Method and apparatus for assessing hazard of rainfall-induced landslide clusters, and computer device

Abstract

A method and apparatus for assessing the hazard of rainfall-induced landslide clusters, and a computer device. The method comprises: acquiring historical rainfall-induced landslide cluster data from past intense rainfall events to construct landslide sample data; performing analysis on the basis of landslide attribute parameters and rainfall-induced landslide cluster data distribution information of the landslide sample data to obtain landslide development characteristics; on the basis of landslide geographical features and geometric features, using the landslide sample data and a plurality of candidate landslide-influencing indexes to analyze underlying patterns of landslide occurrence, so as to establish a landslide hazard evaluation index system; and performing correlation analysis on the plurality of candidate landslide-influencing indexes to determine a target landslide-influencing index, and combining the target landslide-influencing index with the landslide hazard evaluation index system to obtain a landslide hazard assessment model constructed on the basis of an automated machine learning framework. The efficiency of rainfall-induced landslide cluster hazard assessment can be improved and the accuracy of rainfall-induced landslide cluster hazard assessment can be effectively enhanced.

Description

Rainfall group landslide hazard assessment method and device, computer equipment TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a rainfall group landslide hazard assessment method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] In the aspect of geological disaster prevention, rainfall-induced landslide disaster is a problem that needs to be focused on. At present, qualitative or quantitative methods are usually used for landslide hazard assessment.

[0003] In related technologies, the traditional qualitative method relies on the experience of experts, and there is subjective error. The traditional quantitative method is to analyze the landslide mechanism through a physical model to predict the landslide, but it needs a large number of rock and soil parameters as model input, which limits its application in large-scale areas. Moreover, with the complication of the model in structure and technology, the professional technical background requirements for the user are getting higher and higher, which affects the efficiency of rainfall group landslide hazard assessment and the assessment effect is not good. SUMMARY

[0004] Therefore, it is necessary to provide a rainfall group landslide hazard assessment method and device, computer equipment, computer readable storage medium and computer program product capable of improving the efficiency and effect of rainfall group landslide hazard assessment.

[0005] In a first aspect, the present application provides a rainfall group landslide hazard assessment method, comprising:

[0006] Obtaining historical rainfall group landslide data of historical heavy rainfall events, and constructing landslide sample data;

[0007] Analyzing the rainfall group landslide data distribution information based on the landslide attribute parameters and the landslide sample data, and obtaining landslide development characteristics; the landslide development characteristics include landslide geographical characteristics and landslide geometric state characteristics;

[0008] According to the landslide geographical characteristics and the landslide geometric characteristics, the landslide sample data and a plurality of candidate landslide influence indexes are used to analyze the landslide background rule, and a landslide hazard assessment index system is established;

[0009] Through correlation analysis on the plurality of candidate landslide influence indexes, a target landslide influence index is determined, and a landslide hazard assessment model based on an automatic machine learning framework is obtained by combining the target landslide influence index and the landslide hazard assessment index system; the landslide hazard assessment model is used for rainfall group landslide hazard assessment of a heavy rainfall event.

[0010] In one of the embodiments, the historical rainfall group landslide data of the historical heavy rainfall event is obtained, and landslide sample data is constructed, including:

[0011] According to the satellite image of the historical heavy rainfall event, the historical rainfall group landslide data is obtained;

[0012] Through data checking and data supplementing processing on the historical rainfall group landslide data, landslide sample data containing rainfall group landslide data distribution is obtained.

[0013] In one of the embodiments, the rainfall group landslide data distribution information based on the landslide attribute parameters and the landslide sample data is analyzed to obtain landslide development characteristics, including:

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

[0015] According to the landslide attribute parameters, the landslide flowability of the landslide sample data is analyzed to obtain the landslide geographical characteristics and the landslide geometric characteristics as the landslide development characteristics.

[0016] In one of the embodiments, according to the landslide geographical characteristics and the landslide geometric characteristics, the landslide sample data and a plurality of candidate landslide influence indexes are used to analyze landslide generation background rules, and a landslide hazard evaluation index system is established, including:

[0017] A plurality of candidate landslide influence indexes associated with the regional range of the historical heavy rainfall event are obtained;

[0018] Combining the landslide geographical characteristics and the landslide geometric characteristics, the landslide sample data and the plurality of candidate landslide influence indexes are analyzed to determine landslide spatial distribution rules and landslide disaster environment;

[0019] According to the landslide spatial distribution rules and the landslide disaster environment, and the plurality of candidate landslide influence indexes, the landslide hazard evaluation index system is constructed.

[0020] In one of the embodiments, by performing correlation analysis on the plurality of candidate landslide influence indexes, a target landslide influence index is determined, and the target landslide influence index and the landslide hazard evaluation index system are combined to obtain a landslide hazard assessment model constructed based on an automatic machine learning framework, including:

[0021] Through correlation analysis on the plurality of candidate landslide influence indexes, the selected candidate landslide influence index is taken as the target landslide influence index;

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

[0023] In combination with the target landslide influence index and the landslide danger evaluation index system, an initial evaluation model is constructed by using an automatic machine learning framework;

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

[0025] In one of the embodiments, the method further comprises:

[0026] The landslide danger evaluation model is subjected to model performance detection by using a preset model evaluation index;

[0027] Based on the landslide danger evaluation model that passes the detection, the rainfall group landslide danger of the historical heavy rainfall event is evaluated to obtain a landslide danger evaluation result;

[0028] According to the landslide danger evaluation result, a rainfall group landslide danger prompt image of the historical heavy rainfall event is displayed;

[0029] The model evaluation index includes any one or more of the following:

[0030] The area under the curve index, the accuracy index, the precision index, and the recall index.

[0031] In a second aspect, the present application further provides a rainfall group landslide danger evaluation device, comprising:

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

[0033] A landslide development feature obtaining module is configured to analyze landslide attribute parameters and rainfall group landslide data distribution information of the landslide sample data and obtain landslide development features; the landslide development features include landslide geographic features and landslide geometric state features;

[0034] A landslide evaluation system establishing module is configured to analyze landslide generation background rules by using the landslide sample data and a plurality of candidate landslide influence indexes according to the landslide geographic features and the landslide geometric features, and establish a landslide danger evaluation index system;

[0035] The landslide risk assessment model obtaining module is configured to determine a target landslide influence index by performing correlation analysis on the plurality of candidate landslide influence indexes, and obtain a landslide risk assessment model constructed based on an automatic machine learning framework by combining the target landslide influence index and the landslide risk assessment index system; the landslide risk assessment model is configured to perform rainfall-induced landslide risk assessment on a heavy rainfall event.

[0036] In a third aspect, the present application further provides a computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0037] obtain historical rainfall-induced landslide data of historical heavy rainfall events, and construct landslide sample data;

[0038] analyze the landslide attribute parameters and the rainfall-induced landslide data distribution information of the landslide sample data to obtain landslide development characteristics; the landslide development characteristics comprise landslide geographical characteristics and landslide geometric state characteristics;

[0039] analyze the landslide sample data and a plurality of candidate landslide influence indexes according to the landslide geographical characteristics and the landslide geometric characteristics to analyze landslide generation background rules, and establish a landslide risk assessment index system;

[0040] determine a target landslide influence index by performing correlation analysis on the plurality of candidate landslide influence indexes, and obtain a landslide risk assessment model constructed based on an automatic machine learning framework by combining the target landslide influence index and the landslide risk assessment index system; the landslide risk assessment model is configured to perform rainfall-induced landslide risk assessment on a heavy rainfall event.

[0041] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the following steps:

[0042] obtain historical rainfall-induced landslide data of historical heavy rainfall events, and construct landslide sample data;

[0043] analyze the landslide attribute parameters and the rainfall-induced landslide data distribution information of the landslide sample data to obtain landslide development characteristics; the landslide development characteristics comprise landslide geographical characteristics and landslide geometric state characteristics;

[0044] analyze the landslide sample data and a plurality of candidate landslide influence indexes according to the landslide geographical characteristics and the landslide geometric characteristics to analyze landslide generation background rules, and establish a landslide risk assessment index system;

[0045] The target landslide influence index is determined through correlation analysis on the plurality of candidate landslide influence indexes, and a landslide danger assessment model based on an automatic machine learning framework is obtained in combination of the target landslide influence index and the landslide danger evaluation index system; the landslide danger assessment model is used for rainfall group landslide danger assessment of a heavy rainfall event.

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

[0047] Historical rainfall group landslide data of historical heavy rainfall events are acquired to construct landslide sample data;

[0048] The landslide development characteristics are obtained based on analysis of landslide attribute parameters and rainfall group landslide data distribution information of the landslide sample data; the landslide development characteristics include landslide geographic characteristics and landslide geometric state characteristics;

[0049] The landslide danger evaluation index system is established by analyzing landslide generation background rules using the landslide sample data and a plurality of candidate landslide influence indexes according to the landslide geographic characteristics and the landslide geometric characteristics;

[0050] The target landslide influence index is determined through correlation analysis on the plurality of candidate landslide influence indexes, and a landslide danger assessment model based on an automatic machine learning framework is obtained in combination of the target landslide influence index and the landslide danger evaluation index system; the landslide danger assessment model is used for rainfall group landslide danger assessment of a heavy rainfall event.

[0051] The above rainfall group landslide danger assessment method, device, computer equipment, computer readable storage medium and computer program product acquire historical rainfall group landslide data of historical heavy rainfall events to construct landslide sample data, analyze based on landslide attribute parameters and rainfall group landslide data distribution information of the landslide sample data to obtain landslide development characteristics, which include landslide geographic characteristics and landslide geometric state characteristics, then analyze landslide generation background rules using the landslide sample data and a plurality of candidate landslide influence indexes according to the landslide geographic characteristics and the landslide geometric characteristics to establish a landslide danger evaluation index system, and further determine a target landslide influence index through correlation analysis on the plurality of candidate landslide influence indexes, and obtain a landslide danger assessment model based on an automatic machine learning framework in combination of the target landslide influence index and the landslide danger evaluation index system, which is used for rainfall group landslide danger assessment of a heavy rainfall event, thereby realizing optimization of rainfall group landslide danger assessment, improving rainfall group landslide danger assessment efficiency, and effectively improving rainfall group landslide danger assessment precision. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0053] FIG. 1 is a flowchart of a rainfall group landslide hazard assessment method in an embodiment;

[0054] FIG. 2 is a schematic diagram of a rainfall group landslide hazard assessment process based on an automatic machine learning framework in an embodiment;

[0055] FIG. 3 is a flowchart of a rainfall group landslide hazard assessment method in another embodiment;

[0056] FIG. 4 is a structural block diagram of a rainfall group landslide hazard assessment device in an embodiment;

[0057] FIG. 5 is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

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

[0059] In an exemplary embodiment, as shown in FIG. 1, a rainfall group landslide hazard assessment method is provided, and the present embodiment is exemplified by applying the method to a terminal. 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 can be realized through the interaction of the terminal and the server. In the present embodiment, the method includes the following steps 101 to 104. Wherein:

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

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

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

[0063] As an example, the landslide development features can include landslide geographic features and landslide geometric state features.

[0064] In a specific implementation, landslide density, landslide length, landslide width, landslide height, and other landslide attribute parameters can be used to determine the rainfall group landslide geographic features and the landslide geometric features, and to obtain the landslide development features representing the landslide development law.

[0065] At step 103, the landslide sample data and the plurality of candidate landslide influence indicators are used to analyze the landslide generation background law according to the landslide geographic features and the landslide geometric features, and a landslide hazard evaluation index system is established.

[0066] By way of example, landslide internal and external influence factor data within the regional range of historical heavy rainfall events can be collected, and a plurality of candidate landslide influence indicators can be determined. Then, the landslide sample data and the plurality of candidate landslide influence indicators can be used to analyze the landslide generation background law according to the landslide geographic features and the landslide geometric features, such as analyzing the landslide disaster environment and the landslide spatial distribution law, to determine the landslide occurrence potential conditions and the distribution characteristics in the geographical space, and to establish the landslide hazard evaluation index system.

[0067] At step 104, the target landslide influence indicator is determined by performing correlation analysis on the plurality of candidate landslide influence indicators, and a landslide hazard assessment model based on an automatic machine learning framework is obtained by combining the target landslide influence indicator and the landslide hazard evaluation index system.

[0068] The landslide hazard assessment model can be used to perform rainfall group landslide hazard assessment on a heavy rainfall event.

[0069] In an example, the target landslide influence indicator can be selected by performing correlation test on the plurality of candidate landslide influence indicators. Then, the landslide hazard assessment model can be obtained by combining the target landslide influence indicator and the landslide hazard evaluation index system, establishing a model based on an automatic machine learning framework, and training the model. Thus, based on a heavy rainfall scenario, the rainfall group landslide data and the internal and external factors affecting the landslide are comprehensively considered, and an integrated model in the automatic machine learning framework is used to construct the model, thereby realizing the hazard assessment of the rainfall group landslide.

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

[0071] Compared with the traditional method, the technical scheme of the embodiment extracts rainfall group landslide data based on high-resolution satellite images, reveals the geographical development characteristics and geometric characteristics of landslides by combining landslide density and geometric parameters, and under the condition of collecting internal and external influence factors of landslides, the spatial distribution rule of landslides is analyzed in depth, and a landslide hazard evaluation index system is established. Then, based on the automatic machine learning framework, the rainfall group landslide hazard evaluation can be carried out. It can effectively solve the deficiencies of traditional landslide hazard evaluation methods in efficiency and accuracy, provide support for group landslide hazard evaluation in heavy rainfall scenarios, and meet the needs of geological disaster assessment and prevention in rainfall-prone areas.

[0072] In the above-mentioned rainfall group landslide hazard evaluation method, by obtaining historical rainfall group landslide data of historical heavy rainfall events, landslide sample data is constructed, and the development characteristics of landslides are obtained based on analysis of landslide attribute parameters and rainfall group landslide data distribution information of the landslide sample data. Then, according to the geographical characteristics of landslides and the geometric characteristics of landslides, the landslide sample data and the multiple candidate landslide influence indexes are used to analyze the background rule of landslide generation, and a landslide hazard evaluation index system is established. Then, by performing correlation analysis on the multiple candidate landslide influence indexes, the target landslide influence index is determined, and the landslide hazard evaluation model based on the automatic machine learning framework is obtained by combining the target landslide influence index and the landslide hazard evaluation index system. The optimization of the rainfall group landslide hazard evaluation is realized, which can improve the efficiency of the rainfall group landslide hazard evaluation and effectively improve the accuracy of the rainfall group landslide hazard evaluation.

[0073] In an exemplary embodiment, the obtaining of the historical rainfall group landslide data of the historical heavy rainfall event and the construction of the landslide sample data can include the following steps:

[0074] According to the satellite image of the historical heavy rainfall event, the historical rainfall group landslide data is obtained; by performing data checking and data supplementing on the historical rainfall group landslide data, the landslide sample data containing the rainfall group landslide data distribution is obtained.

[0075] In practical applications, high-resolution satellite images within a preset time range can be obtained according to the occurrence date of a historical heavy rainfall event, such as images one month before and after the occurrence date, as shown in FIG. 2. The historical rainfall group landslide data can be extracted through a human-computer interaction visual interpretation method, and objective and detailed rainfall group landslide data distribution can be obtained by checking and supplementing high-resolution satellite images within the regional range of the historical heavy rainfall event, to construct a rainfall group landslide database (i.e., landslide sample data)

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

[0077] In an optional embodiment, for the data preprocessing process of checking and supplementing, historical rainfall group landslide data can be collected, such as meteorological data including but not limited to rainfall, rainfall intensity, rainfall duration, temperature, etc., topographic and geomorphic data such as slope, aspect, and altitude, geological data such as soil type, rock properties, and vegetation coverage, and historical landslide information such as location, size, and occurrence time. The historical rainfall group landslide data can be cleaned, such as removing duplicate, erroneous, or abnormal data records, and data conversion, such as normalization processing, to facilitate further processing by machine learning algorithms.

[0078] In an exemplary embodiment, analyzing the rainfall group landslide data distribution information based on the landslide attribute parameters and the landslide sample data to obtain the landslide development characteristics can include the following steps:

[0079] Based on the rainfall group landslide data distribution information of the landslide sample data, the distribution pattern of the rainfall group landslide data in geographical space is obtained, and the landslide density parameter and the landslide geometric parameter are determined as the landslide attribute parameters. The landslide flowability 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, as shown in FIG. 2, GIS (Geographic Information System) tools and statistical methods can be used to obtain the distribution pattern of the landslide sample data in geographical space, which can be characterized based on landslide point density and landslide surface density quantitative indicators. The flowability of the landslide can be analyzed by statistics of landslide density, landslide length, landslide width, and landslide height (i.e., landslide density parameters and landslide geometric parameters), and the equivalent friction coefficient, to obtain the landslide development law, i.e., the landslide development characteristics.

[0081] In an exemplary embodiment, the landslide sample data and the plurality of candidate landslide impact indicators are analyzed according to the landslide geographical features and the landslide geometric features to analyze landslide generation background rules and establish a landslide hazard evaluation index system, which can include the following steps:

[0082] The plurality of candidate landslide impact indicators associated with the regional range of the historical heavy rainfall event are obtained, and the landslide sample data and the plurality of candidate landslide impact indicators are analyzed in combination with the landslide geographical features and the landslide geometric features to determine landslide spatial distribution rules and landslide disaster environment. The landslide hazard evaluation index system is constructed according to the landslide spatial distribution rules and the landslide disaster environment, and the plurality of candidate landslide impact indicators.

[0083] In actual application, as shown in FIG. 2, by collecting landslide internal and external impact factor data, using correlation analysis, principal component analysis and other methods to screen out the impact factors most closely related to the landslide, a plurality of candidate landslide impact indicators can be determined. Then, based on the spatial analysis function of the GIS tool, the landslide sample data and the plurality of candidate landslide impact indicators can be superimposed and analyzed to study and analyze the distribution rules of the rainfall group landslide disaster and the landslide disaster environment, and then a landslide hazard evaluation index system containing the plurality of candidate landslide impact indicators can be constructed.

[0084] For example, the landslide hazard evaluation index system can contain 5-day cumulative rainfall, elevation, slope, aspect, terrain humidity index, normalized vegetation index, stratum lithology, distance from water system, distance from road, surface coverage and other impact factors.

[0085] In an exemplary embodiment, by performing correlation analysis on the plurality of candidate landslide impact indicators to determine a target landslide impact indicator, and combining the target landslide impact indicator with the landslide hazard evaluation index system, a landslide hazard evaluation model constructed based on an automatic machine learning framework can be obtained, which can include the following steps:

[0086] The correlation analysis is performed on the plurality of candidate landslide impact indicators, and the screened candidate landslide impact indicators are taken as the target landslide impact indicators. In the landslide sample data, the landslide samples and non-landslide samples are selected according to the target landslide impact indicators as training sample data. The target landslide impact indicators and the landslide hazard evaluation index system are combined to construct an initial evaluation model using an automatic machine learning framework. The initial evaluation model is trained based on the training sample data to obtain the landslide hazard evaluation model.

[0087] In a specific implementation, as shown in FIG. 2, a Pearson correlation coefficient (an index 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 a plurality of candidate landslide influence indicators to screen target landslide influence indicators, then landslide samples and non-landslide samples can be selected based on a 1:1 ratio to obtain training sample data, and then an initial evaluation model can be constructed based on the target landslide influence indicators and the landslide risk assessment index system using an automatic machine learning framework AutoGluon, and the landslide risk assessment model can be obtained by training based on the training sample data.

[0088] In an example, the automatic machine learning framework can include various ensemble methods such as random forests, gradient boosting trees, etc. Ensemble learning can improve 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, and by adjusting hyperparameters and optimizing model structures, the prediction accuracy and generalization ability of the model can be improved, and its performance can be evaluated by cross-validation and other methods.

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

[0090] The preset model evaluation indicators are used to perform model performance detection on the landslide risk assessment model; based on the landslide risk assessment model that passes the detection, rainfall cluster landslide risk assessment is performed on the historical heavy rainfall events to obtain landslide risk assessment results; and based on the landslide risk assessment results, a rainfall cluster landslide risk prompt image of the historical heavy rainfall events is displayed.

[0091] The model evaluation indicators can include any one or more of the following: area under the curve indicator, accuracy indicator, precision indicator, recall indicator.

[0092] In actual application, for the landslide risk assessment model, AUC (area under the curve, an indicator for evaluating a model), accuracy, precision, and recall (i.e., area under the curve indicator, accuracy indicator, precision indicator, and recall indicator) can be used to detect model performance; as shown in FIG. 2, after establishing the landslide risk assessment model, the historical heavy rainfall events can be evaluated for rainfall cluster landslide risk based on the landslide risk assessment model.

[0093] In an example, the landslide hazard assessment result output by the model can be visualized on a map using a GIS tool, as shown in FIG. 2. According to the landslide hazard assessment result, the natural break method can be used to divide the landslide hazard level (e.g., into levels of extremely low, low, medium, high, and extremely high), and a rainfall group landslide hazard level map (i.e., a rainfall group landslide hazard prompt image) can be generated and displayed, such as a rainfall group landslide hazard prompt image of a geographical area corresponding to a historical heavy rainfall event.

[0094] In an example embodiment, as shown in FIG. 3, another flowchart of a rainfall group landslide hazard assessment method is provided. In this embodiment, the method includes the following steps:

[0095] In step 301, historical rainfall group landslide data is obtained from satellite images of historical heavy rainfall events. Through data checking and data supplementing processing of the historical rainfall group landslide data, landslide sample data containing rainfall group landslide data distribution is obtained. In step 302, based on the rainfall group landslide data distribution information of the landslide sample data, the distribution pattern of the rainfall group landslide data in geographical space is obtained, and the landslide density parameter and the landslide geometric parameter are determined as landslide attribute parameters. In step 303, the landslide flowability of the landslide sample data is analyzed according to the landslide attribute parameters, and the landslide geographical feature and the landslide geometric feature are obtained as landslide development features. In step 304, a plurality of candidate landslide influence indicators associated with the regional range of the historical heavy rainfall event are obtained, and the landslide sample data and the plurality of candidate landslide influence indicators are analyzed in combination with the landslide geographical feature and the landslide geometric feature to determine the landslide spatial distribution rule and the landslide disaster environment. In step 305, according to the landslide spatial distribution rule and the landslide disaster environment, and the plurality of candidate landslide influence indicators, a landslide hazard evaluation index system is constructed. In step 306, the correlation analysis is performed on the plurality of candidate landslide influence indicators, the selected candidate landslide influence indicators are taken as target landslide influence indicators, and the landslide samples and non-landslide samples are selected from the landslide sample data according to the target landslide influence indicators as training sample data. In step 307, the initial evaluation model is constructed by combining the target landslide influence indicators and the landslide hazard evaluation index system, the initial evaluation model is trained based on the training sample data, and the landslide hazard assessment model is obtained. It should be noted that the specific definition of the above steps can be referred to the specific definition of the rainfall group landslide hazard assessment method described above, and will not be repeated here.

[0096] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time but can be executed at different times, and the execution of the steps or stages is not necessarily sequential but can be performed alternately or alternately with at least part of other steps or stages.

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

[0098] In an exemplary embodiment, as shown in FIG. 4, a rainfall group landslide hazard assessment device is provided, comprising:

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

[0100] The landslide development feature obtaining module 402 is configured to analyze based on the landslide attribute parameters and the rainfall group landslide data distribution information of the landslide sample data to obtain landslide development features; the landslide development features include landslide geographic features and landslide geometric state features.

[0101] The landslide evaluation system establishing module 403 is configured to analyze landslide generation background rules by using the landslide sample data and a plurality of candidate landslide influence indicators according to the landslide geographic features and the landslide geometric features, and establish a landslide hazard evaluation index system.

[0102] The landslide hazard assessment model obtaining module 404 is configured to determine target landslide influence indicators by performing correlation analysis on the plurality of candidate landslide influence indicators, and obtain a landslide hazard assessment model constructed based on an automatic machine learning framework by combining the target landslide influence indicators and the landslide hazard evaluation index system; the landslide hazard assessment model is used for rainfall group landslide hazard assessment of a heavy rainfall event.

[0103] In an embodiment, the landslide sample data construction module 401 comprises:

[0104] a data extraction submodule configured to obtain the historical rainfall-induced landslide data from satellite images of the historical heavy rainfall events;

[0105] a data processing submodule configured to obtain landslide sample data containing rainfall-induced landslide data distribution by performing data checking and data supplementing processing on the historical rainfall-induced landslide data.

[0106] In an embodiment, the landslide development feature obtaining module 402 comprises:

[0107] a landslide attribute parameter obtaining submodule configured to obtain a distribution pattern of rainfall-induced landslide data in geographical space based on the rainfall-induced landslide data distribution information of the landslide sample data, and determine a landslide density parameter and a landslide geometric parameter as the landslide attribute parameter;

[0108] a feature analysis submodule configured to analyze the landslide flowability of the landslide sample data according to the landslide attribute parameter, and obtain the landslide geographical feature and the landslide geometric feature as the landslide development feature.

[0109] In an embodiment, the landslide evaluation system establishing module 403 comprises:

[0110] an influence index obtaining submodule configured to obtain a plurality of candidate landslide influence indexes associated with the regional range of the historical heavy rainfall events;

[0111] an index analysis submodule configured to analyze the landslide sample data and the plurality of candidate landslide influence indexes in combination with the landslide geographical feature and the landslide geometric feature, and determine a landslide spatial distribution rule and a landslide disaster-forming environment;

[0112] an index system construction submodule configured to construct the landslide risk evaluation index system according to the landslide spatial distribution rule and the landslide disaster-forming environment, and the plurality of candidate landslide influence indexes.

[0113] In an embodiment, the landslide risk assessment model obtaining module 404 comprises:

[0114] an index screening submodule configured to screen out candidate landslide influence indexes as the target landslide influence indexes by performing correlation analysis on the plurality of candidate landslide influence indexes;

[0115] a sample selection submodule configured to select landslide samples and non-landslide samples as training sample data from the landslide sample data according to the target landslide influence indexes;

[0116] The model construction submodule is configured to combine the target landslide influence indicator and the landslide danger evaluation indicator system, and construct an initial evaluation model by using an automatic machine learning framework.

[0117] The model training submodule is configured to train the initial evaluation model based on the training sample data to obtain the landslide danger evaluation model.

[0118] In an embodiment, the device further comprises:

[0119] The model performance detection module is configured to perform model performance detection on the landslide danger evaluation model by using a preset model evaluation indicator.

[0120] The landslide danger evaluation module is configured to perform rainfall cluster landslide danger evaluation on the historical heavy rainfall events based on the landslide danger evaluation model that passes the detection, to obtain a landslide danger evaluation result.

[0121] The landslide danger prompt image display module is configured to display a rainfall cluster landslide danger prompt image of the historical heavy rainfall events according to the landslide danger evaluation result.

[0122] The model evaluation indicator includes any one or more of the following:

[0123] The area under the curve indicator, the accuracy indicator, the precision indicator, and the recall indicator.

[0124] The above modules of the rainfall cluster landslide danger evaluation device can be realized by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform the operations corresponding to the above modules.

[0125] In an exemplary embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram thereof can be as shown in FIG. 5. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, 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. Among them, 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 operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, mobile cellular network, near field communication (NFC) or other technologies. The computer program is executed by the processor to implement a rainfall group landslide hazard assessment method.

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

[0127] In an exemplary embodiment, a computer device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the following steps:

[0128] Obtaining historical rainfall group landslide data of historical heavy rainfall events, and constructing landslide sample data;

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

[0130] According to the landslide geographical characteristics and the landslide geometric characteristics, analyzing the landslide generation background law by using the landslide sample data and a plurality of candidate landslide influence indexes, and establishing a landslide hazard evaluation index system;

[0131] The target landslide influence index is determined by performing correlation analysis on the plurality of candidate landslide influence indexes, and a landslide danger assessment model based on an automatic machine learning framework is obtained in combination of the target landslide influence index and the landslide danger evaluation index system; the landslide danger assessment model is used for rainfall group landslide danger assessment of a heavy rainfall event.

[0132] In one embodiment, the processor also implements the steps of the rainfall group landslide danger assessment method in the other embodiments described above when executing the computer program.

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

[0134] The historical rainfall group landslide data of historical heavy rainfall events is obtained, and landslide sample data is constructed;

[0135] The landslide development characteristics are obtained based on analysis of the landslide attribute parameters and rainfall group landslide data distribution information of the landslide sample data; the landslide development characteristics include landslide geographic characteristics and landslide geometric state characteristics;

[0136] According to the landslide geographic characteristics and the landslide geometric characteristics, the landslide sample data and a plurality of candidate landslide influence indexes are used to analyze landslide generation background rules, and a landslide danger evaluation index system is established;

[0137] The target landslide influence index is determined by performing correlation analysis on the plurality of candidate landslide influence indexes, and a landslide danger assessment model based on an automatic machine learning framework is obtained in combination of the target landslide influence index and the landslide danger evaluation index system; the landslide danger assessment model is used for rainfall group landslide danger assessment of a heavy rainfall event.

[0138] In one embodiment, the processor also implements the steps of the rainfall group landslide danger assessment method in the other embodiments described above when executing the computer program.

[0139] In one embodiment, a computer program product is provided, and the computer program product includes a computer program, and the computer program is executed by a processor to implement the following steps:

[0140] The historical rainfall group landslide data of historical heavy rainfall events is obtained, and landslide sample data is constructed;

[0141] The landslide development characteristics are obtained based on analysis of the landslide attribute parameters and rainfall group landslide data distribution information of the landslide sample data; the landslide development characteristics include landslide geographic characteristics and landslide geometric state characteristics;

[0142] According to the landslide geographical features and the landslide geometric features, a landslide sample data and a plurality of candidate landslide influence indexes are used to analyze a landslide generation background rule, and a landslide danger evaluation index system is established;

[0143] Through correlation analysis on the plurality of candidate landslide influence indexes, a target landslide influence index is determined, and a landslide danger evaluation model based on an automatic machine learning framework is obtained in combination of the target landslide influence index and the landslide danger evaluation index system; the landslide danger evaluation model is used for rainfall group landslide danger evaluation on a heavy rainfall event.

[0144] In one embodiment, the computer program, when executed by the processor, also implements the steps of the rainfall group landslide danger evaluation method in the other embodiments described above.

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

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to 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. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0147] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0148] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications 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 should be subject to the appended claims.

Claims

1. A method for assessing the risk of a rainfall cluster landslide, characterized by, The method comprises: obtaining historical rainfall group landslide data of historical heavy rainfall events, and constructing landslide sample data; based on the rainfall group landslide data distribution information of the landslide sample data, obtaining the distribution pattern of the rainfall group landslide data in geographical space, determining the landslide density parameter and the landslide geometric parameter as the landslide attribute parameter, and analyzing the landslide flowability of the landslide sample data by using the equivalent friction coefficient according to the landslide attribute parameter, to obtain the landslide geographical feature and the landslide geometric feature as the landslide development feature; obtaining a plurality of candidate landslide influence indicators associated with the regional range of the historical heavy rainfall events, analyzing the landslide sample data and the plurality of candidate landslide influence indicators in combination with the landslide geographical feature and the landslide geometric feature, determining the landslide spatial distribution rule and the landslide disaster environment, and constructing a landslide hazard evaluation index system according to the landslide spatial distribution rule and the landslide disaster environment and the plurality of candidate landslide influence indicators; determining a target landslide influence indicator by correlation analysis on the plurality of candidate landslide influence indicators, and obtaining a landslide hazard assessment model constructed based on an automatic machine learning framework in combination with the target landslide influence indicator and the landslide hazard evaluation index system; the landslide hazard assessment model is used for rainfall group landslide hazard assessment of a heavy rainfall event.

2. The method of claim 1, wherein, The method comprises: obtaining the historical rainfall group landslide data according to satellite images of the historical heavy rainfall events; obtaining landslide sample data containing rainfall group landslide data distribution by data checking and data supplementing processing on the historical rainfall group landslide data.

3. The method of claim 1, wherein, The method comprises: obtaining the historical rainfall group landslide data according to satellite images of the historical heavy rainfall events; obtaining landslide sample data containing rainfall group landslide data distribution by data checking and data supplementing processing on the historical rainfall group landslide data. The method comprises: obtaining the historical rainfall group landslide data according to satellite images of the historical heavy rainfall events; 4. The method according to any one of claims 1 to 3, characterized in that, obtaining landslide sample data containing rainfall group landslide data distribution by data checking and data supplementing processing on the historical rainfall group landslide data. The method comprises: obtaining the historical rainfall group landslide data according to satellite images of the historical heavy rainfall events; obtaining landslide sample data containing rainfall group landslide data distribution by data checking and data supplementing processing on the historical rainfall group landslide data. The method further comprises: performing model performance detection on the landslide hazard assessment model by using a preset model evaluation index; performing rainfall group landslide hazard assessment on the historical heavy rainfall events based on the landslide hazard assessment model that passes the detection, to obtain a landslide hazard assessment result; displaying a rainfall group landslide hazard prompt image of the historical heavy rainfall event according to the landslide hazard assessment result; wherein the model evaluation index comprises any one or more of the following: The area under the curve index, the accuracy index, the precision index, and the recall index.

5. A device for evaluating the risk of a rainfall cluster landslide, characterized by, The device comprises: A landslide sample data construction module configured to acquire historical rainfall group landslide data of historical heavy rainfall events, and to construct landslide sample data; A landslide development feature acquisition module configured to acquire a distribution pattern of rainfall group landslide data in geographical space based on distribution information of the rainfall group landslide data of the landslide sample data, to determine a landslide density parameter and a landslide geometric parameter as landslide attribute parameters, and to analyze landslide flowability of the landslide sample data by using an equivalent friction coefficient according to the landslide attribute parameters, to obtain landslide geographical features and landslide geometric features as landslide development features; A landslide evaluation system establishment module configured to acquire a plurality of candidate landslide influence indexes associated with a regional range of the historical heavy rainfall events, to analyze the landslide sample data and the plurality of candidate landslide influence indexes in combination with the landslide geographical features and the landslide geometric features, to determine a landslide spatial distribution law and a landslide disaster gestating environment, and to construct a landslide hazard evaluation index system according to the landslide spatial distribution law and the landslide disaster gestating environment and the plurality of candidate landslide influence indexes; A landslide hazard assessment model obtaining module configured to determine a target landslide influence index by performing correlation analysis on the plurality of candidate landslide influence indexes, to obtain a landslide hazard assessment model constructed based on an automatic machine learning framework in combination with the target landslide influence index and the landslide hazard evaluation index system; and to perform rainfall group landslide hazard assessment on a heavy rainfall event by using the landslide hazard assessment model. 6.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-5 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 4.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 4.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 4. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 4.

Images