CN116956046A - Earthquake landslide hazard analysis method and device based on cyclic neural network - Google Patents
Earthquake landslide hazard analysis method and device based on cyclic neural network Download PDFInfo
- Publication number
- CN116956046A CN116956046A CN202311147477.8A CN202311147477A CN116956046A CN 116956046 A CN116956046 A CN 116956046A CN 202311147477 A CN202311147477 A CN 202311147477A CN 116956046 A CN116956046 A CN 116956046A
- Authority
- CN
- China
- Prior art keywords
- slope
- analyzed
- information
- earthquake
- landslide
- 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.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 51
- 238000004458 analytical method Methods 0.000 title claims abstract description 41
- 125000004122 cyclic group Chemical group 0.000 title claims abstract description 19
- 238000006073 displacement reaction Methods 0.000 claims abstract description 90
- 230000001133 acceleration Effects 0.000 claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000012502 risk assessment Methods 0.000 claims abstract description 20
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 26
- 230000000306 recurrent effect Effects 0.000 claims description 25
- 238000001228 spectrum Methods 0.000 claims description 24
- 239000002689 soil Substances 0.000 claims description 14
- 230000003595 spectral effect Effects 0.000 claims description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000013075 data extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Geophysics And Detection Of Objects (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The application provides a method and a device for analyzing earthquake landslide hazard based on a cyclic neural network, and relates to the field of earthquake landslide analysis, wherein the method comprises the following steps: acquiring an initial earthquake motion data set, each rotation angle and geological information of a slope to be analyzed; extracting an initial seismic data set to obtain a seismic data input set; forming a model training input data set according to the earthquake motion data input set and a preset critical acceleration data set; calculating each rotation angle according to a preset landslide model to obtain a model training output data set; substituting the model training input data set and the model training output data set into a preset bidirectional circulating neural network for training to obtain an earthquake landslide displacement prediction model; and inputting the geological information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain the designated slope permanent displacement value of the slope to be analyzed. According to the method, the influence of the slope direction on the earthquake landslide risk analysis is considered, and the prediction accuracy is improved.
Description
Technical Field
The application relates to the field of earthquake landslide analysis, in particular to an earthquake landslide risk analysis method and device based on a cyclic neural network.
Background
At present, earthquake landslide disasters are serious in China, are an objective reality which cannot be changed currently, and have the characteristics of wide range, large scale, difficult determination of occurrence areas and the like. With the increase of population, land development, resource utilization and acceleration of urbanization, more mountainous areas are brought into urban planning, and buildings above mountainous areas bear more complicated and severe risks of earthquake landslide, so that risk analysis on the earthquake landslide is necessary. In the existing earthquake landslide risk analysis, the influence of the slope direction on landslide displacement is not considered, so that the prediction accuracy is poor and the prediction effect is poor. Therefore, there is a need for a method for analyzing the risk of an earthquake landslide based on a cyclic neural network, which needs to consider the influence of the slope direction on the analysis of the risk of the earthquake landslide on the one hand, and to improve the prediction accuracy and ensure the prediction effect on the other hand.
Disclosure of Invention
The application aims to provide a seismic landslide risk analysis method and device based on a cyclic neural network so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the application is as follows:
in a first aspect, the application provides a method for analyzing earthquake landslide hazard based on a cyclic neural network, which comprises the following steps:
acquiring an initial earthquake motion data set, each rotation angle and geological information of a slope to be analyzed;
extracting the initial seismic data set to obtain a seismic data input set;
forming a model training input data set according to the earthquake motion data input set and a preset critical acceleration data set;
calculating each rotation angle according to a preset landslide model to obtain a model training output data set;
substituting the model training input data set and the model training output data set into a preset bidirectional cyclic neural network for training to obtain an earthquake landslide displacement prediction model;
inputting the geological information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed;
and carrying out earthquake landslide hazard analysis according to the designated slope permanent displacement value of the slope to be analyzed.
In a second aspect, the present application further provides an earthquake landslide hazard analysis device based on a recurrent neural network, including:
the acquisition module is used for acquiring an initial earthquake motion data set, each rotation angle and geological information of the slope to be analyzed;
the first processing module is used for extracting the initial earthquake motion data set to obtain an earthquake motion data input set;
the second processing module is used for forming a model training input data set according to the earthquake motion data input set and a preset critical acceleration data set;
the third processing module is used for calculating the rotation angles according to a preset landslide model to obtain a model training output data set;
the fourth processing module is used for substituting the model training input data set and the model training output data set into a preset bidirectional circulating neural network for training to obtain an earthquake landslide displacement prediction model;
the fifth processing module is used for inputting the geological information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed;
and the analysis module is used for carrying out earthquake landslide hazard analysis according to the designated slope permanent displacement value of the slope to be analyzed.
The beneficial effects of the application are as follows:
in the earthquake landslide hazard analysis method, the potential influence of the slope direction on landslide displacement is considered, so that the permanent displacement of the earthquake landslide can be predicted more truly and reasonably, further the earthquake landslide hazard assessment can be performed on the side slope more accurately, and the basis of earthquake risk management and decision can be better provided for earthquake-resistant designers or government decision-making departments. In addition, the existing permanent displacement prediction model mainly adopts a simple regression method, prediction precision and generalization capability are to be improved, and the method is based on a bidirectional circulating neural network for data training and has the advantages of high precision, strong generalization capability, good prediction effect, small error and the like on the basis of large-volume sample training. On the basis, the advantages of processing sequence data by the cyclic neural network can be exerted, such as effectively capturing angle information in the sequence, flexibly processing variable-length input and output and having memory capacity. By the method, landslide displacement values in all directions (0-360 degrees) of the side slope can be rapidly and accurately predicted, landslide hazard analysis is further carried out on a potential earthquake area, and earthquake landslide hazard risks can be predicted and estimated more truly and reasonably.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a seismic landslide hazard analysis method based on a recurrent neural network according to an embodiment of the application;
FIG. 2 is a schematic diagram of a seismic landslide hazard analysis device based on a recurrent neural network according to an embodiment of the application;
FIG. 3 is a schematic view of a fifth process module according to the present application;
FIG. 4 is a schematic diagram of a seismic landslide hazard analysis device based on a recurrent neural network according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a two-way recurrent neural network framework according to the present application;
the marks in the figure:
800. an earthquake landslide hazard analysis device based on a cyclic neural network; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component; 901. an acquisition module; 902. a first processing module; 903. a second processing module; 904. a third processing module; 905. a fourth processing module; 906. a fifth processing module; 907. an analysis module; 9041. a first acquisition unit; 9042. a first calculation unit; 9043. a second calculation unit; 9044. a third calculation unit; 9061. a second acquisition unit; 9062. a fourth calculation unit; 9063. a fifth calculation unit; 9064. a sixth calculation unit; 90631. a first computing subunit; 90632. a second computing subunit; 90633. a third calculation subunit; 90634. a fourth calculation subunit; 9071. a first analysis sub-module; 9072. a second analysis sub-module; 90711. a third acquisition unit; 90712. a seventh calculation unit; 90713. an eighth calculation unit; 90721. a first processing unit; 90722. a second processing unit; 90723. and a third processing unit.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a seismic landslide risk analysis method based on a cyclic neural network.
Referring to fig. 1, the method is shown to include steps S1 to S7, specifically:
s1, acquiring an initial earthquake motion data set, various rotation angles and geological information of a slope to be analyzed;
in step S1, the initial seismic data set is collected in a preset seismic database according to a preset standard, specifically including: accessing the global existing earthquake motion database NGA-west2, collecting earthquake motion data, and eliminating aftershocks and earthquake motion records of non-free fields. The preset standard can be used for selecting shallow crustal earthquake motion records: (1) moment vibration levelThe method comprises the steps of carrying out a first treatment on the surface of the (2) Fault distance->The method comprises the steps of carrying out a first treatment on the surface of the (3) The ground peak acceleration PGA is more than or equal to 0.001g. And collecting a plurality of pieces of earthquake motion data meeting the preset standard conditions, wherein the quantity of the earthquake motion data can be 3000 pieces.
In step S1, each rotation angle is 0 ° in the positive X-axis direction in the cartesian coordinate system, and the horizontal earthquake motion can be simulated by rotating the horizontal earthquake motion every 2 ° counterclockwise to simulate the slope in all directions in the horizontal plane.
S2, extracting the initial seismic data set to obtain a seismic data input set;
in step S2, data extraction is performed according to the following table 1, specifically: and extracting corresponding parameter information from the initial seismic data set according to the table 1 to obtain a seismic data input set.
TABLE 1
S3, forming a model training input data set according to the earthquake motion data input set and a preset critical acceleration data set;
in step S3, a preset critical acceleration data set is set, specifically: the slope critical acceleration is set to a range of 0.05 to 0.5, and data values are extracted once every 0.01 interval of the slope critical acceleration.
And then, forming a model training input data set according to the seismic data input set and a preset critical acceleration data set.
S4, calculating the rotation angles according to a preset landslide model to obtain a model training output data set;
in step S4, to clarify the specific calculation of the model training output data set, the preset landslide model includes a slope model and a landslide displacement solving model, including S41 to S44, specifically including:
s41, acquiring acceleration information before rotation of a plurality of earthquake spectrums;
s42, carrying out horizontal vector decomposition on the acceleration information before each seismic spectrum rotates to obtain the acceleration vector quantity information before each seismic spectrum rotates;
s43, calculating the rotation angle and the acceleration component vector information before each earthquake motion spectrum rotates through the slope model to obtain spectrum acceleration values of different slopes;
in step S43, the slope model is:
；
in the above-mentioned method, the step of,a spectral acceleration value representing the ith seismic spectrum at the jth rotation angle; i represents the acceleration of the ith seismic spectrum; j represents a rotation angle +.>；/>A horizontal direction first acceleration component vector representing the acceleration of the ith seismic spectrum; />A horizontal direction second acceleration component vector representing the acceleration of the ith seismic spectrum;indicating the slope direction asθ j The corresponding earthquake motion rotation angle +.>。
S44, calculating the spectral acceleration values of the different slope directions through the landslide displacement solving model to obtain a model training output data set, wherein the model training output data set corresponds to landslide displacement values of different slope directions in a horizontal plane.
In step S44, the landslide displacement solving model adopts a Newmark model, which is a prior art in the field and is not explained here.
S5, substituting the model training input data set and the model training output data set into a preset bidirectional circulating neural network for training to obtain an earthquake landslide displacement prediction model;
as shown in fig. 5, in step S5, a schematic diagram of a bidirectional recurrent neural network framework according to the present application is shown. In the construction process, a Leaky ReLU is selected as an activation function, adam is selected as an optimizer, and then the model training input data set and the model training output data set are substituted into a preset bidirectional circulating neural network for training, model parameters are obtained, and a seismic landslide displacement prediction model is obtained.
S6, inputting the geological information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed;
in step S6, in order to define a specific calculation process, including S61 to S64, the geological information of the slope to be analyzed includes slope position information, slope information and intra-slope attribute information, specifically includes:
s61, acquiring side slope position information, slope body information and slope inner attribute information of a side slope to be analyzed, wherein the slope body information comprises slope height and slope angle, and the slope inner attribute information comprises slope inner soil weight, slope inner water weight, slope inner soil cohesive force and slope inner soil mass inner friction angle;
s62, calculating the slope body information and the in-slope attribute information through a preset slope characteristic model to obtain actual critical acceleration information of the slope to be analyzed;
in step S62, the preset slope characteristic model is:
；
in the above-mentioned method, the step of,representing actual critical acceleration information of the slope to be analyzed;tindicating a slope height;αrepresenting a slope angle;γrepresenting the soil weight in the side slope;γ w the water weight in the slope is represented;c'representing clay cohesion in the side slope;φ'representing the internal friction angle of soil in the side slope;mrepresenting the preset coefficient of the groundwater level.
S63, calculating the side slope position information through a preset earthquake fault source model to obtain earthquake motion information of the side slope to be analyzed;
step S63 includes steps S631 to S634, and specifically includes:
s631, determining earthquake information of the region where the side slope to be analyzed is located according to the side slope position information;
s632, performing magnitude screening according to the seismic information of the region where the side slope to be analyzed is located, and obtaining magnitude occurrence times;
s633, calculating the occurrence times of the earthquake magnitude through the preset earthquake fault source model to obtain initial earthquake motion information of the slope to be analyzed;
in step S633, the preset seismic fault source model is an existing monte carlo model. Assuming that the earthquake occurs to follow poisson distribution, when the Monte Carlo model is adopted for simulation, the simulation of the earthquake catalogue is carried out for a plurality of times (for example, the simulation times are 1000 times) within a certain period (for example, the earthquake catalogue is set to 100 years), wherein the simulated earthquake time, the magnitude and the position are included in each earthquake catalogue, and thus the initial earthquake motion information of the side slope to be analyzed is obtained.
S634, extracting the initial earthquake motion information of the slope to be analyzed to obtain the earthquake motion information of the slope to be analyzed.
And based on the initial earthquake motion information of the side slope to be analyzed, carrying out data extraction according to 12 earthquake parameters in the table 1 to obtain the earthquake motion information of the side slope to be analyzed.
S64, inputting the actual critical acceleration information of the slope to be analyzed and the earthquake motion information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed.
And S7, carrying out earthquake landslide hazard analysis according to the designated slope permanent displacement value of the slope to be analyzed.
In step S7, in order to determine the risk of the earthquake landslide from the annual overrun ratio of the landslide displacement value, step S7 includes S711 to S713, specifically including:
s711, acquiring a first probability density function when the moment magnitude is a first preset value and a second probability density function when the fault distance is a second preset value;
s712, solving the first probability density function, the second probability density function and the designated slope permanent displacement value of the slope to be analyzed through a preset judgment model to obtain the annual overrun rate of the landslide displacement value;
in step S712, the preset determination model is:
；
in the above-mentioned method, the step of,indicating exceeding a specific landslide displacement value +.>The annual overrun of the time landslide displacement value; />The overrun rate of the preset year is indicated,mindicating that moment magnitude is selected as variablem；/>Representing the fault distance as a variable +.>；/>Indicating when to setm=M w Andr=R rup time shiftDExceeding a given landslide displacement value +.>Probability of (2); />Representing a first probability density function;representing a second probability density function;Dand the permanent displacement value of the designated slope direction of the slope to be analyzed is represented.
S713, when the annual overrun of the landslide displacement value is larger than the preset annual overrun, the slope to be analyzed is in a dangerous state.
In step S7, in order to determine the risk of the earthquake landslide from the landslide displacement risk curve, step S7 includes S721 to S723, specifically:
s721, drawing a displacement curve according to the specified slope permanent displacement value of the slope to be analyzed to obtain a displacement risk evaluation curve;
s722, drawing a displacement curve according to the preset displacement value to obtain a displacement risk reference curve;
s723, when the offset value between the displacement risk evaluation curve and the displacement risk reference curve is larger than a preset offset value, the slope to be analyzed is in a dangerous state.
Example 2:
as shown in fig. 2, the present embodiment provides an earthquake landslide hazard analysis apparatus based on a recurrent neural network, the apparatus including:
the acquisition module 901 is used for acquiring an initial earthquake motion data set, each rotation angle and geological information of a slope to be analyzed;
a first processing module 902, configured to extract the initial seismic data set to obtain a seismic data input set;
a second processing module 903, configured to form a model training input data set according to the seismic data input set and a preset critical acceleration data set;
the third processing module 904 is configured to calculate each rotation angle according to a preset landslide model, so as to obtain a model training output data set;
the fourth processing module 905 is configured to substitute the model training input data set and the model training output data set into a preset bidirectional circulating neural network to perform training, so as to obtain a seismic landslide displacement prediction model;
a fifth processing module 906, configured to input geological information of the slope to be analyzed into the earthquake landslide displacement prediction model, to obtain a specified slope permanent displacement value of the slope to be analyzed;
and the analysis module 907 is used for carrying out earthquake landslide hazard analysis according to the designated slope permanent displacement value of the slope to be analyzed.
In one disclosed implementation of the present application, the third processing module 904 includes:
a first acquiring unit 9041 for acquiring acceleration information before rotation of a plurality of pieces of seismic spectrum;
the first calculating unit 9042 is configured to perform horizontal vector decomposition on the acceleration information before rotation of each seismic spectrum, so as to obtain acceleration component information before rotation of each seismic spectrum;
the second calculating unit 9043 is configured to calculate the rotation angle and the acceleration component vector information before rotation of each seismic spectrum through the slope model, so as to obtain spectrum acceleration values of different slopes;
and a third calculation unit 9044, configured to calculate the spectral acceleration values of the different slope directions through the landslide displacement solution model, to obtain a model training output data set, where the model training output data set corresponds to the landslide displacement values of each different slope direction in the horizontal plane.
As shown in fig. 3, in one implementation of the disclosed application, the fifth processing module 906 includes:
a second obtaining unit 9061, configured to obtain slope position information, slope information, and slope inner attribute information of a slope to be analyzed, where the slope information includes a slope height and a slope angle, and the slope inner attribute information includes a slope inner soil weight, a slope inner water weight, a slope inner soil cohesion, and a slope inner soil mass inner friction angle;
a fourth calculating unit 9062, configured to calculate the slope information and the intra-slope attribute information through a preset slope feature model, to obtain actual critical acceleration information of the slope to be analyzed;
a fifth calculating unit 9063, configured to calculate the slope position information through a preset seismic fault source model, to obtain seismic information of the slope to be analyzed;
and a sixth calculation unit 9064, configured to input the actual critical acceleration information of the slope to be analyzed and the seismic vibration information of the slope to be analyzed into the seismic landslide displacement prediction model, so as to obtain a specified slope permanent displacement value of the slope to be analyzed.
In one embodiment of the disclosed method, the fifth calculating unit 9063 includes:
the first calculating subunit 90631 is configured to determine seismic information of an area where the side slope to be analyzed is located according to the side slope position information;
the second calculating subunit 90632 is used for performing magnitude screening according to the seismic information of the region where the side slope to be analyzed is located, so as to obtain magnitude occurrence times;
a third calculation subunit 90633, configured to calculate the number of times of occurrence of the magnitude through the preset seismic fault source model, to obtain initial seismic vibration information of the slope to be analyzed;
and the fourth computing subunit 90634 is configured to extract the initial seismic information of the slope to be analyzed, and obtain the seismic information of the slope to be analyzed.
In one disclosed implementation, the analysis module 907 includes a first analysis submodule 9071, and the first analysis submodule 9071 includes:
a third obtaining unit 90711, configured to obtain a first probability density function when the moment magnitude is a first preset value and a second probability density function when the fault distance is a second preset value;
a seventh calculation unit 90712, configured to solve the first probability density function, the second probability density function, and the specified slope permanent displacement value of the slope to be analyzed by using a preset judgment model, so as to obtain an annual overrun ratio of the landslide displacement value;
and an eighth calculating unit 90713, configured to, when the annual overrun of the landslide displacement value is greater than a preset annual overrun, determine that the slope to be analyzed is in a dangerous state.
In one disclosed embodiment, the analysis module 907 further comprises a second analysis sub-module 9072, the second analysis sub-module 9072 comprising:
the first processing unit 90721 is used for drawing a displacement curve according to the specified slope permanent displacement value of the slope to be analyzed to obtain a displacement risk evaluation curve;
the second processing unit 90722 is configured to perform displacement curve drawing according to the preset displacement value to obtain a displacement risk reference curve;
and the third processing unit 90723 is configured to, when the offset value between the displacement risk evaluation curve and the displacement risk reference curve is greater than a preset offset value, make the slope to be analyzed be in a dangerous state.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
Example 3:
corresponding to the above method embodiment, a device for analyzing the risk of earthquake landslide based on a recurrent neural network is further provided in this embodiment, and a device for analyzing the risk of earthquake landslide based on a recurrent neural network described below and a method for analyzing the risk of earthquake landslide based on a recurrent neural network described above may be referred to correspondingly.
Fig. 4 is a block diagram illustrating a seismic landslide hazard analysis apparatus 800 based on a recurrent neural network, in accordance with an exemplary embodiment. As shown in fig. 4, the seismic landslide hazard analysis apparatus 800 based on the recurrent neural network may include: a processor 801, a memory 802. The recurrent neural network-based earthquake landslide hazard analysis apparatus 800 may further include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the seismic landslide risk analysis device 800 based on the recurrent neural network, so as to complete all or part of the steps in the seismic landslide risk analysis method based on the recurrent neural network. The memory 802 is used to store various types of data to support the operation of the seismic landslide risk analysis device 800 over a recurrent neural network, which may include, for example, instructions for any application or method operating on the seismic landslide risk analysis device 800 over a recurrent neural network, as well as application-related data such as contact data, transceived messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the seismic landslide hazard analysis device 800 and other devices based on a recurrent neural network. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, a cyclic neural network-based seismic landslide risk analysis device 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (DigitalSignal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing a cyclic neural network-based seismic landslide risk analysis method as described above.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of a method of seismic landslide risk analysis based on a recurrent neural network as described above. For example, the computer readable storage medium may be the memory 802 including program instructions described above, which are executable by the processor 801 of a recurrent neural network-based seismic landslide risk analysis device 800 to perform a recurrent neural network-based seismic landslide risk analysis method described above.
Example 4:
corresponding to the above method embodiment, a readable storage medium is further provided in this embodiment, and a readable storage medium described below and a seismic landslide risk analysis method based on a recurrent neural network described above may be referred to correspondingly.
A readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method for seismic landslide risk analysis based on a recurrent neural network of the above method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. The earthquake landslide hazard analysis method based on the cyclic neural network is characterized by comprising the following steps of:
acquiring an initial earthquake motion data set, each rotation angle and geological information of a slope to be analyzed;
extracting the initial seismic data set to obtain a seismic data input set;
forming a model training input data set according to the earthquake motion data input set and a preset critical acceleration data set;
calculating each rotation angle according to a preset landslide model to obtain a model training output data set;
substituting the model training input data set and the model training output data set into a preset bidirectional cyclic neural network for training to obtain an earthquake landslide displacement prediction model;
inputting the geological information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed;
and carrying out earthquake landslide hazard analysis according to the designated slope permanent displacement value of the slope to be analyzed.
2. The seismic landslide risk analysis method based on the cyclic neural network according to claim 1, wherein the rotation angles are calculated according to a preset landslide model to obtain a model training output data set, the preset landslide model comprises a slope model and a landslide displacement solving model, and the method comprises the following steps:
acquiring acceleration information before rotation of a plurality of earthquake spectrums;
performing horizontal vector decomposition on the acceleration information before each seismic spectrum rotates to obtain the acceleration component information before each seismic spectrum rotates;
calculating the rotation angle and the acceleration component vector information before each earthquake motion spectrum rotates through the slope model to obtain spectrum acceleration values of different slopes;
and calculating the spectral acceleration values of different slope directions through the landslide displacement solving model to obtain a model training output data set, wherein the model training output data set corresponds to the landslide displacement values of different slope directions in a horizontal plane.
3. The method for analyzing the risk of the earthquake landslide based on the cyclic neural network according to claim 1, wherein the geological information of the slope to be analyzed is input into the earthquake landslide displacement prediction model to obtain a specified slope permanent displacement value of the slope to be analyzed, the geological information of the slope to be analyzed comprises slope position information, slope body information and in-slope attribute information, and the method comprises the following steps:
acquiring side slope position information, slope body information and slope inner attribute information of a side slope to be analyzed, wherein the slope body information comprises a slope height and a slope angle, and the slope inner attribute information comprises the slope inner soil weight, the slope inner water weight, the slope inner soil cohesion and the inner friction angle of a slope inner soil body;
calculating the slope body information and the slope inner attribute information through a preset slope characteristic model to obtain actual critical acceleration information of the slope to be analyzed;
calculating the side slope position information through a preset earthquake fault source model to obtain earthquake motion information of the side slope to be analyzed;
and inputting the actual critical acceleration information of the slope to be analyzed and the earthquake motion information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed.
4. The method for analyzing the risk of a landslide based on a recurrent neural network according to claim 3, wherein the calculating the slope position information by a preset seismic fault source model to obtain the earthquake motion information of the slope to be analyzed comprises the following steps:
determining earthquake information of the region where the side slope to be analyzed is located according to the side slope position information;
performing magnitude screening according to the seismic information of the region where the side slope to be analyzed is located, so as to obtain magnitude occurrence times;
calculating the occurrence times of the earthquake magnitude through the preset earthquake fault source model to obtain initial earthquake motion information of the slope to be analyzed;
and extracting the initial earthquake motion information of the slope to be analyzed to obtain the earthquake motion information of the slope to be analyzed.
5. The method for analyzing the risk of the earthquake landslide based on the cyclic neural network according to claim 1, wherein the method for analyzing the risk of the earthquake landslide according to the specified slope permanent displacement value of the slope to be analyzed comprises the following steps:
acquiring a first probability density function when the moment-magnitude is a first preset value and a second probability density function when the fault distance is a second preset value;
solving the first probability density function, the second probability density function and the specified slope permanent displacement value of the slope to be analyzed through a preset judgment model to obtain the annual overrun of the landslide displacement value;
and when the annual overrun of the landslide displacement value is larger than the preset annual overrun, the slope to be analyzed is in a dangerous state.
6. An earthquake landslide hazard analysis device based on a cyclic neural network, which is characterized by comprising:
the acquisition module is used for acquiring an initial earthquake motion data set, each rotation angle and geological information of the slope to be analyzed;
the first processing module is used for extracting the initial earthquake motion data set to obtain an earthquake motion data input set;
the second processing module is used for forming a model training input data set according to the earthquake motion data input set and a preset critical acceleration data set;
the third processing module is used for calculating the rotation angles according to a preset landslide model to obtain a model training output data set;
the fourth processing module is used for substituting the model training input data set and the model training output data set into a preset bidirectional circulating neural network for training to obtain an earthquake landslide displacement prediction model;
the fifth processing module is used for inputting the geological information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a designated slope permanent displacement value of the slope to be analyzed;
and the analysis module is used for carrying out earthquake landslide hazard analysis according to the designated slope permanent displacement value of the slope to be analyzed.
7. The seismic landslide risk analysis device of claim 6 wherein the third processing module wherein the predetermined landslide model comprises a slope direction model and a landslide displacement solution model comprising:
a first acquisition unit for acquiring acceleration information before rotation of a plurality of seismic spectrums;
the first calculation unit is used for carrying out horizontal vector decomposition on the acceleration information before each earthquake motion spectrum rotates to obtain the acceleration component information before each earthquake motion spectrum rotates;
the second calculation unit is used for calculating the rotation angle and the acceleration component vector information before each earthquake motion spectrum rotates through the slope model to obtain spectrum acceleration values of different slopes;
the third calculation unit is used for calculating the spectral acceleration values of different slope directions through the landslide displacement solving model to obtain a model training output data set, and the model training output data set corresponds to the landslide displacement values of different slope directions in a horizontal plane.
8. The seismic landslide risk analysis device based on a recurrent neural network of claim 6, wherein the geological information of the slope to be analyzed in the fifth processing module includes slope position information, slope body information and intra-slope attribute information, comprising:
the second acquisition unit is used for acquiring slope position information, slope information and slope inner attribute information of the slope to be analyzed, wherein the slope information comprises slope height and slope angle, and the slope inner attribute information comprises slope inner soil weight, slope inner water weight, slope inner soil cohesive force and inner friction angle of soil in the slope;
the fourth calculation unit is used for calculating the slope body information and the in-slope attribute information through a preset slope characteristic model to obtain actual critical acceleration information of the slope to be analyzed;
a fifth calculation unit, configured to calculate the slope position information through a preset seismic fault source model, to obtain seismic vibration information of the slope to be analyzed;
and the sixth calculation unit is used for inputting the actual critical acceleration information of the slope to be analyzed and the earthquake motion information of the slope to be analyzed into the earthquake landslide displacement prediction model to obtain a specified slope permanent displacement value of the slope to be analyzed.
9. The seismic landslide hazard analysis device of claim 8 wherein the fifth computing unit comprises:
the first calculating subunit is used for determining the earthquake information of the area where the side slope to be analyzed is located according to the side slope position information;
the second calculation subunit is used for performing magnitude screening according to the seismic information of the region where the side slope to be analyzed is located, so as to obtain magnitude occurrence times;
the third calculation subunit is used for calculating the occurrence times of the earthquake magnitude through the preset earthquake fault source model to obtain initial earthquake motion information of the slope to be analyzed;
and the fourth calculating subunit is used for extracting the initial earthquake motion information of the slope to be analyzed to obtain the earthquake motion information of the slope to be analyzed.
10. The seismic landslide hazard analysis device of claim 6 wherein the analysis module comprises a first analysis submodule comprising:
the third acquisition unit is used for acquiring a first probability density function when the moment magnitude is a first preset value and a second probability density function when the fault distance is a second preset value;
the seventh calculation unit is used for solving the first probability density function, the second probability density function and the specified slope permanent displacement value of the slope to be analyzed through a preset judgment model to obtain the annual overrun rate of the landslide displacement value;
and the eighth calculation unit is used for enabling the slope to be analyzed to be in a dangerous state when the annual overrun rate of the landslide displacement value is larger than the preset annual overrun rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147477.8A CN116956046B (en) | 2023-09-07 | 2023-09-07 | Earthquake landslide hazard analysis method and device based on cyclic neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147477.8A CN116956046B (en) | 2023-09-07 | 2023-09-07 | Earthquake landslide hazard analysis method and device based on cyclic neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116956046A true CN116956046A (en) | 2023-10-27 |
| CN116956046B CN116956046B (en) | 2023-12-29 |
Family
ID=88442704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311147477.8A Active CN116956046B (en) | 2023-09-07 | 2023-09-07 | Earthquake landslide hazard analysis method and device based on cyclic neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116956046B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108254782A (en) * | 2018-02-09 | 2018-07-06 | 中国地质大学（北京） | A kind of acquisition methods and system of side slope eaerthquake damage failure probability |
| CN109523090A (en) * | 2018-12-04 | 2019-03-26 | 国网湖南省电力有限公司 | A kind of transmission line of electricity heavy rain Prediction of Landslide and system |
| CN109558971A (en) * | 2018-11-09 | 2019-04-02 | 河海大学 | Intelligent landslide monitoring device and method based on LSTM shot and long term memory network |
| CN109992847A (en) * | 2019-03-14 | 2019-07-09 | 桂林电子科技大学 | A kind of Prediction of Displacement in Landslide method of hybrid machine learning model |
| CN110378055A (en) * | 2019-07-25 | 2019-10-25 | 西南交通大学 | A kind of seismic slope permanent displacement calculation method |
| CN111310898A (en) * | 2020-02-14 | 2020-06-19 | 中国地质大学（武汉） | Landslide hazard susceptibility prediction method based on RNN |
| CN112101660A (en) * | 2020-09-15 | 2020-12-18 | 重庆交通大学 | Rainfall type landslide displacement prediction model and method based on staged attention mechanism |
| US20210026027A1 (en) * | 2019-07-25 | 2021-01-28 | Southwest Jiaotong University | Mechanical-model based earthquake-induced landslide hazard assessment method in earthquake-prone mountainous area |
| CN112668244A (en) * | 2021-01-06 | 2021-04-16 | 西南交通大学 | Slope earthquake stability prediction method, device and equipment and readable storage medium |
| CN112862069A (en) * | 2021-01-21 | 2021-05-28 | 西北大学 | Landslide displacement prediction method based on SVR-LSTM mixed deep learning |
| CN113065455A (en) * | 2021-03-30 | 2021-07-02 | 中国水利水电科学研究院 | Landslide risk inspection method and system based on deep learning |
| CN113268852A (en) * | 2021-04-14 | 2021-08-17 | 西南交通大学 | Monte Carlo simulation-based earthquake landslide probability risk analysis method |
| JP2021162591A (en) * | 2020-03-30 | 2021-10-11 | 青▲島▼理工大学Qingdao University Of Technology | Performance earthquake motion danger degree analysis method by three-layer dataset neural network |
| CN113496099A (en) * | 2021-04-06 | 2021-10-12 | 西南交通大学 | Slope permanent displacement prediction model training method based on deep learning |
| CN114330101A (en) * | 2021-12-01 | 2022-04-12 | 武汉大学 | Slope earthquake slip prediction method and system based on artificial neural network |
| CN114818518A (en) * | 2022-06-30 | 2022-07-29 | 深圳特科动力技术有限公司 | Method for analyzing monitoring information of landslide prevention danger of abrupt slope |
| CN115575966A (en) * | 2022-10-20 | 2023-01-06 | 汕头大学 | Geological disaster displacement monitoring system |
| CN116203619A (en) * | 2022-12-08 | 2023-06-02 | 西南交通大学 | Regional earthquake landslide simulation method based on spatial cross-correlation multi-seismic vibration parameters |
| CN116609823A (en) * | 2023-04-13 | 2023-08-18 | 西南交通大学 | Probabilistic earthquake landslide risk evaluation method considering fault and earthquake vibration characteristics |
-
2023
- 2023-09-07 CN CN202311147477.8A patent/CN116956046B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108254782A (en) * | 2018-02-09 | 2018-07-06 | 中国地质大学（北京） | A kind of acquisition methods and system of side slope eaerthquake damage failure probability |
| CN109558971A (en) * | 2018-11-09 | 2019-04-02 | 河海大学 | Intelligent landslide monitoring device and method based on LSTM shot and long term memory network |
| CN109523090A (en) * | 2018-12-04 | 2019-03-26 | 国网湖南省电力有限公司 | A kind of transmission line of electricity heavy rain Prediction of Landslide and system |
| CN109992847A (en) * | 2019-03-14 | 2019-07-09 | 桂林电子科技大学 | A kind of Prediction of Displacement in Landslide method of hybrid machine learning model |
| US20210026027A1 (en) * | 2019-07-25 | 2021-01-28 | Southwest Jiaotong University | Mechanical-model based earthquake-induced landslide hazard assessment method in earthquake-prone mountainous area |
| CN110378055A (en) * | 2019-07-25 | 2019-10-25 | 西南交通大学 | A kind of seismic slope permanent displacement calculation method |
| CN111310898A (en) * | 2020-02-14 | 2020-06-19 | 中国地质大学（武汉） | Landslide hazard susceptibility prediction method based on RNN |
| JP2021162591A (en) * | 2020-03-30 | 2021-10-11 | 青▲島▼理工大学Qingdao University Of Technology | Performance earthquake motion danger degree analysis method by three-layer dataset neural network |
| CN112101660A (en) * | 2020-09-15 | 2020-12-18 | 重庆交通大学 | Rainfall type landslide displacement prediction model and method based on staged attention mechanism |
| CN112668244A (en) * | 2021-01-06 | 2021-04-16 | 西南交通大学 | Slope earthquake stability prediction method, device and equipment and readable storage medium |
| CN112862069A (en) * | 2021-01-21 | 2021-05-28 | 西北大学 | Landslide displacement prediction method based on SVR-LSTM mixed deep learning |
| CN113065455A (en) * | 2021-03-30 | 2021-07-02 | 中国水利水电科学研究院 | Landslide risk inspection method and system based on deep learning |
| CN113496099A (en) * | 2021-04-06 | 2021-10-12 | 西南交通大学 | Slope permanent displacement prediction model training method based on deep learning |
| CN113268852A (en) * | 2021-04-14 | 2021-08-17 | 西南交通大学 | Monte Carlo simulation-based earthquake landslide probability risk analysis method |
| CN114330101A (en) * | 2021-12-01 | 2022-04-12 | 武汉大学 | Slope earthquake slip prediction method and system based on artificial neural network |
| CN114818518A (en) * | 2022-06-30 | 2022-07-29 | 深圳特科动力技术有限公司 | Method for analyzing monitoring information of landslide prevention danger of abrupt slope |
| CN115575966A (en) * | 2022-10-20 | 2023-01-06 | 汕头大学 | Geological disaster displacement monitoring system |
| CN116203619A (en) * | 2022-12-08 | 2023-06-02 | 西南交通大学 | Regional earthquake landslide simulation method based on spatial cross-correlation multi-seismic vibration parameters |
| CN116609823A (en) * | 2023-04-13 | 2023-08-18 | 西南交通大学 | Probabilistic earthquake landslide risk evaluation method considering fault and earthquake vibration characteristics |
Non-Patent Citations (6)
| Title |
|---|
| NING XI 等: "Machine Learning Approaches for Slope Deformation Prediction Based on Monitored Time-Series Displacement Data: A Comparative Investigation", 《APPLIED SCIENCES》, pages 1 - 19 * |
| WENLI MA 等: "Landslide Displacement Prediction With Gated Recurrent Unit and Spatial-Temporal Correlation", 《FRONTIERS IN EARTH SCIENCE》, pages 1 - 9 * |
| YIN CHENG 等: "Prediction Models of Newmark Sliding Displacement of Slopes Using Deep Neural Network and Mixed-effect Regression", 《COMPUTERS AND GEOTECHNICS》, pages 1 - 16 * |
| YU HUANG 等: "Recurrent neural networks for complicated seismic dynamic response prediction of a slope system", 《ENGINEERING GEOLOGY》, pages 1 - 14 * |
| 刘爱娟 等: "考虑动态临界加速度的地震边坡永久位移预测模型研究", 《地震工程学报》, vol. 43, no. 2, pages 445 - 452 * |
| 李璐: "基于机器学习法的黑方台典型滑坡体易发 性评价及高精度位移预测分析", 《自然灾害学报》, no. 2023, pages 008 - 109 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116956046B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lanzano et al. | A revised ground‐motion prediction model for shallow crustal earthquakes in Italy | |
| Abrahamson et al. | Probabilistic seismic hazard analysis in California using nonergodic ground‐motion models | |
| Yuan et al. | Density distribution of landslides triggered by the 2008 Wenchuan earthquake and their relationships to peak ground acceleration | |
| Villani et al. | Repeatable site and path effects on the ground‐motion sigma based on empirical data from southern California and simulated waveforms from the CyberShake platform | |
| Candia et al. | A new state‐of‐the‐art platform for probabilistic and deterministic seismic hazard assessment | |
| Erden et al. | Analysis of earthquake parameters to generate hazard maps by integrating AHP and GIS for Küçükçekmece region | |
| Gesch | Consideration of vertical uncertainty in elevation-based sea-level rise assessments: Mobile Bay, Alabama case study | |
| Ji et al. | A GIS-based tool for probabilistic physical modelling and prediction of landslides: GIS-FORM landslide susceptibility analysis in seismic areas | |
| Hosseinpour et al. | Seismic loss estimation software: a comprehensive review of risk assessment steps, software development and limitations | |
| CN114021487B (en) | Early warning method, device and equipment for landslide collapse and readable storage medium | |
| Kowsari et al. | Calibration of ground motion models to Icelandic peak ground acceleration data using Bayesian Markov Chain Monte Carlo simulation | |
| Kropivnitskaya et al. | Real-time earthquake intensity estimation using streaming data analysis of social and physical sensors | |
| Strader et al. | A Monte Carlo model for estimating tornado impacts | |
| CN115542397B (en) | Tsunami danger analysis method based on SVM | |
| Nascimento et al. | Modeling the environmental susceptibility of landfill sites in California | |
| Ashadi et al. | Probabilistic Seismic‐Hazard Analysis for Central Java Province, Indonesia | |
| Podili et al. | Ground motion parameters for the 2011 Great Japan Tohoku earthquake | |
| Douglas et al. | Assessing components of ground‐motion variability from simulations for the Marmara Sea region (Turkey) | |
| Hao et al. | Assessing disaster impact in real time: Data-driven system integrating humans, hazards, and the built environment | |
| Davatgari-Tafreshi et al. | Empirical ground-motion models (GMMs) and associated correlations for cumulative absolute velocity, Arias intensity, and significant durations calibrated on Iranian strong motion database | |
| Rosti et al. | Comparison of PSH results with historical macroseismic observations at different scales. Part 2: application to South-East France | |
| CN116956046B (en) | Earthquake landslide hazard analysis method and device based on cyclic neural network | |
| JP2018136247A (en) | Estimation method and estimation system for earthquake motion intensity distribution | |
| Thingbaijam et al. | Characterization of focal mechanisms for upper crustal distributed seismicity in Aotearoa New Zealand | |
| Pothon et al. | Comparing probabilistic seismic hazard maps with ShakeMap footprints for Indonesia |
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 |