CN113536659B - Method, system and storage medium for rapidly predicting post-earthquake road disaster area - Google Patents
Method, system and storage medium for rapidly predicting post-earthquake road disaster area Download PDFInfo
- Publication number
- CN113536659B CN113536659B CN202110641538.0A CN202110641538A CN113536659B CN 113536659 B CN113536659 B CN 113536659B CN 202110641538 A CN202110641538 A CN 202110641538A CN 113536659 B CN113536659 B CN 113536659B
- Authority
- CN
- China
- Prior art keywords
- landslide
- earthquake
- road
- unit
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Security & Cryptography (AREA)
- Biomedical Technology (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Geophysics And Detection Of Objects (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method, a system and a storage medium for quickly predicting a post-earthquake road disaster area, wherein the method comprises the following steps: dividing a region of interest into a plurality of ramp units; obtaining a training set consisting of landslide units and non-landslide units based on historical seismic landslide distribution data; training based on a training set to obtain a landslide probability evaluation model; using a landslide probability evaluation model to carry out landslide probability evaluation to obtain a dangerous unit; and determining the landslide range of each dangerous unit by using a physical mechanical model to obtain the disaster area prediction result of the post-earthquake road. Compared with the prior art, the landslide probability evaluation model is trained by using a machine learning method to obtain the dangerous unit with higher landslide probability, and then the dangerous unit is researched by using a mechanical model, so that the rapid evaluation of the influence of landslide on the road in the post-earthquake research area and the accurate space positioning of the road disaster situation are realized, the rapid evaluation of a wide area space can be carried out, and a reference is provided for the formulation of earthquake emergency rescue measures.
Description
Technical Field
The invention relates to the technical field of seismic data processing, in particular to a method and a system for quickly predicting a post-seismic road disaster area and a storage medium.
Background
Earthquake landslide always causes huge economic loss and casualties. Except for directly burying houses, landslides often damage roads and block traffic, and rescue after earthquake is seriously influenced. Therefore, in order to reduce earthquake loss and ensure smooth emergency rescue work after earthquake, the influence range of the landslide after earthquake needs to be accurately predicted, particularly, the road disaster area needs to be quickly and effectively evaluated, and powerful support is provided for making an emergency rescue scheme.
In order to realize the prediction and evaluation of earthquake landslide disasters, a traditional mechanical model is firstly applied to the field of earthquake disasters, for example, a mechanical model-based earthquake landslide risk quantitative evaluation method disclosed in Chinese patent CN110390169A evaluates landslide risk through simulated earthquake information to determine a landslide danger area, thereby carrying out disaster protection in advance. However, the accuracy of the mechanical model needs to be supported by accurate data, so that the method is more suitable for landslide analysis of a single body or a local area, and the prediction effect of the method for the large-range post-earthquake-disaster area is poor.
In addition to mechanical models, with the development of information technology, machine learning methods are also widely used in earthquake disaster evaluation. The machine learning method can process a large amount of data of wide-area earthquake landslide, and construct the relationship between influencing factors and landslide, for example, the regional landslide risk evaluation method based on slope body unit and machine learning disclosed in chinese patent CN 107463991A. However, when a disaster area is evaluated using a machine learning method, since this method relies on historical data, a machine learning model having high versatility is not available in many cases when historical data is missing, and application to prediction of a disaster area is limited.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method, a system and a storage medium for quickly predicting a road affected by landslide in a post-earthquake road affected area, the method and the system are combined with a machine learning method and a physical mechanical model to realize quick prediction and evaluation of the road affected by landslide in the post-earthquake research area, a dangerous unit with high landslide probability is obtained by using the machine learning method, and then the dangerous unit is researched by using the mechanical model, so that accurate space positioning of the road affected condition after earthquake can be realized, the wide area space can be quickly evaluated, and important reference value is provided for formulating earthquake emergency rescue measures.
The purpose of the invention can be realized by the following technical scheme:
a method for quickly predicting a post-earthquake road disaster area comprises the following steps:
s1, obtaining a research area and current seismic parameters, dividing the research area into a plurality of slope units according to the elevation of the research area, obtaining seismic landslide factor data corresponding to each slope unit, and obtaining historical seismic landslide distribution data of the research area;
s2, finding a landslide unit in a research area according to historical earthquake landslide distribution data, randomly selecting a plurality of non-landslide units in the research area, and forming a training set by the landslide unit and the non-landslide units;
s3, model training is carried out on the basis of the training set by using a machine learning method, and a landslide probability evaluation model with the earthquake landslide factor data as input and the landslide probability as output is obtained;
s4, using a landslide probability evaluation model to evaluate the landslide probability of all slope units, and recording the slope units with the landslide probability larger than a preset probability threshold as dangerous units;
s5, establishing a physical mechanical model for calculating the landslide based on the energy conservation principle, calculating the landslide of each dangerous unit by using the physical mechanical model, and determining the landslide range of the dangerous unit based on the landslide and the slope direction of the dangerous unit;
and S6, obtaining a disaster area prediction result of the road after the earthquake based on the road distribution of the research area and the landslide range of the dangerous unit.
Further, the seismic landslide factor data includes: elevation, gradient, slope direction, section curvature, plane curvature, stratum lithology, fault distance, river distance, vegetation coverage index, earthquake motion peak acceleration, earthquake motion peak speed and earthquake centre distance, wherein the earthquake motion peak acceleration, the earthquake motion peak speed and the earthquake centre distance are determined according to current earthquake parameters.
Further, the slope unit in the step S1 is obtained by calculating convergence through elevation and dividing basin boundaries by using a hydrological analysis method.
Further, in step S1, landslide distribution data of an earthquake closest to the current earthquake parameter in the historical earthquakes of the study area is used as historical earthquake landslide distribution data.
Further, in the step S3, the machine learning method is a four-layer BP neural network model, and the network structure is 12-10-15-1.
Further, the preset probability threshold is 60%.
Further, the step S5 of calculating the slip distance of the dangerous unit by using the physical mechanical model specifically includes:
-δE p +E EQ ＝E DP
in the above formula, δ E p Representing potential energy of sliding mass, E EQ Representing seismic energy acquired by the sliding mass, E DP Representing the energy dissipated by the sliding body during sliding, deltaE p The calculation formula of (a) is as follows:
-δE p ＝βmgδ r
wherein beta represents the slope of the side slope of the dangerous unit, m represents the mass of the sliding soil body, the mass is estimated according to the area of the dangerous unit and the thickness of the soil layer, g represents the gravity acceleration, and delta represents the gravity acceleration r Representing a slip to be calculated;
E DP the calculation formula of (a) is as follows:
wherein mu represents the friction coefficient, and the coefficient is obtained from the friction angle of the soil body, so as to obtain the slip distance delta r The calculation formula of (a) is as follows:
wherein the seismic energy E is obtained by a sliding body EQ The calculation formula of (a) is as follows:
in the formula, alpha represents the impedance ratio of the upper soil body to the bedrock, 0.3 is taken, A represents the area of the dangerous unit, R represents the distance from the dangerous unit to the seismic source, and M represents the Leeb magnitude corresponding to the current seismic parameters.
Further, step S6 specifically includes: and obtaining a slope sliding range prediction graph of the research area based on the slope sliding range of the dangerous unit, and integrating the road distribution graph and the slope sliding range prediction graph of the research area into the same graph to obtain a disaster area prediction result of the road after the earthquake.
A post-earthquake road disaster area rapid prediction system comprises:
the system comprises a sample learning module, a risk unit evaluation module and a risk unit evaluation module, wherein the sample learning module is used for constructing a training set based on a research area, current seismic parameters and historical seismic landslide distribution data, obtaining a landslide probability evaluation model by using a machine learning method and taking seismic landslide factor data as input and landslide probability as output, and obtaining a risk unit based on the landslide probability evaluation model;
the mechanical model module is used for calculating the sliding distance of the dangerous unit according to the physical mechanical model and determining the landslide range of the dangerous unit based on the sliding distance and the slope direction of the dangerous unit;
and the area drawing module is used for obtaining the disaster area prediction result of the road after the earthquake based on the road distribution of the research area and the landslide range of the dangerous unit.
A computer storage medium having stored thereon a computer program that, when executed, implements a method for rapidly predicting a post-earthquake roadway disaster area.
Compared with the prior art, the invention has the following beneficial effects:
(1) The method is characterized in that a machine learning method and a physical mechanical model are combined to realize rapid prediction and evaluation of influence of landslide on roads in a post-earthquake research area, a dangerous unit with high landslide probability is obtained by the machine learning method, and then the mechanical model is used for researching the dangerous unit, so that accurate space positioning of disaster conditions of the post-earthquake roads can be realized, rapid evaluation of wide-area space can be performed, and important reference value is provided for making earthquake emergency rescue measures.
(2) Compared with the method of evaluating the earthquake disaster by only depending on experience, the method of the invention preliminarily determines the dangerous units by using a machine learning method, and then carries out sliding range research based on a mechanical model, thereby having higher accuracy and better applicability to the actual earthquake landslide condition.
(3) The method for determining the dangerous unit with the high landslide probability by using the machine learning method can process a large amount of uncertain data, is suitable for realizing wide-area rapid evaluation, has low requirements on required data, is convenient to acquire because the data come from station monitoring and satellite remote sensing, and is suitable for the actual condition of emergency after earthquake.
(4) Compared with the method of singly depending on a machine learning method to predict the disaster-affected area, the method of determining the dangerous unit by using the machine learning method has the advantages that the accuracy is high, the dependency on historical data is reduced, a sliding mechanism is considered after the dangerous unit is determined, a physical mechanical model is introduced, the sliding range is calculated based on energy conservation, the universality is high, and the prediction on the disaster-affected conditions of different areas after earthquake is more accurate.
(5) According to the method, the physical mechanical model based on the energy conservation principle is established, the sliding distance of the landslide is calculated, the calculation speed is higher, the wide area space can be quickly evaluated, and the universality is higher.
Drawings
FIG. 1 is a flow chart of a method for rapidly predicting a post-earthquake road disaster area;
FIG. 2 is a data distribution grid diagram of landslide factor of a historical earthquake (Ludian earthquake);
FIG. 3 is a diagram of a study region partitioning ramp unit;
FIG. 4 is a distribution diagram of landslide points of a historical earthquake (Ludian earthquake);
FIG. 5 is a schematic diagram of sample distribution in a machine learning training set;
FIG. 6 is a spatial distribution diagram of post-earthquake risk units based on machine learning;
FIG. 7 is a diagram illustrating a post-earthquake slope slip range prediction;
FIG. 8 is a diagram of a post-earthquake road disaster area prediction result;
FIG. 9 is a schematic diagram of a post-earthquake road disaster area rapid prediction system;
reference numerals are as follows: m1, a sample learning module, M2, a mechanical model module, M3 and a region drawing module.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Example 1:
in the embodiment, a county city affected by an earthquake in Yunnan province is taken as a research area, main roads in the research area are taken as research objects, earthquake parameters such as an earthquake source and an earthquake magnitude are set on the assumption that the Yunnan Ludian has the earthquake, and the application is used for evaluating and predicting the disaster situation of the roads after the earthquake.
A method for rapidly predicting a post-earthquake road disaster area is shown in figure 1 and comprises the following steps:
s1, obtaining a research area and current seismic parameters, dividing the research area into a plurality of slope units according to the elevation of the research area, obtaining seismic landslide factor data corresponding to each slope unit, and obtaining historical seismic landslide distribution data of the research area.
In step S1, the administrative ranges of five counties affected by the earthquake in Yunnan province are used as research areas, earthquake parameters such as earthquake sources and earthquake magnitudes are set on the assumption that the Yunnan Ludian has the earthquake, and earthquake landslide factor data including elevation, gradient, slope direction, section curvature, plane curvature, stratigraphic lithology, fault distance, river distance, vegetation coverage index, earthquake dynamic peak acceleration PGV, earthquake dynamic peak velocity PGA and earthquake centre distance are obtained from station monitoring and satellite remote sensing. And acquiring a grid map of the spatial distribution of the data of each seismic landslide factor, as shown in fig. 2. Based on the obtained elevation grid of the research area, a hydrological analysis tool of GIS software is utilized to extract ridges and valley lines, so that the research area is divided into more than 18 ten thousand slope units, and the slope units are basic units for subsequent earthquake landslide evaluation, as shown in FIG. 3. And acquiring the seismic landslide factor data corresponding to each slope unit.
In the historical earthquake of the research area, landslide distribution data of an earthquake closest to the current earthquake parameters is used as historical earthquake landslide distribution data, in the embodiment, a 6.5-level earthquake of Yunnan province Ludian in 2014 is selected, and a distribution diagram of landslide points 715 after the earthquake is obtained, as shown in fig. 4.
S2, finding out landslide units in the research area according to historical earthquake landslide distribution data, randomly selecting a plurality of non-landslide units in the research area, and forming a training set by the landslide units and the non-landslide units.
In this embodiment, a slope unit corresponding to a known 715-point landslide point is used as a landslide unit, 7150 random points are created by using a GIS in a non-landslide region in historical seismic landslide distribution data as non-landslide points, slope units corresponding to the non-landslide points are used as non-landslide units, and the landslide units and the non-landslide units form a training set. In this embodiment, the distribution of the samples in the constructed machine learning training set in the research area is shown in fig. 5.
S3, model training is carried out on the basis of the training set by using a machine learning method, and a landslide probability evaluation model with earthquake landslide factor data as input and landslide probability as output is obtained;
in the step S3, a BP neural network with the structure of 12-10-15-1 is constructed, seismic landslide factor data corresponding to the training concentrated landslide unit and the non-landslide unit are used as an input layer of the BP neural network, and landslide probability is used as an output result of the BP neural network to carry out model training. In the model training process, 70% of training sets are randomly selected as training samples, and 30% of training sets are selected as testing samples. The BP neural network obtains the mapping relation between 12 earthquake landslide factor data and landslide probability through training, and the landslide probability evaluation model is built.
S4, carrying out landslide probability evaluation on all slope units by using a landslide probability evaluation model, and recording the slope units with landslide probability greater than a preset probability threshold as dangerous units;
in step S4, earthquake landslide factor data corresponding to all slope units in the whole research area are extracted, a trained landslide probability evaluation model is input, and the landslide probability evaluation model outputs evaluation results of the landslide probability of each slope unit after earthquake. And taking the slope unit with the probability of more than 60% as a landslide high risk unit, and recording as a dangerous unit to obtain a spatial distribution map of the dangerous unit after the earthquake, as shown in fig. 6. In other embodiments, the magnitude of the probability threshold may be varied according to the predicted demand.
S5, establishing a physical mechanical model for calculating the landslide based on the energy conservation principle, calculating the landslide of each dangerous unit by using the physical mechanical model, and determining the landslide range of the dangerous unit based on the landslide and the slope direction of the dangerous unit;
in step S5, according to the basic principle of energy conservation, the following formula is obtained:
-δE p +E EQ ＝E DP
in the above formula, δ E p Representing the potential energy of the sliding body, E EQ Representing seismic energy acquired by the sliding mass, E DP Representing the energy dissipated by the slider during sliding;
sliding body potential energy delta E p The calculation formula of (a) is as follows:
-δE p ＝βmgδ r
wherein beta represents the slope of the side slope of the dangerous unit, m represents the mass of the sliding soil body, the mass is estimated according to the area of the dangerous unit and the thickness of the soil layer, g represents the gravity acceleration, and delta represents the gravity acceleration r Representing a slip to be calculated;
seismic energy E acquired by sliding body EQ The calculation formula of (a) is as follows:
in the above formula, E IP In the embodiment, 0.3 is taken out, A represents the area of a dangerous unit, R represents the distance from the dangerous unit to a seismic source, and M represents the Leeb magnitude corresponding to the current seismic parameter.
Energy E dissipated by the sliding body during sliding DP The calculation formula of (c) is as follows:
wherein mu represents a friction coefficient and is obtained according to the friction angle of the soil body;
the sum of the slip distance delta is obtained r The calculation formula of (c) is as follows:
and (4) taking the dangerous units obtained in the step (S4) as research objects, extracting the gradient of each dangerous unit, the effective friction angle estimated according to the lithology of the stratum and the specification and the corresponding current seismic parameters, and calculating the sliding range of the dangerous units shown in the figure 7 through a formula.
And S6, obtaining a disaster area prediction result of the road after the earthquake based on the road distribution of the research area and the landslide range of the dangerous unit.
In step S6, a slope sliding range prediction map of the research area is obtained based on the landslide range of the hazard unit, as shown in fig. 7, the road distribution map of the research area and the slope sliding range prediction map are drawn in an overlapping manner, and are integrated onto the same map to obtain a disaster area prediction result of the post-earthquake road, as shown in fig. 8.
A system for quickly predicting a disaster area of a post-earthquake road, as shown in fig. 9, includes:
the sample learning module M1 is used for constructing a training set based on a research area, current seismic parameters and historical seismic landslide distribution data, obtaining a landslide probability evaluation model taking seismic landslide factor data as input and landslide probability as output by using a machine learning method, and obtaining a dangerous unit based on the landslide probability evaluation model;
the mechanical model module M2 is used for calculating the slip distance of the dangerous unit according to the physical mechanical model and determining the landslide range of the dangerous unit based on the slip distance and the slope direction of the dangerous unit;
and the area drawing module M3 is used for obtaining the disaster area prediction result of the road after the earthquake based on the road distribution of the research area and the landslide range of the dangerous unit.
A computer storage medium having stored thereon a computer program that, when executed, implements a method for rapid prediction of post-earthquake roads in a disaster area.
According to the method, rapid prediction and evaluation of influence of landslide on roads in a post-earthquake research area are realized, a machine learning method and a physical mechanical model are combined, a dangerous unit with high landslide probability is obtained by the machine learning method, then the dangerous unit is researched by the mechanical model, the sliding range of the dangerous unit is obtained, accurate space positioning of post-earthquake road disaster situation can be realized, rapid evaluation of wide area space can be carried out, and important reference value is provided for formulating earthquake emergency rescue measures.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A method for quickly predicting a post-earthquake road disaster area is characterized by comprising the following steps:
s1, obtaining a research area and current seismic parameters, dividing the research area into a plurality of slope units according to the elevation of the research area, obtaining seismic landslide factor data corresponding to each slope unit, and obtaining historical seismic landslide distribution data of the research area;
s2, finding a landslide unit in a research area according to historical earthquake landslide distribution data, randomly selecting a plurality of non-landslide units in the research area, and forming a training set by the landslide unit and the non-landslide units;
s3, model training is carried out on the basis of the training set by using a machine learning method, and a landslide probability evaluation model with earthquake landslide factor data as input and landslide probability as output is obtained;
s4, using a landslide probability evaluation model to evaluate the landslide probability of all slope units, and recording the slope units with the landslide probability larger than a preset probability threshold as dangerous units;
s5, establishing a physical mechanical model for calculating the landslide based on the energy conservation principle, calculating the landslide of each dangerous unit by using the physical mechanical model, and determining the landslide range of the dangerous unit based on the landslide and the slope direction of the dangerous unit;
and S6, obtaining a disaster area prediction result of the road after the earthquake based on the road distribution of the research area and the landslide range of the dangerous unit.
2. The method for rapidly predicting the disaster area of the post-earthquake road according to claim 1, wherein the earthquake landslide factor data comprises: elevation, gradient, slope direction, section curvature, plane curvature, stratum lithology, fault distance, river distance, vegetation coverage index, earthquake peak acceleration, earthquake peak speed and earthquake centre distance, wherein the earthquake peak acceleration, the earthquake peak speed and the earthquake centre distance are determined according to current earthquake parameters.
3. The method for rapidly predicting the disaster area of the post-earthquake road according to claim 1, wherein the slope unit in the step S1 is obtained by converging and dividing the boundaries of the drainage basin through elevation calculation by using a hydrological analysis method.
4. The method for rapidly predicting the disaster area of the post-earthquake road according to claim 1, wherein in the step S1, landslide distribution data of an earthquake in the historical earthquake of the research area, which is closest to the current earthquake parameter, is used as historical earthquake landslide distribution data.
5. The method for rapidly predicting the disaster area of the post-earthquake road according to claim 1, wherein the machine learning method used in the step S3 is a four-layer BP neural network model, and the network structure is 12-10-15-1.
6. The method as claimed in claim 1, wherein the preset probability threshold is 60%.
7. The method for rapidly predicting the disaster area of the post-earthquake road according to claim 1, wherein the step S5 of calculating the slip distance of the dangerous unit by using a physical mechanical model specifically comprises the following steps:
-δE p +E EQ ＝E DP
in the above-mentioned formula, the compound has the following structure,δE p representing the potential energy of the sliding body, E EQ Representing seismic energy acquired by the sliding mass, E DP Representing the energy dissipated by the sliding body during sliding, deltaE p The calculation formula of (a) is as follows:
-δE p ＝βmgδ r
where β represents the slope of the hazard unit, m represents the mass of the sliding mass, g represents the acceleration of gravity, δ r Representing a slip to be calculated;
E DP the calculation formula of (a) is as follows:
where μ represents the coefficient of friction, and the slip δ is obtained in summary r The calculation formula of (a) is as follows:
wherein the seismic energy E is obtained by a sliding body EQ The calculation formula of (a) is as follows:
in the above formula, α represents the impedance ratio of the upper soil and the bedrock, a represents the area of the dangerous unit, R represents the distance from the dangerous unit to the seismic source, and M represents the corresponding richter magnitude of the current seismic parameter.
8. The method for rapidly predicting the post-earthquake road disaster area according to claim 1, wherein the step S6 specifically comprises: and obtaining a slope sliding range prediction graph of the research area based on the slope sliding range of the dangerous unit, and integrating the road distribution graph and the slope sliding range prediction graph of the research area into the same graph to obtain a disaster area prediction result of the road after the earthquake.
9. A system for rapidly predicting a post-earthquake road disaster area, based on the method for rapidly predicting a post-earthquake road disaster area according to any one of claims 1 to 8, comprising:
the system comprises a sample learning module (M1) and a risk unit evaluation module, wherein the sample learning module is used for constructing a training set based on a research area, current seismic parameters and historical seismic landslide distribution data, obtaining a landslide probability evaluation model taking seismic landslide factor data as input and landslide probability as output by using a machine learning method, and obtaining a risk unit based on the landslide probability evaluation model;
the mechanical model module (M2) is used for calculating the slip distance of the dangerous unit according to the physical mechanical model and determining the landslide range of the dangerous unit based on the slip distance and the slope direction of the dangerous unit;
and the region drawing module (M3) is used for obtaining a disaster area prediction result of the road after the earthquake based on the road distribution of the research region and the landslide range of the dangerous unit.
10. A computer storage medium having a computer program stored thereon, wherein the computer program when executed implements the method for rapidly predicting a post-earthquake road disaster area according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110641538.0A CN113536659B (en) | 2021-06-09 | 2021-06-09 | Method, system and storage medium for rapidly predicting post-earthquake road disaster area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110641538.0A CN113536659B (en) | 2021-06-09 | 2021-06-09 | Method, system and storage medium for rapidly predicting post-earthquake road disaster area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113536659A CN113536659A (en) | 2021-10-22 |
| CN113536659B true CN113536659B (en) | 2022-11-04 |
Family
ID=78095745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110641538.0A Active CN113536659B (en) | 2021-06-09 | 2021-06-09 | Method, system and storage medium for rapidly predicting post-earthquake road disaster area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536659B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836749B (en) * | 2021-10-26 | 2024-04-05 | 新兴际华科技发展有限公司 | Earthquake rescue virtual exercise system |
| CN116341901B (en) * | 2023-03-07 | 2023-09-12 | 重庆大学 | Integrated evaluation method for landslide surface domain-monomer hazard early warning |
| CN116307270B (en) * | 2023-05-16 | 2023-08-22 | 南京信息工程大学 | Method and system for evaluating casualties influenced by landslide chain type disasters induced by storm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613096A (en) * | 2020-12-15 | 2021-04-06 | 应急管理部国家自然灾害防治研究院 | Geological disaster evaluation method for different stages before and after strong earthquake |
| CN112767219A (en) * | 2021-02-03 | 2021-05-07 | 上海交通大学 | Post-earthquake disaster population rapid space assessment method and system based on machine learning |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107463991A (en) * | 2017-06-28 | 2017-12-12 | 西南石油大学 | A kind of Regional Landslide method for evaluating hazard based on slopes unit and machine learning |
| CN108228988A (en) * | 2017-12-25 | 2018-06-29 | 重庆大学 | A kind of Slope Displacement Prediction and slip method of discrimination based on big data driving |
| CN109359738A (en) * | 2018-10-19 | 2019-02-19 | 西南交通大学 | A kind of Landslide hazard appraisal procedure based on QPSO-BP neural network |
| CN110376639A (en) * | 2019-07-12 | 2019-10-25 | 清华大学 | Earthquake-landslide speed based on actual measurement earthquake motion, which is called the score, analyses method and device |
| CN111199313A (en) * | 2019-12-26 | 2020-05-26 | 航天信息股份有限公司 | Method and system for predicting landslide accumulated displacement trend based on neural network |
| CN111563621B (en) * | 2020-04-30 | 2023-05-30 | 中国地质调查局武汉地质调查中心 | Method, system, device and storage medium for evaluating danger of regional landslide |
-
2021
- 2021-06-09 CN CN202110641538.0A patent/CN113536659B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613096A (en) * | 2020-12-15 | 2021-04-06 | 应急管理部国家自然灾害防治研究院 | Geological disaster evaluation method for different stages before and after strong earthquake |
| CN112767219A (en) * | 2021-02-03 | 2021-05-07 | 上海交通大学 | Post-earthquake disaster population rapid space assessment method and system based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113536659A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113536659B (en) | Method, system and storage medium for rapidly predicting post-earthquake road disaster area | |
| Chousianitis et al. | Predictive model of Arias intensity and Newmark displacement for regional scale evaluation of earthquake-induced landslide hazard in Greece | |
| Chauhan et al. | Landslide susceptibility zonation of the Chamoli region, Garhwal Himalayas, using logistic regression model | |
| Saroglou et al. | UAV-based mapping, back analysis and trajectory modeling of a coseismic rockfall in Lefkada island, Greece | |
| Li et al. | Rainfall and earthquake-induced landslide susceptibility assessment using GIS and Artificial Neural Network | |
| KR100982447B1 (en) | Landslide occurrence prediction system and predicting method using the same | |
| CN113283802A (en) | Landslide risk assessment method for complex and difficult mountain area | |
| Irwansyah et al. | Earthquake hazard zonation using peak ground acceleration (PGA) approach | |
| CN111932591B (en) | Method and system for remote sensing intelligent extraction of typical geological disasters | |
| CN113251914A (en) | Surface deformation prediction method combining InSAR technology and long-term memory neural network | |
| Sanchez et al. | A 3-D lithospheric model of the Caribbean-South American plate boundary | |
| CN113378396A (en) | Early identification method for hidden danger points of small watershed geological disaster | |
| CN113780741B (en) | Landslide risk evaluation method, system and storage medium based on slope characteristics | |
| Ayad et al. | Quantification of the disturbances of phosphate series using the box-counting method on geoelectrical images (Sidi Chennane, Morocco) | |
| CN112064617B (en) | Soil-stone mixture foundation quality detection method | |
| Bretzler et al. | Chapter A2 | |
| Yu et al. | Research on site classification method based on BP neural network | |
| Achour et al. | Modelling uncertainty of stream networks derived from elevation data using two free softwares: R and saga | |
| Ihsan et al. | The comparison of spatial models in Peak Ground Acceleration (PGA) study | |
| JP2022053155A (en) | Earthquake motion evaluation model generation method, earthquake motion evaluation model generation device, earthquake motion evaluation method, and earthquake motion evaluation device | |
| Rifai et al. | Data mining applied for liquefaction mapping and prediction learn from Palu Earthquakes | |
| Bouguerba et al. | Geostatistical analysis of spatial variability of the liquefaction potential–Case study of a site located in Algiers (Algeria) | |
| CN114330723B (en) | Soil regional frost heaving amount deduction method | |
| CN117572509B (en) | Mining method of hydrothermal pulse type mineral product related to porphyry activities | |
| CN116797755B (en) | Modeling method for multi-time-space three-dimensional geological structure of mixed rock zone |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |