A landslide disaster warning method and system

Abstract

The present invention provides a method and system for early warning of mountain landslide disasters, belonging to the technical field of early warning of mountain landslide disasters, and the method comprises: obtaining rainfall, longitudinal displacement, lateral displacement and groundwater level, performing surface fitting operations respectively, and obtaining a first prediction domain and a second prediction domain; obtaining real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level, substituting them into the surface fitting equation respectively, and obtaining a first lateral displacement and a first longitudinal displacement, a second lateral displacement and a second longitudinal displacement; if the real-time longitudinal displacement is greater than or equal to the mean value between the first longitudinal displacement and the second longitudinal displacement, and / or the real-time lateral displacement is greater than or equal to the mean value between the first lateral displacement and the second lateral displacement, then an early warning is issued; otherwise, no early warning is issued. The present invention adopts a surface fitting method to predict and warn mountain landslide disasters from multiple dimensions.

Description

Technical Field

[0001] The present invention relates to the technical field of mountain landslide disaster early warning, and in particular to a mountain landslide disaster early warning method and system. Background Art

[0002] At present, the traditional early warning scheme for mountain landslide disasters is to first predict mountain landslide disasters and then issue mountain landslide disaster early warnings based on the prediction results. The traditional mountain landslide disaster prediction scheme is generally as follows:

[0003] 1. Geological Survey and Analysis

[0004] Geological survey and analysis are fundamental to landslide disaster prediction. Detailed investigation of factors such as the geological structure, stratum lithology, geological structure, and groundwater distribution in a potential landslide area can determine the geological background and potential sliding surface. Furthermore, historical landslide events must be analyzed to identify their occurrence patterns and provide foundational data for prediction.

[0005] 2. Application of monitoring instruments

[0006] Monitoring instruments play a vital role in predicting mountain landslide disasters. By deploying displacement monitoring stations, landslide stress monitoring stations, and groundwater monitoring wells, the dynamic changes of landslide masses can be monitored in real time. This monitoring data can help predict the probability and scale of landslides.

[0007] 3. Application of Remote Sensing Technology

[0008] Remote sensing technology, with its advantages of wide coverage and rapid information acquisition, plays a vital role in predicting mountain landslide hazards. Using satellite remote sensing and drone remote sensing techniques, high-resolution imagery of landslide areas can be obtained, extracting morphological characteristics and texture information of the landslide mass, and subsequently analyzing its development trends and potential hazards.

[0009] 4. Time Forecast and Classification

[0010] Temporal forecasting is the process of predicting when a landslide will occur. By comprehensively analyzing monitoring data and remote sensing information, we can determine the stability of the slope and predict the likely timeframe for a landslide. Furthermore, landslides can be classified based on factors such as scale, speed, and impact area, providing a basis for developing early warning measures.

[0011] V. Forecasting Methods and Models

[0012] Forecasting methods and models are at the core of landslide disaster prediction. Currently, commonly used forecasting methods include physical models, statistical models, and artificial intelligence models. Physical models are based on mechanical principles and geological conditions, statistical models use historical data for statistical analysis, and artificial intelligence models use machine learning algorithms to learn and predict from monitoring data.

[0013] 6. Precipitation Parameter Forecast

[0014] Precipitation is an important factor affecting the occurrence of mountain landslides. By monitoring and predicting rainfall, it is possible to determine whether the landslide area has the conditions for landslides to occur. Therefore, rainfall parameter forecasting is of great significance in the prediction of mountain landslides.

[0015] However, the above traditional schemes basically predict mountain landslide disasters from a single dimension, and then combine the prediction results of multiple single dimensions as the final prediction result. There are few that predict mountain landslide disasters from multiple dimensions. Summary of the Invention

[0016] The present invention provides a landslide disaster early warning method and system, which adopts a surface fitting method to perform landslide disaster prediction and early warning from multiple dimensions.

[0017] The embodiments of this specification disclose a method for early warning of mountain landslide disasters, including:

[0018] Acquiring historical data of a landslide body causing a mountain landslide disaster, wherein the historical data includes rainfall, longitudinal displacement, lateral displacement, and groundwater level;

[0019] The rainfall amount is used as a row vector and the lateral displacement is used as a column vector to form a first matrix, and then the longitudinal displacement is introduced to perform a surface fitting operation to obtain a three-dimensional surface and a rainfall surface fitting equation, and the three-dimensional surface is recorded as a first prediction domain;

[0020] The groundwater level is used as a row vector and the lateral displacement is used as a column vector to form a second matrix, and then the longitudinal displacement is introduced to perform a surface fitting operation to obtain a three-dimensional surface and a groundwater level surface fitting equation, and the three-dimensional surface is recorded as a second prediction domain;

[0021] Acquiring real-time data of the landslide body to be predicted and warned, the real-time data including real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level;

[0022] Substituting the real-time rainfall into the rainfall surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a first lateral displacement and a first longitudinal displacement corresponding to the real-time rainfall based on the first prediction domain;

[0023] Substituting the real-time groundwater level into the groundwater level surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a second lateral displacement and a second longitudinal displacement corresponding to the real-time groundwater level based on the second prediction domain;

[0024] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement and the second longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement and the second lateral displacement;

[0025] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0026] In some embodiments of this specification, the historical data further includes rock strength, and the rock strength is used as a row vector and the lateral displacement is used as a column vector to form a third matrix. The longitudinal displacement is then introduced and a surface fitting operation is performed to obtain a three-dimensional surface and a rock strength surface fitting equation, and the three-dimensional surface is recorded as the third prediction domain.

[0027] The real-time data also includes real-time rock strength. The real-time rock strength is substituted into the rock strength surface fitting equation to obtain a target value. If the target value is greater than 0, a third lateral displacement and a third longitudinal displacement corresponding to the real-time rock strength are obtained based on a third prediction domain.

[0028] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the third longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the third lateral displacement;

[0029] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0030] In some embodiments of the present specification, the historical data further includes vegetation coverage, the vegetation coverage is used as a row vector, and the lateral displacement is used as a column vector to form a fourth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a vegetation coverage surface fitting equation, and the three-dimensional surface is recorded as the fourth prediction domain;

[0031] The real-time data also includes a real-time vegetation coverage rate. The real-time vegetation coverage rate is substituted into the vegetation coverage rate surface fitting equation to obtain a target value. If the target value is greater than 0, a fourth lateral displacement and a fourth longitudinal displacement corresponding to the real-time vegetation coverage rate are obtained based on a fourth prediction domain.

[0032] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the fourth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the fourth lateral displacement;

[0033] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0034] In some embodiments of the present specification, the historical data further includes rainfall intensity, and the rainfall intensity is used as a row vector, and the lateral displacement is used as a column vector to form a fifth matrix. The longitudinal displacement is then introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a rainfall intensity surface fitting equation, and the three-dimensional surface is recorded as the fifth prediction domain.

[0035] The real-time data also includes real-time rainfall intensity. The real-time rainfall intensity is substituted into the rainfall intensity surface fitting equation to obtain a target value. If the target value is greater than 0, a fifth lateral displacement and a fifth longitudinal displacement corresponding to the real-time rainfall intensity are obtained based on a fifth prediction domain.

[0036] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the fifth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the fifth lateral displacement;

[0037] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0038] In some embodiments of the present specification, the historical data further includes landslide body stress, the landslide body stress is used as a row vector, and the lateral displacement is used as a column vector to form a sixth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a landslide body stress surface fitting equation, and the three-dimensional surface is recorded as the sixth prediction domain;

[0039] The real-time data also includes real-time landslide body stress, and the real-time landslide body stress is substituted into the landslide body stress surface fitting equation to obtain a target value. If the target value is greater than 0, a sixth lateral displacement and a sixth longitudinal displacement corresponding to the real-time landslide body stress are obtained based on a sixth prediction domain.

[0040] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the sixth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the sixth lateral displacement;

[0041] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0042] In some embodiments of the present specification, the historical data further includes rock hardness, and the rock hardness is used as a row vector and the lateral displacement is used as a column vector to form a seventh matrix. The longitudinal displacement is then introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a rock hardness surface fitting equation, and the three-dimensional surface is recorded as the seventh prediction domain;

[0043] The real-time data also includes real-time rock hardness. The real-time rock hardness is substituted into the rock hardness surface fitting equation to obtain a target value. If the target value is greater than 0, a seventh lateral displacement and a seventh longitudinal displacement corresponding to the real-time rock hardness are obtained based on a seventh prediction domain.

[0044] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the seventh longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the seventh lateral displacement;

[0045] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0046] In some embodiments of the present specification, the historical data further includes tree inclination, the tree inclination is used as a row vector, and the lateral displacement is used as a column vector to form an eighth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a surface fitting equation of the tree inclination, and the three-dimensional surface is recorded as the eighth prediction domain;

[0047] The real-time data also includes real-time tree inclination. The real-time tree inclination is substituted into the tree inclination surface fitting equation to obtain a target value. If the target value is greater than 0, an eighth lateral displacement and an eighth longitudinal displacement corresponding to the real-time tree inclination are obtained based on an eighth prediction domain.

[0048] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the eighth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the eighth lateral displacement;

[0049] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0050] In some embodiments of the present specification, the historical data further includes the longitude of the highest point of the landslide soil, the longitude is used as a row vector, and the lateral displacement is used as a column vector to form a ninth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a longitude surface fitting equation, and the three-dimensional surface is recorded as the ninth prediction domain;

[0051] The real-time data also includes real-time longitude. The real-time longitude is substituted into the longitude surface fitting equation to obtain a target value. If the target value is greater than 0, a ninth lateral displacement and a ninth longitudinal displacement corresponding to the real-time longitude are obtained based on a ninth prediction domain.

[0052] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the ninth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the ninth lateral displacement;

[0053] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0054] In some embodiments of the present specification, the historical data further includes the latitude of the highest point of the landslide soil, the latitude is used as a row vector, and the lateral displacement is used as a column vector to form a tenth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a latitude surface fitting equation, and the three-dimensional surface is recorded as the tenth prediction domain;

[0055] The real-time data also includes real-time latitude. The real-time latitude is substituted into the latitude surface fitting equation to obtain a target value. If the target value is greater than 0, a tenth lateral displacement and a tenth longitudinal displacement corresponding to the real-time latitude are obtained based on a tenth prediction domain.

[0056] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the tenth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the tenth lateral displacement;

[0057] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0058] The embodiments of this specification also disclose an early warning system for mountain landslide disasters, which is used to implement any of the above-mentioned early warning methods for mountain landslide disasters. The early warning system for mountain landslide disasters includes: a first acquisition module, which is used to acquire historical data of the landslide body where the mountain landslide disaster occurs, wherein the historical data includes rainfall, longitudinal displacement, lateral displacement, and groundwater level;

[0059] a first fitting module, configured to construct a first matrix by taking the rainfall amount as a row vector and the lateral displacement as a column vector, then importing the longitudinal displacement, performing a surface fitting operation, obtaining a three-dimensional surface and a rainfall surface fitting equation, and recording the three-dimensional surface as a first prediction domain;

[0060] a second fitting module, configured to construct a second matrix by taking the groundwater level as a row vector and the lateral displacement as a column vector, then importing the longitudinal displacement, performing a surface fitting operation, obtaining a three-dimensional surface and a groundwater level surface fitting equation, and recording the three-dimensional surface as a second prediction domain;

[0061] The second acquisition module is used to obtain real-time data of the landslide body to be predicted and warned, wherein the real-time data includes real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level;

[0062] a first displacement acquisition module, configured to substitute the real-time rainfall into the rainfall surface fitting equation to obtain a target value, and if the target value is greater than 0, obtain a first lateral displacement and a first longitudinal displacement corresponding to the real-time rainfall based on the first prediction domain;

[0063] a second displacement acquisition module, configured to substitute the real-time groundwater level into the groundwater level surface fitting equation to obtain a target value, and if the target value is greater than 0, obtain a second lateral displacement and a second longitudinal displacement corresponding to the real-time groundwater level based on a second prediction domain;

[0064] A comparison and warning module is used to compare the real-time longitudinal displacement with the average of the first longitudinal displacement and the second longitudinal displacement, and to compare the real-time lateral displacement with the average of the first lateral displacement and the second lateral displacement; if the real-time longitudinal displacement is greater than or equal to the average, and / or the real-time lateral displacement is greater than or equal to the average, a warning is issued; if the real-time longitudinal displacement is less than the average, and the real-time lateral displacement is less than the average, no warning is issued.

[0065] The embodiments of this specification can achieve at least the following beneficial effects:

[0066] By acquiring historical data on landslide bodies that have caused mountain landslide disasters and performing surface fitting on them, a first prediction domain and a second prediction domain are obtained. The data in the first and second prediction domains are then compared with the real-time data of the landslide body to be predicted and warned. Based on the comparison results, a mountain landslide disaster prediction and warning is performed. This invention uses surface fitting to perform mountain landslide disaster prediction and warning from multiple dimensions, resulting in better prediction results and timely warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0068] Figure 1 Schematic diagram of a landslide disaster early warning method according to some embodiments of the present invention. DETAILED DESCRIPTION

[0069] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the embodiments of the present invention. Therefore, the drawings and description are to be regarded as illustrative in nature and not restrictive.

[0070] The disclosure below provides many different embodiments or examples for implementing different structures of the embodiments of the present invention. In order to simplify the disclosure of the embodiments of the present invention, the components and configurations of specific examples are described below. Of course, these are merely examples and are not intended to limit the embodiments of the present invention. In addition, the embodiments of the present invention may repeat reference numerals and / or reference letters in different examples. Such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or configurations discussed.

[0071] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0072] like Figure 1 As shown, the embodiment of this specification discloses a method for early warning of mountain landslide disasters, including:

[0073] Acquiring historical data of a landslide body causing a mountain landslide disaster, wherein the historical data includes rainfall, longitudinal displacement, lateral displacement, and groundwater level;

[0074] The rainfall amount is used as a row vector and the lateral displacement is used as a column vector to form a first matrix, and then the longitudinal displacement is introduced to perform a surface fitting operation to obtain a three-dimensional surface and a rainfall surface fitting equation, and the three-dimensional surface is recorded as a first prediction domain;

[0075] The groundwater level is used as a row vector and the lateral displacement is used as a column vector to form a second matrix, and then the longitudinal displacement is introduced to perform a surface fitting operation to obtain a three-dimensional surface and a groundwater level surface fitting equation, and the three-dimensional surface is recorded as a second prediction domain;

[0076] Acquiring real-time data of the landslide body to be predicted and warned, the real-time data including real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level;

[0077] Substituting the real-time rainfall into the rainfall surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a first lateral displacement and a first longitudinal displacement corresponding to the real-time rainfall based on the first prediction domain;

[0078] Substituting the real-time groundwater level into the groundwater level surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a second lateral displacement and a second longitudinal displacement corresponding to the real-time groundwater level based on the second prediction domain;

[0079] The real-time longitudinal displacement is compared with the average of the first longitudinal displacement and the second longitudinal displacement, and the real-time lateral displacement is compared with the average of the first lateral displacement and the second lateral displacement; if the real-time longitudinal displacement is greater than or equal to the average, and / or the real-time lateral displacement is greater than or equal to the average, an early warning is issued; if the real-time longitudinal displacement is less than the average, and the real-time lateral displacement is less than the average, no early warning is issued.

[0080] In some embodiments, the historical data further includes rock strength, and the rock strength is used as a row vector and the lateral displacement is used as a column vector to form a third matrix. The longitudinal displacement is then introduced and a surface fitting operation is performed to obtain a three-dimensional surface and a rock strength surface fitting equation, and the three-dimensional surface is recorded as a third prediction domain.

[0081] The real-time data also includes real-time rock strength. The real-time rock strength is substituted into the rock strength surface fitting equation to obtain a target value. If the target value is greater than 0, a third lateral displacement and a third longitudinal displacement corresponding to the real-time rock strength are obtained based on a third prediction domain.

[0082] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the third longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the third lateral displacement;

[0083] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0084] In some embodiments, the historical data further includes vegetation coverage, the vegetation coverage is used as a row vector, the lateral displacement is used as a column vector to form a fourth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a vegetation coverage surface fitting equation, and the three-dimensional surface is recorded as the fourth prediction domain;

[0085] The real-time data also includes a real-time vegetation coverage rate. The real-time vegetation coverage rate is substituted into the vegetation coverage rate surface fitting equation to obtain a target value. If the target value is greater than 0, a fourth lateral displacement and a fourth longitudinal displacement corresponding to the real-time vegetation coverage rate are obtained based on a fourth prediction domain.

[0086] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the fourth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the fourth lateral displacement;

[0087] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0088] In some embodiments, the historical data further includes rainfall intensity, and the rainfall intensity is used as a row vector, and the lateral displacement is used as a column vector to form a fifth matrix. The longitudinal displacement is then introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a rainfall intensity surface fitting equation, and the three-dimensional surface is recorded as the fifth prediction domain.

[0089] The real-time data also includes real-time rainfall intensity. The real-time rainfall intensity is substituted into the rainfall intensity surface fitting equation to obtain a target value. If the target value is greater than 0, a fifth lateral displacement and a fifth longitudinal displacement corresponding to the real-time rainfall intensity are obtained based on a fifth prediction domain.

[0090] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the fifth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the fifth lateral displacement;

[0091] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0092] In some embodiments, the historical data further includes landslide body stress, the landslide body stress is used as a row vector, and the lateral displacement is used as a column vector to form a sixth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a landslide body stress surface fitting equation, and the three-dimensional surface is recorded as the sixth prediction domain;

[0093] The real-time data also includes real-time landslide body stress, and the real-time landslide body stress is substituted into the landslide body stress surface fitting equation to obtain a target value. If the target value is greater than 0, a sixth lateral displacement and a sixth longitudinal displacement corresponding to the real-time landslide body stress are obtained based on a sixth prediction domain.

[0094] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the sixth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the sixth lateral displacement;

[0095] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0096] In some embodiments, the historical data further includes rock hardness, and the rock hardness is used as a row vector and the lateral displacement is used as a column vector to form a seventh matrix. The longitudinal displacement is then introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a rock hardness surface fitting equation, and the three-dimensional surface is recorded as the seventh prediction domain.

[0097] The real-time data also includes real-time rock hardness. The real-time rock hardness is substituted into the rock hardness surface fitting equation to obtain a target value. If the target value is greater than 0, a seventh lateral displacement and a seventh longitudinal displacement corresponding to the real-time rock hardness are obtained based on a seventh prediction domain.

[0098] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the seventh longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the seventh lateral displacement;

[0099] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0100] In some embodiments, the historical data further includes tree inclinations, the tree inclinations are used as row vectors, and the lateral displacements are used as column vectors to form an eighth matrix, and then the longitudinal displacements are introduced to perform a surface fitting operation to obtain a three-dimensional surface and a surface fitting equation for the tree inclinations, and the three-dimensional surface is recorded as the eighth prediction domain;

[0101] The real-time data also includes real-time tree inclination. The real-time tree inclination is substituted into the tree inclination surface fitting equation to obtain a target value. If the target value is greater than 0, an eighth lateral displacement and an eighth longitudinal displacement corresponding to the real-time tree inclination are obtained based on an eighth prediction domain.

[0102] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the eighth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the eighth lateral displacement;

[0103] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0104] In some embodiments, the historical data further includes the longitude of the highest point of the landslide soil, the longitude is used as a row vector, and the lateral displacement is used as a column vector to form a ninth matrix, and then the longitudinal displacement is introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a longitude surface fitting equation, and the three-dimensional surface is recorded as a ninth prediction domain;

[0105] The real-time data also includes real-time longitude. The real-time longitude is substituted into the longitude surface fitting equation to obtain a target value. If the target value is greater than 0, a ninth lateral displacement and a ninth longitudinal displacement corresponding to the real-time longitude are obtained based on a ninth prediction domain.

[0106] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the ninth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the ninth lateral displacement;

[0107] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0108] In some embodiments, the historical data further includes the latitude of the highest point of the landslide soil, the latitude is used as a row vector, and the lateral displacement is used as a column vector to form a tenth matrix, and then the longitudinal displacement is imported, and a surface fitting operation is performed to obtain a three-dimensional surface and a latitude surface fitting equation, and the three-dimensional surface is recorded as the tenth prediction domain;

[0109] The real-time data also includes real-time latitude. The real-time latitude is substituted into the latitude surface fitting equation to obtain a target value. If the target value is greater than 0, a tenth lateral displacement and a tenth longitudinal displacement corresponding to the real-time latitude are obtained based on a tenth prediction domain.

[0110] comparing the real-time longitudinal displacement with an average of the first longitudinal displacement, the second longitudinal displacement, and the tenth longitudinal displacement, and comparing the real-time lateral displacement with an average of the first lateral displacement, the second lateral displacement, and the tenth lateral displacement;

[0111] If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

[0112] It is clear that the above-mentioned embodiments can be used in combination, such as comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement, the third longitudinal displacement, the fourth longitudinal displacement, the fifth longitudinal displacement, the sixth longitudinal displacement, the seventh longitudinal displacement, the eighth longitudinal displacement, the ninth longitudinal displacement and the tenth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement, the third lateral displacement, the fourth lateral displacement, the fifth lateral displacement, the sixth lateral displacement, the seventh lateral displacement, the eighth lateral displacement, the ninth lateral displacement and the tenth lateral displacement; if the real-time longitudinal displacement is greater than or equal to the average, and / or the real-time lateral displacement is greater than or equal to the average, an early warning is issued; if the real-time longitudinal displacement is less than the average, and the real-time lateral displacement is less than the average, no early warning is issued.

[0113] It can be understood that historical data and real-time data correspond to each other. For example, if the historical rainfall during surface fitting is the average daily, weekly, monthly, and annual rainfall, then the real-time rainfall substituted into the equation is also the corresponding average daily, weekly, monthly, and annual rainfall, and so on for the rest of the data.

[0114] It can also be understood that the specific monitoring positions of the landslide body stress can be set according to actual conditions, such as around and in the middle of the slope of the landslide body. The data finally used is the landslide body stress, which is the average of the monitoring results of all positions, and the rest of the data is similar.

[0115] It can also be understood that the landslide body corresponding to the historical data and the landslide body corresponding to the real-time data can be the same landslide body, or they can be landslide bodies that are similar in one or more aspects, such as the geological structure, stratigraphic lithology, geological structure, and groundwater distribution of the landslide area; the higher the similarity, the higher the prediction accuracy.

[0116] The present invention uses surface fitting to take into account rainfall, longitudinal displacement, lateral displacement, groundwater level, rainfall intensity, rock strength, rock hardness, vegetation coverage, tree inclination, landslide body stress, longitude and latitude of the highest point of the landslide body soil, the impact of these data on the occurrence of landslides, and the degree of influence of these data on each other, that is, to predict and warn mountain landslide disasters from multiple dimensions. The prediction and warning effect is good and the accuracy is high. Even if no warning is issued, the changes in the current landslide body can be seen based on the comparison results.

[0117] The embodiments of this specification also disclose an early warning system for mountain landslide disasters, which is used to implement any of the above-mentioned early warning methods for mountain landslide disasters. The early warning system for mountain landslide disasters includes: a first acquisition module, which is used to acquire historical data of the landslide body where the mountain landslide disaster occurs, wherein the historical data includes rainfall, longitudinal displacement, lateral displacement, and groundwater level;

[0118] a first fitting module, configured to construct a first matrix by taking the rainfall amount as a row vector and the lateral displacement as a column vector, then importing the longitudinal displacement, performing a surface fitting operation, obtaining a three-dimensional surface and a rainfall surface fitting equation, and recording the three-dimensional surface as a first prediction domain;

[0119] a second fitting module, configured to construct a second matrix by taking the groundwater level as a row vector and the lateral displacement as a column vector, then importing the longitudinal displacement, performing a surface fitting operation, obtaining a three-dimensional surface and a groundwater level surface fitting equation, and recording the three-dimensional surface as a second prediction domain;

[0120] The second acquisition module is used to obtain real-time data of the landslide body to be predicted and warned, wherein the real-time data includes real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level;

[0121] a first displacement acquisition module, configured to substitute the real-time rainfall into the rainfall surface fitting equation to obtain a target value, and if the target value is greater than 0, obtain a first lateral displacement and a first longitudinal displacement corresponding to the real-time rainfall based on the first prediction domain;

[0122] a second displacement acquisition module, configured to substitute the real-time groundwater level into the groundwater level surface fitting equation to obtain a target value, and if the target value is greater than 0, obtain a second lateral displacement and a second longitudinal displacement corresponding to the real-time groundwater level based on a second prediction domain;

[0123] A comparison and warning module is used to compare the real-time longitudinal displacement with the average of the first longitudinal displacement and the second longitudinal displacement, and to compare the real-time lateral displacement with the average of the first lateral displacement and the second lateral displacement; if the real-time longitudinal displacement is greater than or equal to the average, and / or the real-time lateral displacement is greater than or equal to the average, a warning is issued; if the real-time longitudinal displacement is less than the average, and the real-time lateral displacement is less than the average, no warning is issued.

[0124] It is understandable that corresponding functional modules may be added when implementing the methods of the above embodiments.

[0125] In practice, before surface fitting, the matrix can be preprocessed to remove NaN values ​​or 0 values, and then the surface fitting operation can be performed.

[0126] It should be understood that the surface fitting operation can be performed using existing software tools, such as the Curve Fitting tool in Matlab. The above modules can be data reading modules of existing data detection (acquisition) / measurement devices / sensors or systems, which can directly obtain corresponding data.

[0127] It is clear that obtaining corresponding data in the system in advance through existing equipment can obtain a large amount of test data. These test data can be simulation experiment data in the laboratory or actual measurement or operation data of the system in practice.

[0128] The above embodiments are intended to illustrate the present invention, not to limit the present invention. Therefore, changes in illustrative values ​​or substitutions of equivalent components should still fall within the scope of the present invention.

[0129] From the above detailed description, it will be clear to those skilled in the art that the present invention can indeed achieve the aforementioned objectives and is in compliance with the provisions of the Patent Law.

[0130] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as covering the preferred embodiments and all changes and modifications that fall within the scope of the invention. The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

[0131] It should be noted that the above description of the relevant processes is for illustration and purpose only and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the processes under the guidance of this specification. However, such modifications and changes are still within the scope of this specification.

[0132] The basic concepts have been described above. It will be apparent to those skilled in the art after reading this application that the above disclosures are merely illustrative and do not constitute limitations on this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and amendments to this application. Such modifications, improvements, and amendments are suggested in this application and remain within the spirit and scope of the exemplary embodiments of this application.

[0133] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or more in different places in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application may be appropriately combined.

[0134] In addition, it will be understood by those skilled in the art that various aspects of the present application can be illustrated and described by a number of patentable categories or situations, including any new and useful combination of processes, machines, products or substances, or any new and useful improvements thereto. Therefore, various aspects of the present application can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software can all be referred to as "units", "modules" or "systems". In addition, various aspects of the present application can take the form of a computer program product embodied in one or more computer-readable media, wherein computer-readable program code is contained therein.

[0135] The computer program code required for the operation of each part of the application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scale, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, conventional procedural programming languages ​​such as C programming language, Visual Basic, Fortran 2103, Per 1, COBOL 2102, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy or other programming languages. The program code can be run completely on a user's computer, or run on a user's computer as an independent software package, or partly run on a user's computer and partly run on a remote computer, or run completely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer by any network form, such as a local area network (LAN) or a wide area network (WAN), or be connected to an external computer (such as by the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0136] In addition, unless expressly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some embodiments of the invention that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the implementation of the various components described above can be embodied in a hardware device, it can also be implemented as a pure software solution, for example, installation on an existing server or mobile device.

[0137] Similarly, it should be noted that in order to simplify the presentation of this disclosure and thereby facilitate understanding of one or more of the invention's embodiments, the foregoing descriptions of the embodiments of this disclosure sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this approach should not be interpreted as reflecting an intention that the claimed subject matter requires more features than expressly recited in each claim. Rather, the subject matter of the invention may possess fewer features than the single embodiment described above.

Claims

1. A method for early warning of mountain landslide disasters, characterized in that: include: Acquiring historical data of landslide bodies where mountain landslide disasters occur, wherein the historical data include rainfall, longitudinal displacement, lateral displacement and groundwater level; The rainfall is used as a row vector and the lateral displacement is used as a column vector to form a first matrix, and then the longitudinal displacement is introduced to perform a surface fitting operation to obtain a three-dimensional surface and a rainfall surface fitting equation, and the three-dimensional surface is recorded as a first prediction domain; The groundwater level is used as a row vector and the lateral displacement is used as a column vector to form a second matrix, and then the longitudinal displacement is introduced to perform a surface fitting operation to obtain a three-dimensional surface and a groundwater level surface fitting equation, and the three-dimensional surface is recorded as a second prediction domain; Acquire real-time data of the landslide body to be predicted and warned, the real-time data including real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level; Substituting the real-time rainfall into the rainfall surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a first lateral displacement and a first longitudinal displacement corresponding to the real-time rainfall based on a first prediction domain; Substituting the real-time groundwater level into the groundwater level surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a second lateral displacement and a second longitudinal displacement corresponding to the real-time groundwater level based on a second prediction domain; comparing the real-time longitudinal displacement with the average of the first longitudinal displacement and the second longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement and the second lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

2. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes rock strength. The rock strength is used as a row vector and the lateral displacement is used as a column vector to form a third matrix. The longitudinal displacement is then introduced and a surface fitting operation is performed to obtain a three-dimensional surface and a rock strength surface fitting equation. The three-dimensional surface is recorded as a third prediction domain. The real-time data also includes real-time rock strength. The real-time rock strength is substituted into the rock strength surface fitting equation to obtain a target value. If the target value is greater than 0, a third lateral displacement and a third longitudinal displacement corresponding to the real-time rock strength are obtained based on a third prediction domain. comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the third longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the third lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

3. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes vegetation coverage, the vegetation coverage is used as a row vector, the lateral displacement is used as a column vector, a fourth matrix is ​​formed, and then the longitudinal displacement is introduced, a surface fitting operation is performed, a three-dimensional surface and a vegetation coverage surface fitting equation are obtained, and the three-dimensional surface is recorded as a fourth prediction domain; The real-time data also includes a real-time vegetation coverage rate. The real-time vegetation coverage rate is substituted into the vegetation coverage rate surface fitting equation to obtain a target value. If the target value is greater than 0, a fourth lateral displacement and a fourth longitudinal displacement corresponding to the real-time vegetation coverage rate are obtained based on a fourth prediction domain. comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the fourth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the fourth lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

4. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes rainfall intensity, the rainfall intensity is used as a row vector, the lateral displacement is used as a column vector, a fifth matrix is ​​formed, and then the longitudinal displacement is introduced, a surface fitting operation is performed, a three-dimensional surface and a rainfall intensity surface fitting equation are obtained, and the three-dimensional surface is recorded as the fifth prediction domain; The real-time data also includes real-time rainfall intensity. The real-time rainfall intensity is substituted into the rainfall intensity surface fitting equation to obtain a target value. If the target value is greater than 0, a fifth lateral displacement and a fifth longitudinal displacement corresponding to the real-time rainfall intensity are obtained based on a fifth prediction domain. comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the fifth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the fifth lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

5. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes landslide body stress, the landslide body stress is used as a row vector, the lateral displacement is used as a column vector, a sixth matrix is ​​formed, and then the longitudinal displacement is introduced, a surface fitting operation is performed, a three-dimensional surface and a landslide body stress surface fitting equation are obtained, and the three-dimensional surface is recorded as a sixth prediction domain; The real-time data also includes real-time landslide body stress, and the real-time landslide body stress is substituted into the landslide body stress surface fitting equation to obtain a target value. If the target value is greater than 0, a sixth lateral displacement and a sixth longitudinal displacement corresponding to the real-time landslide body stress are obtained based on a sixth prediction domain; comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the sixth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the sixth lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

6. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes rock hardness. The rock hardness is used as a row vector and the lateral displacement is used as a column vector to form a seventh matrix. The longitudinal displacement is then introduced to perform a surface fitting operation to obtain a three-dimensional surface and a rock hardness surface fitting equation. The three-dimensional surface is recorded as the seventh prediction domain. The real-time data also includes real-time rock hardness. The real-time rock hardness is substituted into the rock hardness surface fitting equation to obtain a target value. If the target value is greater than 0, a seventh lateral displacement and a seventh longitudinal displacement corresponding to the real-time rock hardness are obtained based on a seventh prediction domain. comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the seventh longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the seventh lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

7. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes the tree inclination, the tree inclination is used as a row vector, the lateral displacement is used as a column vector, an eighth matrix is ​​formed, and then the longitudinal displacement is introduced, a surface fitting operation is performed, a three-dimensional surface and a tree inclination surface fitting equation are obtained, and the three-dimensional surface is recorded as an eighth prediction domain; The real-time data also includes the real-time tree inclination, the real-time tree inclination is substituted into the tree inclination surface fitting equation to obtain a target value, and if the target value is greater than 0, an eighth lateral displacement and an eighth longitudinal displacement corresponding to the real-time tree inclination are obtained based on an eighth prediction domain; comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the eighth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the eighth lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

8. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes the longitude of the highest point of the landslide soil. The longitude is used as a row vector, and the lateral displacement is used as a column vector to form a ninth matrix. The longitudinal displacement is then introduced, and a surface fitting operation is performed to obtain a three-dimensional surface and a longitude surface fitting equation, and the three-dimensional surface is recorded as a ninth prediction domain. The real-time data also includes the real-time longitude. The real-time longitude is substituted into the longitude surface fitting equation to obtain a target value. If the target value is greater than 0, a ninth lateral displacement and a ninth longitudinal displacement corresponding to the real-time longitude are obtained based on a ninth prediction domain. comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the ninth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the ninth lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

9. The early warning method for mountain landslide disaster according to claim 1, characterized in that: The historical data also includes the latitude of the highest point of the landslide body soil, the latitude is used as a row vector, the lateral displacement is used as a column vector, a tenth matrix is ​​formed, and then the longitudinal displacement is introduced, a surface fitting operation is performed, a three-dimensional surface and a latitude surface fitting equation are obtained, and the three-dimensional surface is recorded as the tenth prediction domain; The real-time data also includes the real-time latitude. The real-time latitude is substituted into the latitude surface fitting equation to obtain a target value. If the target value is greater than 0, a tenth lateral displacement and a tenth longitudinal displacement corresponding to the real-time latitude are obtained based on a tenth prediction domain. comparing the real-time longitudinal displacement with the average of the first longitudinal displacement, the second longitudinal displacement and the tenth longitudinal displacement, and comparing the real-time lateral displacement with the average of the first lateral displacement, the second lateral displacement and the tenth lateral displacement; If the real-time longitudinal displacement is greater than or equal to the mean, and / or the real-time lateral displacement is greater than or equal to the mean, an early warning is issued; if the real-time longitudinal displacement is less than the mean, and the real-time lateral displacement is less than the mean, no early warning is issued.

10. An early warning system for mountain landslide disasters, characterized in that: A method for early warning of landslide disasters according to any one of claims 1 to 9, wherein the early warning system for landslide disasters comprises: A first acquisition module is used to acquire historical data of a landslide body where a mountain landslide disaster occurs, wherein the historical data includes rainfall, longitudinal displacement, lateral displacement and groundwater level; A first fitting module is used to use the rainfall as a row vector and the lateral displacement as a column vector to form a first matrix, then import the longitudinal displacement, perform a surface fitting operation, obtain a three-dimensional surface and a rainfall surface fitting equation, and record the three-dimensional surface as a first prediction domain; A second fitting module is used to use the groundwater level as a row vector and the lateral displacement as a column vector to form a second matrix, then import the longitudinal displacement, perform a surface fitting operation, obtain a three-dimensional surface and a groundwater level surface fitting equation, and record the three-dimensional surface as a second prediction domain; The second acquisition module is used to acquire real-time data of the landslide body to be predicted and warned, wherein the real-time data includes real-time rainfall, real-time longitudinal displacement, real-time lateral displacement and real-time groundwater level; A first displacement acquisition module, used for substituting the real-time rainfall into the rainfall surface fitting equation to obtain a target value, and if the target value is greater than 0, obtaining a first lateral displacement and a first longitudinal displacement corresponding to the real-time rainfall based on a first prediction domain; A second displacement acquisition module is used to substitute the real-time groundwater level into the groundwater level surface fitting equation to obtain a target value, and if the target value is greater than 0, obtain a second lateral displacement and a second longitudinal displacement corresponding to the real-time groundwater level based on a second prediction domain; A comparison and warning module is used to compare the real-time longitudinal displacement with the average of the first longitudinal displacement and the second longitudinal displacement, and to compare the real-time lateral displacement with the average of the first lateral displacement and the second lateral displacement; if the real-time longitudinal displacement is greater than or equal to the average, and / or the real-time lateral displacement is greater than or equal to the average, a warning is issued; if the real-time longitudinal displacement is less than the average, and the real-time lateral displacement is less than the average, no warning is issued.

Images