation index system is established by analyzing the landslide generation background law based on the landslide geographical features and the landslide geometric features using the landslide sample data and a plurality of candidate landslide impact indicators, including:

[0017] Acquire a plurality of candidate landslide impact indicators associated with the regional range of the historical heavy rainfall event;

[0018] In combination with the geographical features of the landslide and the geometric features of the landslide, the landslide sample data and the multiple candidate landslide impact indicators are analyzed to determine the spatial distribution law of the landslide and the landslide disaster-prone environment;

[0019] The landslide hazard assessment index system is constructed according to the landslide spatial distribution law, the landslide disaster-prone environment, and the multiple candidate landslide impact indicators.

[0020] In one embodiment, the target landslide impact index is determined by performing correlation analysis on the multiple candidate landslide impact indicators, and the landslide hazard assessment model based on the automatic machine learning framework is obtained by combining the target landslide impact index and the landslide hazard assessment index system, including:

[0021] By performing correlation analysis on the plurality of candidate landslide impact indicators, the selected candidate landslide impact indicators are used as the target landslide impact indicators;

[0022] In the landslide sample data, landslide samples and non-landslide samples are selected according to the target landslide impact index as training sample data;

[0023] Combining the target landslide impact index and the landslide hazard evaluation index system, an initial assessment model is constructed using an automatic machine learning framework;

[0024] The initial assessment model is trained based on the training sample data to obtain the landslide hazard assessment model.

[0025] In one embodiment, the method further comprises:

[0026] Using preset model evaluation indicators to perform model performance testing on the landslide hazard assessment model;

[0027] Based on the landslide hazard assessment model that has passed the test, a rainfall cluster landslide hazard assessment is performed on the historical heavy rainfall event to obtain a landslide hazard assessment result;

[0028] According to the landslide hazard assessment result, a rainfall cluster landslide hazard warning image of the historical heavy rainfall event is displayed;

[0029] The model evaluation indicators include any one or more of the following:

[0030] Area under the curve indicator, accuracy indicator, precision indicator, and recall rate indicator.

[0031] In a second aspect, the present application also provides a device for assessing the hazard of landslides caused by rainfall, comprising:

[0032] The landslide sample data construction module is used to obtain the historical rainfall group landslide data of historical heavy rainfall events and construct the landslide sample data;

[0033] A landslide development feature acquisition module is used to analyze the landslide attribute parameters and the rainfall group landslide data distribution information of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include landslide geographical characteristics and landslide geometric state characteristics;

[0034] A landslide evaluation system establishment module is used to analyze the landslide generation background law based on the landslide geographical characteristics and the landslide geometric characteristics, using the landslide sample data and a plurality of candidate landslide impact indicators, and establish a landslide hazard evaluation index system;

[0035] The landslide hazard assessment model obtaining module is used to determine the target landslide impact index by performing correlation analysis on the multiple candidate landslide impact indicators, and to obtain a landslide hazard assessment model constructed based on an automatic machine learning framework by combining the target landslide impact index and the landslide hazard evaluation index system; the landslide hazard assessment model is used to perform rainfall cluster landslide hazard assessment on heavy rainfall events.

[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0038] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0039] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0040] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0042] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0043] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0044] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0045] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0046] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0047] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0048] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0049] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0050] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0051] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for assessing the hazard of rainfall-induced landslides obtain historical rainfall-induced landslide data of historical heavy rainfall events, construct landslide sample data, analyze the landslide development characteristics based on landslide attribute parameters and the rainfall-induced landslide data distribution information of the landslide sample data, and obtain the landslide development characteristics, which include landslide geographical characteristics and landslide geometric state characteristics. Then, according to the landslide geographical characteristics and landslide geometric characteristics, the landslide sample data and multiple candidate landslide impact indicators are used to analyze the background law of landslide generation, and a landslide hazard assessment index system is established. Then, by performing correlation analysis on multiple candidate landslide impact indicators, the target landslide impact indicator is determined. Combined with the target landslide impact indicator and the landslide hazard assessment index system, a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained. The landslide hazard assessment model is used to perform rainfall-induced landslide hazard assessment on heavy rainfall events, realizes the optimization of rainfall-induced landslide hazard assessment, can improve the efficiency of rainfall-induced landslide hazard assessment, and effectively improves the accuracy of rainfall-induced landslide hazard assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a flow chart of a method for assessing the hazard of landslides caused by rainfall clusters in one embodiment;

[0054] Figure 2 A schematic diagram of a rainfall-induced landslide hazard assessment process based on an automatic machine learning framework in one embodiment;

[0055] Figure 3 A schematic flow chart of a method for assessing the hazard of landslides caused by rainfall clusters in another embodiment;

[0056] Figure 4 It is a structural block diagram of a device for assessing the risk of landslides caused by rainfall in an embodiment;

[0057] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] In an exemplary embodiment, Figure 1 As shown, a method for assessing the risk of landslides caused by rainfall is provided. This embodiment uses the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 101 to 104. Among them:

[0060] Step 101, obtaining historical rainfall group landslide data of historical heavy rainfall events, and constructing landslide sample data.

[0061] In practical applications, high-resolution satellite images of historical heavy rainfall events can be obtained for data extraction, and the extracted landslide data can be verified, supplemented and other data preprocessing to obtain landslide sample data containing the distribution of rainfall cluster landslide data.

[0062] Step 102, analyzing the landslide attribute parameters and the rainfall cluster landslide data distribution information of the landslide sample data to obtain the landslide development characteristics.

[0063] As an example, landslide development characteristics may include landslide geographical characteristics and landslide geometric state characteristics.

[0064] In the specific implementation, landslide attribute parameters such as landslide density, landslide length, landslide width, and landslide height can be used to determine the geographical characteristics and geometric characteristics of rainfall-induced landslides, and obtain landslide development characteristics that characterize the laws of landslide development.

[0065] Step 103, according to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation, and establish a landslide hazard evaluation index system.

[0066] For example, data on internal and external influencing factors of landslides in the area of ​​historical heavy rainfall events can be collected to determine multiple candidate landslide impact indicators. Then, based on the geographical characteristics and geometric characteristics of landslides, landslide sample data and multiple candidate landslide impact indicators can be used to analyze the background laws of landslide occurrence. For example, the landslide hazard-prone environment and the spatial distribution laws of landslides can be analyzed to determine the potential conditions for landslide occurrence and their distribution characteristics in geographical space, and to establish a landslide hazard evaluation index system.

[0067] Step 104, determining a target landslide impact index by performing a correlation analysis on the multiple candidate landslide impact indexes, and obtaining a landslide hazard assessment model based on an automatic machine learning framework by combining the target landslide impact index and the landslide hazard assessment index system.

[0068] Among them, the landslide hazard assessment model can be used to assess the hazard of landslides caused by heavy rainfall events.

[0069] In one example, a correlation test can be performed on multiple candidate landslide impact indicators to screen out the target landslide impact indicator, and then the target landslide impact indicator and the landslide hazard evaluation index system can be combined to establish a model based on the automatic machine learning framework and perform model training to obtain a landslide hazard assessment model. Based on the heavy rainfall scenario, by integrating the data of rainfall-induced landslides and the internal and external factors affecting landslides, the integrated model in the automatic machine learning framework is used to build the model, realizing the hazard evaluation of rainfall-induced landslides.

[0070] In another example, with the rapid development of artificial intelligence, machine learning can be applied to solve nonlinear relationship problems, especially in integrated learning models. Machine learning methods can learn and discover hidden and unknown patterns in databases with high precision, and can process and analyze large amounts of complex data, such as rainfall, terrain, vegetation and other influencing factors, and have strong adaptability and flexibility. The automated machine learning framework can well alleviate the difficulties that researchers may face when using machine learning, and the use of the automated machine learning framework can broaden the scope of application of machine learning models and reduce excessive interaction with users.

[0071] Compared with the traditional method, the technical solution of this embodiment extracts rainfall-induced landslide data based on high-resolution satellite images, combines landslide density, geometric parameters, etc. to reveal the geographical development characteristics and geometric characteristics of landslides, and conducts in-depth spatial distribution law analysis of landslides under the conditions of collecting internal and external influencing factors of landslides, establishes a landslide hazard evaluation index system, and then can carry out rainfall-induced landslide hazard evaluation based on the automatic machine learning framework. It can effectively solve the shortcomings of traditional landslide hazard evaluation methods in terms of efficiency and accuracy, provide support for the evaluation of landslide hazard in groups under heavy rainfall scenarios, and meet the needs of geological disaster assessment and prevention in areas with frequent rainfall.

[0072] In the above-mentioned rainfall-induced landslide hazard assessment method, historical rainfall-induced landslide data of historical heavy rainfall events are obtained to construct landslide sample data, and the landslide attribute parameters and the rainfall-induced landslide data distribution information of the landslide sample data are analyzed to obtain the landslide development characteristics, and then according to the landslide geographical characteristics and landslide geometric characteristics, the landslide sample data and multiple candidate landslide impact indicators are used to analyze the landslide generation background law, and a landslide hazard assessment index system is established, and then by performing correlation analysis on multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and the target landslide impact indicator and the landslide hazard assessment index system are combined to obtain a landslide hazard assessment model constructed based on an automatic machine learning framework, which realizes the optimization of rainfall-induced landslide hazard assessment, can improve the efficiency of rainfall-induced landslide hazard assessment, and effectively improves the accuracy of rainfall-induced landslide hazard assessment.

[0073] In an exemplary embodiment, the acquisition of historical rainfall group landslide data of historical heavy rainfall events and the construction of landslide sample data may include the following steps:

[0074] The historical rainfall cluster landslide data are obtained based on the satellite images of the historical heavy rainfall event; and landslide sample data including the distribution of rainfall cluster landslide data are obtained by performing data verification and data supplementation on the historical rainfall cluster landslide data.

[0075] In practical applications, high-resolution satellite images within a preset time range can be obtained based on the date of occurrence of historical heavy rainfall events. For example, images one month before and after the date of occurrence can be obtained. Figure 2 As shown in the figure, historical rainfall-induced landslide data can be extracted through visual interpretation by human-computer interaction. Then, by verifying and supplementing the high-resolution satellite images in the area of ​​historical heavy rainfall events, objective and detailed rainfall-induced landslide data distribution can be obtained, and a rainfall-induced landslide database (i.e., landslide sample data) can be constructed.

[0076] Alternatively, a visual interpretation method based on human-computer interaction can utilize the image features (such as hue, color, shape, size, shadow, texture, etc.) and spatial features (such as position and layout) of the image, combined with a variety of non-remote sensing information materials for comprehensive analysis and logical reasoning to extract data.

[0077] In an optional embodiment, for the verification and supplementation of data preprocessing process, historical rainfall-induced landslide data can be collected, such as meteorological data such as rainfall amount, rainfall intensity, rainfall duration, temperature, topographic data such as slope, slope aspect, altitude, geological data such as soil type, rock properties, vegetation coverage, historical landslide information such as location, scale, and occurrence time, and data cleaning is performed on the historical rainfall-induced landslide data, such as removing duplicate, erroneous or abnormal data records, and data conversion, such as normalization, is performed to facilitate further processing by the machine learning algorithm.

[0078] In an exemplary embodiment, the analyzing of the landslide attribute parameters and the distribution information of the rainfall-induced landslide data of the landslide sample data to obtain the landslide development characteristics may include the following steps:

[0079] Based on the distribution information of rainfall-induced landslide data of the landslide sample data, the distribution pattern of rainfall-induced landslide data in geographic space is obtained, and landslide density parameters and landslide geometric parameters are determined as the landslide attribute parameters; the landslide fluidity of the landslide sample data is analyzed according to the landslide attribute parameters, and the landslide geographical characteristics and the landslide geometric characteristics are obtained as the landslide development characteristics.

[0080] Specifically, Figure 2 As shown in the figure, GIS (Geographic Information System) tools and statistical methods can be used to obtain the distribution pattern of landslide sample data in geographic space, and can be characterized based on quantitative indicators of landslide point density and landslide surface density. Then, by statistically analyzing parameters such as landslide density, landslide length, landslide width, and landslide height (i.e., landslide density parameters and landslide geometric parameters), and using the equivalent friction coefficient to analyze the fluidity of the landslide, the landslide development law, that is, the landslide development characteristics, can be obtained.

[0081] In an exemplary embodiment, the analyzing the landslide generation background law based on the landslide geographical features and the landslide geometric features and using the landslide sample data and a plurality of candidate landslide impact indicators to establish a landslide hazard evaluation index system may include the following steps:

[0082] Acquire multiple candidate landslide impact indicators associated with the regional scope of the historical heavy rainfall event; analyze the landslide sample data and the multiple candidate landslide impact indicators in combination with the landslide geographical characteristics and the landslide geometric characteristics to determine the spatial distribution law of landslides and the landslide disaster-prone environment; construct the landslide hazard evaluation index system based on the spatial distribution law of landslides, the landslide disaster-prone environment, and the multiple candidate landslide impact indicators.

[0083] In practical applications, such as Figure 2 As shown in the figure, by collecting data on internal and external influencing factors of landslides and using correlation analysis, principal component analysis and other methods to screen out the influencing factors most closely related to landslides, multiple candidate landslide influencing indicators can be determined. Then, based on the spatial analysis function of GIS tools, the landslide sample data can be superimposed and analyzed with multiple candidate landslide influencing indicators to study and analyze the distribution law of rainfall-induced landslide disasters and the landslide disaster-pregnant environment, and then a landslide hazard evaluation index system containing multiple candidate landslide influencing indicators can be constructed.

[0084] For example, the landslide hazard assessment index system can include multiple influencing factors such as 5-day cumulative rainfall, elevation, slope, slope aspect, terrain moisture index, normalized vegetation index, stratum lithology, distance from water system, distance from road, and surface cover.

[0085] In an exemplary embodiment, by performing correlation analysis on the multiple candidate landslide impact indicators, determining the target landslide impact indicator, combining the target landslide impact indicator with the landslide hazard evaluation index system, and obtaining a landslide hazard assessment model based on an automatic machine learning framework, the following steps may be included:

[0086] By performing correlation analysis on the multiple candidate landslide impact indicators, the screened candidate landslide impact indicators are used as the target landslide impact indicators; in the landslide sample data, landslide samples and non-landslide samples are selected according to the target landslide impact indicators as training sample data; combining the target landslide impact indicators and the landslide hazard assessment index system, an initial assessment model is constructed using an automatic machine learning framework; the initial assessment model is trained based on the training sample data to obtain the landslide hazard assessment model.

[0087] In the specific implementation, Figure 2As shown, the Pearson correlation coefficient (an indicator used in statistics to measure the degree of linear correlation between two variables, which can reflect the strength and direction of the linear relationship between the two variables) can be used to perform correlation analysis on multiple candidate landslide impact indicators to screen out the target landslide impact indicator. Then, landslide samples and non-landslide samples can be selected based on a 1:1 ratio to obtain training sample data. Then, the target landslide impact indicator and the landslide hazard evaluation index system can be combined to build an initial evaluation model using the automatic machine learning framework AutoGluon, which can be trained based on the training sample data to obtain a landslide hazard assessment model.

[0088] In one example, the automatic machine learning framework can include multiple ensemble methods, such as random forests, gradient boosting trees, etc. Ensemble learning can improve the overall prediction performance by combining the prediction results of multiple base learners to build an ensemble model. In the automatic machine learning framework, one or more ensemble models can be selected for training. By adjusting hyperparameters and optimizing the model structure, the prediction accuracy and generalization ability of the model can be improved, and its performance can be evaluated by methods such as cross-validation.

[0089] In an exemplary embodiment, the following steps may also be included:

[0090] The preset model evaluation index is used to test the model performance of the landslide hazard assessment model; based on the landslide hazard assessment model that has passed the test, a rainfall-induced landslide hazard assessment is performed on the historical heavy rainfall event to obtain a landslide hazard assessment result; based on the landslide hazard assessment result, a rainfall-induced landslide hazard prompt image of the historical heavy rainfall event is displayed.

[0091] The model evaluation index may include any one or more of the following: area under the curve index, accuracy index, precision index, and recall index.

[0092] In practical applications, for landslide hazard assessment models, AUC (area under the curve, the area under the ROC curve, a model evaluation index), accuracy, precision, and recall (i.e., area under the curve index, accuracy index, precision index, and recall index) can be used to detect model performance; Figure 2 As shown, after the landslide hazard assessment model is established, the landslide hazard assessment of historical heavy rainfall events can be carried out based on the landslide hazard assessment model.

[0093] In one example, GIS tools can be used to visualize the landslide hazard assessment results output by the model on a map, such as Figure 2As shown, according to the landslide hazard assessment results, the natural break point method can be used to divide the landslide hazard levels (such as extremely low, low, medium, high, and extremely high levels), and a rainfall-induced landslide hazard level map (i.e., a rainfall-induced landslide hazard warning image) can be generated for display, such as displaying a rainfall-induced landslide hazard warning image for the geographical area corresponding to the historical heavy rainfall event.

[0094] In an exemplary embodiment, Figure 3 As shown, another flow chart of a method for assessing the hazard of landslides caused by rainfall clusters is provided. In this embodiment, the method comprises the following steps:

[0095] In step 301, historical rainfall cluster landslide data are obtained based on satellite images of historical heavy rainfall events, and landslide sample data containing the distribution of rainfall cluster landslide data are obtained by performing data verification and data supplementation on the historical rainfall cluster landslide data. In step 302, based on the distribution information of rainfall cluster landslide data of landslide sample data, the distribution pattern of rainfall cluster landslide data in geographic space is obtained, and landslide density parameters and landslide geometric parameters are determined as landslide attribute parameters. In step 303, the landslide mobility of landslide sample data is analyzed according to the landslide attribute parameters, and the landslide geographical characteristics and landslide geometric characteristics are obtained as landslide development characteristics. In step 304, multiple candidate landslide impact indicators associated with the regional scope of historical heavy rainfall events are obtained, and the landslide sample data and multiple candidate landslide impact indicators are analyzed in combination with the landslide geographical characteristics and landslide geometric characteristics to determine the spatial distribution law of landslides and the landslide disaster-pregnant environment. In step 305, a landslide hazard evaluation index system is constructed according to the spatial distribution law of landslides and the landslide disaster-prone environment, as well as multiple candidate landslide impact indicators. In step 306, by performing correlation analysis on multiple candidate landslide impact indicators, the selected candidate landslide impact indicators are used as target landslide impact indicators. In the landslide sample data, landslide samples and non-landslide samples are selected according to the target landslide impact indicators as training sample data. In step 307, in combination with the target landslide impact indicators and the landslide hazard evaluation index system, an initial evaluation model is constructed using an automatic machine learning framework, and the initial evaluation model is trained based on the training sample data to obtain a landslide hazard evaluation model. It should be noted that the specific limitations of the above steps can be found in the specific limitations of a method for assessing the hazard of a rainfall-induced landslide above, which will not be repeated here.

[0096] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0097] Based on the same inventive concept, the embodiment of the present application also provides a rainfall-induced landslide hazard assessment device for implementing the rainfall-induced landslide hazard assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more rainfall-induced landslide hazard assessment device embodiments provided below can refer to the limitations of the rainfall-induced landslide hazard assessment method above, and will not be repeated here.

[0098] In an exemplary embodiment, Figure 4 As shown, a device for assessing the hazard of landslides caused by rainfall clusters is provided, comprising:

[0099] The landslide sample data construction module 401 is used to obtain historical rainfall group landslide data of historical heavy rainfall events and construct landslide sample data;

[0100] The landslide development characteristic acquisition module 402 is used to analyze the landslide attribute parameters and the rainfall group landslide data distribution information of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0101] A landslide evaluation system establishment module 403 is used to analyze the landslide generation background law based on the landslide geographical features and the landslide geometric features, using the landslide sample data and a plurality of candidate landslide impact indicators, and establish a landslide hazard evaluation indicator system;

[0102] The landslide hazard assessment model obtaining module 404 is used to determine the target landslide impact index by performing correlation analysis on the multiple candidate landslide impact indicators, and to obtain a landslide hazard assessment model constructed based on an automatic machine learning framework by combining the target landslide impact index and the landslide hazard evaluation index system; the landslide hazard assessment model is used to perform rainfall cluster landslide hazard assessment on heavy rainfall events.

[0103] In one embodiment, the landslide sample data construction module 401 includes:

[0104] A data extraction submodule, for obtaining the historical rainfall-induced landslide data based on the satellite images of the historical heavy rainfall events;

[0105] The data processing submodule is used to obtain landslide sample data including the distribution of rainfall-induced landslide data by performing data verification and data supplementation on the historical rainfall-induced landslide data.

[0106] In one embodiment, the landslide development characteristic acquisition module 402 includes:

[0107] A landslide attribute parameter obtaining submodule is used to obtain the distribution pattern of rainfall-induced landslide data in geographic space based on the distribution information of rainfall-induced landslide data of the landslide sample data, and determine landslide density parameters and landslide geometric parameters as the landslide attribute parameters;

[0108] The feature analysis submodule is used to analyze the landslide fluidity of the landslide sample data according to the landslide attribute parameters, and obtain the landslide geographical features and the landslide geometric features as the landslide development features.

[0109] In one embodiment, the landslide assessment system establishment module 403 includes:

[0110] An impact index acquisition submodule is used to acquire a plurality of candidate landslide impact indicators associated with the regional scope of the historical heavy rainfall event;

[0111] An index analysis submodule is used to analyze the landslide sample data and the multiple candidate landslide impact indicators in combination with the landslide geographical features and the landslide geometric features to determine the spatial distribution law of landslides and the landslide disaster-prone environment;

[0112] The index system construction submodule is used to construct the landslide hazard evaluation index system according to the landslide spatial distribution law and the landslide disaster-prone environment, as well as the multiple candidate landslide impact indicators.

[0113] In one embodiment, the landslide hazard assessment model obtaining module 404 includes:

[0114] An indicator screening submodule, configured to perform correlation analysis on the plurality of candidate landslide impact indicators and use the screened candidate landslide impact indicators as the target landslide impact indicators;

[0115] A sample selection submodule, used to select landslide samples and non-landslide samples from the landslide sample data according to the target landslide impact index as training sample data;

[0116] A model building submodule, for combining the target landslide impact index and the landslide hazard evaluation index system, and using an automatic machine learning framework to build an initial evaluation model;

[0117] The model training submodule is used to train the initial assessment model based on the training sample data to obtain the landslide hazard assessment model.

[0118] In one embodiment, the apparatus further comprises:

[0119] A model performance detection module, used to perform model performance detection on the landslide hazard assessment model using preset model evaluation indicators;

[0120] A landslide hazard assessment module is used to perform a rainfall cluster landslide hazard assessment on the historical heavy rainfall event based on the landslide hazard assessment model that has passed the detection, and obtain a landslide hazard assessment result;

[0121] A landslide hazard warning image display module is used to display a landslide hazard warning image of a rainfall cluster of the historical heavy rainfall event according to the landslide hazard assessment result;

[0122] The model evaluation indicators include any one or more of the following:

[0123] Area under the curve indicator, accuracy indicator, precision indicator, and recall rate indicator.

[0124] Each module in the above-mentioned rainfall-induced landslide hazard assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0125] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for assessing the hazard of rain-induced landslides is implemented.

[0126] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0128] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0129] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0130] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0131] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0132] In one embodiment, when the processor executes the computer program, the processor also implements the steps of the method for assessing the hazard of landslides caused by rainfall clusters in other embodiments described above.

[0133] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0134] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0135] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0136] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0137] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0138] In one embodiment, when the computer program is executed by a processor, the steps of the method for assessing the hazard of landslides caused by rainfall clusters in other embodiments described above are also implemented.

[0139] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0140] Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data;

[0141] Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics;

[0142] According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system;

[0143] By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

[0144] In one embodiment, when the computer program is executed by a processor, the steps of the method for assessing the hazard of landslides caused by rainfall clusters in other embodiments described above are also implemented.

[0145] It should be noted that the collection, use and processing of relevant data involved in this application must comply with relevant regulations.

[0146] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and 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 the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0147] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0148] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for assessing the hazard of landslides caused by rainfall clusters, characterized in that: The method comprises: Obtain historical rainfall cluster landslide data of historical heavy rainfall events and construct landslide sample data; Analyze the landslide attribute parameters and the distribution information of the rainfall group landslide data of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include the landslide geographical characteristics and the landslide geometric state characteristics; According to the geographical features and geometric features of the landslide, the landslide sample data and a plurality of candidate landslide impact indicators are used to analyze the background law of landslide generation and establish a landslide hazard evaluation index system; By performing correlation analysis on the multiple candidate landslide impact indicators, the target landslide impact indicator is determined, and a landslide hazard assessment model constructed based on an automatic machine learning framework is obtained by combining the target landslide impact indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used to conduct rainfall cluster landslide hazard assessment for heavy rainfall events.

2. The method according to claim 1, characterized in that The acquisition of historical rainfall group landslide data of historical heavy rainfall events and construction of landslide sample data includes: According to the satellite images of the historical heavy rainfall events, the historical rainfall cluster landslide data are obtained; By performing data verification and data supplementation processing on the historical rainfall-induced landslide data, landslide sample data including the distribution of rainfall-induced landslide data are obtained.

3. The method according to claim 1, characterized in that The landslide attribute parameters and the rainfall group landslide data distribution information of the landslide sample data are analyzed to obtain the landslide development characteristics, including: Based on the distribution information of rainfall-induced landslide data of the landslide sample data, the distribution pattern of rainfall-induced landslide data in geographic space is obtained, and landslide density parameters and landslide geometric parameters are determined as the landslide attribute parameters; The landslide fluidity of the landslide sample data is analyzed according to the landslide attribute parameters to obtain the landslide geographical features and the landslide geometric features as the landslide development features.

4. The method according to claim 1, characterized in that: The method of analyzing the landslide generation background law based on the landslide geographical features and the landslide geometric features and using the landslide sample data and a plurality of candidate landslide impact indicators to establish a landslide hazard evaluation index system includes: Acquire a plurality of candidate landslide impact indicators associated with the regional range of the historical heavy rainfall event; In combination with the geographical features of the landslide and the geometric features of the landslide, the landslide sample data and the multiple candidate landslide impact indicators are analyzed to determine the spatial distribution law of the landslide and the landslide disaster-prone environment; The landslide hazard assessment index system is constructed according to the landslide spatial distribution law, the landslide disaster-prone environment, and the multiple candidate landslide impact indicators.

5. The method according to claim 1, characterized in that The method comprises: determining a target landslide impact index by performing correlation analysis on the plurality of candidate landslide impact indexes, and combining the target landslide impact index with the landslide hazard evaluation index system to obtain a landslide hazard evaluation model based on an automatic machine learning framework, including: By performing correlation analysis on the plurality of candidate landslide impact indicators, the selected candidate landslide impact indicators are used as the target landslide impact indicators; In the landslide sample data, landslide samples and non-landslide samples are selected according to the target landslide impact index as training sample data; Combining the target landslide impact index and the landslide hazard evaluation index system, an initial assessment model is constructed using an automatic machine learning framework; The initial assessment model is trained based on the training sample data to obtain the landslide hazard assessment model.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Using preset model evaluation indicators to perform model performance testing on the landslide hazard assessment model; Based on the landslide hazard assessment model that has passed the test, a rainfall cluster landslide hazard assessment is performed on the historical heavy rainfall event to obtain a landslide hazard assessment result; According to the landslide hazard assessment result, a rainfall cluster landslide hazard warning image of the historical heavy rainfall event is displayed; The model evaluation indicators include any one or more of the following: Area under the curve indicator, accuracy indicator, precision indicator, and recall rate indicator.

7. A device for assessing the hazard of landslides caused by rainfall, characterized in that: The device comprises: The landslide sample data construction module is used to obtain the historical rainfall group landslide data of historical heavy rainfall events and construct the landslide sample data; A landslide development feature acquisition module is used to analyze the landslide attribute parameters and the rainfall group landslide data distribution information of the landslide sample data to obtain the landslide development characteristics; the landslide development characteristics include landslide geographical characteristics and landslide geometric state characteristics; A landslide evaluation system establishment module is used to analyze the landslide generation background law based on the landslide geographical characteristics and the landslide geometric characteristics, using the landslide sample data and a plurality of candidate landslide impact indicators, and establish a landslide hazard evaluation index system; The landslide hazard assessment model obtaining module is used to determine the target landslide impact index by performing correlation analysis on the multiple candidate landslide impact indicators, and to obtain a landslide hazard assessment model constructed based on an automatic machine learning framework by combining the target landslide impact index and the landslide hazard evaluation index system; the landslide hazard assessment model is used to perform rainfall cluster landslide hazard assessment on heavy rainfall events.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images