CN113791444A - Earthquake motion record selection method based on cluster analysis - Google Patents

Earthquake motion record selection method based on cluster analysis Download PDF

Info

Publication number
CN113791444A
CN113791444A CN202111079292.9A CN202111079292A CN113791444A CN 113791444 A CN113791444 A CN 113791444A CN 202111079292 A CN202111079292 A CN 202111079292A CN 113791444 A CN113791444 A CN 113791444A
Authority
CN
China
Prior art keywords
seismic
clustering
earthquake
record
algorithm
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.)
Withdrawn
Application number
CN202111079292.9A
Other languages
Chinese (zh)
Inventor
刘亭亭
吕大刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University of Science and Technology
Original Assignee
Jiangsu University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University of Science and Technology filed Critical Jiangsu University of Science and Technology
Priority to CN202111079292.9A priority Critical patent/CN113791444A/en
Publication of CN113791444A publication Critical patent/CN113791444A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V1/00Seismology; Seismic or acoustic prospecting or detecting
    • G01V1/24Recording seismic data
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V1/00Seismology; Seismic or acoustic prospecting or detecting
    • G01V1/28Processing seismic data, e.g. for interpretation or for event detection
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V1/00Seismology; Seismic or acoustic prospecting or detecting
    • G01V1/28Processing seismic data, e.g. for interpretation or for event detection
    • G01V1/30Analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • G06F18/232Non-hierarchical techniques
    • G06F18/2321Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/12Computing arrangements based on biological models using genetic models
    • G06N3/126Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biophysics (AREA)
  • Evolutionary Biology (AREA)
  • Geophysics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Geology (AREA)
  • Acoustics & Sound (AREA)
  • Environmental & Geological Engineering (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Physiology (AREA)
  • Genetics & Genomics (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

The invention relates to a seismic oscillation record selection method based on cluster analysis, which comprises the following steps: step 1: selecting earthquake motion records based on a strong earthquake database; step 2: selecting the range of the seismic level and the seismic distance strip, and giving specific seismic information of each seismic record; and step 3: according to a fuzzy C-means clustering algorithm, taking the mean value of the magnitude and the epicenter distance of each earthquake motion record as a clustering center, repeatedly modifying the clustering center and the data membership degree through an iterative process, and giving a preliminary trial calculation clustering analysis result; and 4, step 4: introducing a simulated annealing algorithm to converge to global optimal clustering analysis; and 5: and on the basis of clustering analysis according to the magnitude and the epicenter distance, combining the soil layer shear wave velocity and the thickness of the soil covering layer of the field to give reaction spectrum curves of each group of earthquake motion records under different field types. The invention realizes the self-adaptive classification of the earthquake motion record database so as to provide technical support for the subsequent power time-course analysis.

Description

Earthquake motion record selection method based on cluster analysis
Technical Field
The invention belongs to the technical field of seismic engineering and disaster prevention and reduction engineering, and particularly relates to a method for selecting seismic motion records based on cluster analysis.
Background
In the field of seismic engineering, with the continuous development of seismic observation technology and the continuous increase of observation stations, global seismic motion record databases are more and more, and how to reasonably select seismic motion records becomes a key of performance-based seismic design. Because the earthquake occurs randomly in time and space, with the gradual enrichment of a large amount of earthquake source information, field information, fault types, earthquake occurrence time and the like, in order to explore a physical mechanism of earthquake occurrence and propagation and further dig the correlation among earthquake motion record data deeply, a big data method is needed to select the earthquake motion records.
The existing classification method mainly depends on the earthquake magnitude, the distance and the site condition to carry out primary selection on the earthquake motion records, the boundary between various types needs to be given in advance according to the expert experience, and the characteristics of the earthquake motion records can not be objectively reflected.
Disclosure of Invention
In order to overcome the defect that the traditional primary selection method only can consider fixed earthquake magnitude and distance grouping, the invention provides a method for primarily selecting earthquake magnitude records according to the earthquake magnitude and distance and considering field categories by carrying out cluster analysis on the earthquake magnitude records based on a global clustering algorithm in machine learning, deeply excavating the statistical properties of the earthquake magnitude and distance of the earthquake magnitude records and considering the influences of different field categories and different cluster groupings on earthquake magnitude spectrum characteristics.
In order to achieve the purpose, the invention is realized by the following technical scheme:
the invention relates to a seismic oscillation record selection method based on cluster analysis, which comprises the following steps:
step 1, selecting earthquake motion records based on a strong earthquake database, and carrying out reasonable baseline offset correction and filtering processing;
step 2, selecting a wider range of the seismic magnitude and the seismic distance strip, and giving specific seismic information of each seismic motion record;
step 3, according to a fuzzy C-means clustering algorithm, taking the mean value of the earthquake magnitude and the earthquake center distance of each earthquake motion record as a clustering center, repeatedly modifying the clustering center and the data membership degree through an iterative process, and giving a preliminary trial-computation clustering analysis result;
step 4, searching an optimal solution by simulating the selection of the nature and the genetic mechanism, and introducing a simulated annealing algorithm to more effectively and more quickly converge to global optimal clustering analysis in order to prevent the later-stage fitness of the genetic algorithm from tending to be consistent, so that the seismic motion record clustering analysis result has stronger robustness, global convergence, implicit parallelism and wide adaptability;
and step 5, on the basis of carrying out cluster analysis according to the magnitude of earthquake and the distance between the epicenter, combining the shear wave velocity of the soil layer and the thickness of the covering soil layer of the field, giving out the clustering grouping condition of each group of earthquake motion records under the condition of different field types, and fully considering the influence of different field types and different clustering groupings on the earthquake motion spectrum characteristics.
Further, in step 1, the seismic motion recording needs to be subjected to reasonable baseline shift correction and filtering processing.
Further, step 2 specifically includes: the seismic record database contains specific seismic information such as: the earthquake name, station, earthquake magnitude, earthquake center distance, fault type, site condition and the like, and provides abundant data for subsequent research;
and selecting earthquake motion records in a wider range of the earthquake magnitude M-epicenter distance R strip to avoid obvious tendencies of results.
Further, in step 2, the band ranges are: 5< M <7.9, 10km < R <60 km.
Further, in step 3, the fuzzy C-means clustering algorithm measures the correlation size among data points by using a number between [0,1], namely the membership degree, then determines the clustering degree of each given data point according to the membership degree of the given data point, clusters the earthquake motion records into four groups, and obtains a preliminary trial clustering analysis result by repeatedly modifying the clustering center and the data membership degree.
Further, in step 4, the cluster analysis of the genetic simulated annealing algorithm is that the energy of the substance gradually approaches to a lower state along with the reduction of the temperature, and finally reaches a certain balance, the fuzzy cluster analysis is combined to obtain the optimal solution, namely the energy lowest state, the simulated annealing algorithm is combined with the genetic algorithm to amplify the individual fitness difference with similar fitness, so that the advantages of excellent individuals are more obvious, and the optimization approaches to the optimal solution by increasing the population size and the maximum genetic algebra.
Further, step 5 comprises: and classifying the fields according to the anti-seismic standard, giving a corresponding relation between the field type and the shear wave velocity, and giving a response spectrum curve of each field type and different cluster grouping earthquake motion records based on the clustering analysis result and considering the influence of different field types on the earthquake motion spectrum characteristics.
The invention has the beneficial effects that: the invention relates to a seismic record selection method based on cluster analysis, which considers the influences of earthquake magnitude, distance and field category, uses a cluster analysis method in machine learning, takes the mean value of the earthquake magnitude and the earthquake center distance as a cluster center, repeatedly modifies the cluster center and the data membership degree through iteration, and gives a preliminary trial calculation cluster analysis result; on the basis, the global optimal clustering classification is obtained more effectively and more quickly based on the clustering analysis of the genetic simulated annealing algorithm, and finally, the influences of different field categories and different clustering groups on the seismic frequency spectrum characteristics are given.
The earthquake motion records are classified according to the distance or the similarity, the correlation rule between different earthquake motion records is given based on the magnitude of earthquake and the distance of earthquake, and the influence of different field categories on the earthquake motion frequency spectrum characteristic is fully considered, so that the dynamic analysis result has good statistical properties, and a theoretical basis is provided for subsequent exploration.
Drawings
FIG. 1 is a flow chart of a seismic motion selection method based on cluster analysis according to the present invention.
FIG. 2 is the result of a seismic record clustering analysis based on the fuzzy C-means algorithm.
FIG. 3 is the result of a seismic record clustering analysis based on a genetic simulated annealing algorithm.
FIG. 4 is a comparison of seismic dynamic acceleration response spectral means based on different cluster groupings.
FIG. 5 is a seismic acceleration response spectrum mean comparison based on different field classes.
Detailed Description
In the following description, for purposes of explanation, numerous implementation details are set forth in order to provide a thorough understanding of the embodiments of the invention. It should be understood, however, that these implementation details are not to be interpreted as limiting the invention. That is, in some embodiments of the invention, such implementation details are not necessary. In addition, some conventional structures and components are shown in simplified schematic form in the drawings.
Referring to fig. 1, the embodiment provides a method for selecting a seismic record based on cluster analysis, which includes the following steps:
step S1, selecting earthquake motion records based on the strong earthquake database, and carrying out reasonable baseline offset correction and filtering processing;
s2, selecting a wider range of the seismic magnitude and the seismic center distance strip, and giving concrete seismic information of each seismic record;
step S3, according to a fuzzy C-means clustering algorithm, taking the mean value of the earthquake magnitude and the earthquake center distance of each earthquake motion record as a clustering center, repeatedly modifying the clustering center and the data membership degree through an iterative process, and giving a preliminary trial calculation clustering analysis result;
s4, searching an optimal solution by simulating the selection of the nature and the genetic mechanism, and introducing a simulated annealing algorithm to more effectively and more quickly converge to global optimal cluster analysis in order to prevent the later-stage fitness of the genetic algorithm from tending to be consistent, so that the seismic motion record cluster analysis result has stronger robustness, global convergence, implicit parallelism and wide adaptability;
and step S5, on the basis of cluster analysis according to the magnitude of earthquake and the distance between earthquakes, combining the shear wave velocity of the soil layer and the thickness of the covering soil layer of the field to give the clustering grouping condition of each group of earthquake motion records under different field types, and fully considering the influence of different field types and different clustering groupings on the earthquake motion frequency spectrum characteristics.
The seismic record selection method provided by the embodiment can overcome the defect that only fixed earthquake magnitude and distance grouping are considered in the prior art, the influence of seismic record data on clustering results is deeply mined based on a global clustering algorithm in machine learning, and classification is performed according to the correlation degree between different seismic records, so that the dynamic analysis result has good statistical properties.
The method comprises the following specific steps:
1. seismic motion selection based on a strong seismic database.
(1) Selecting 2157 groups of horizontal bidirectional seismic records in a database, striving for a wider magnitude M and a wider epicenter distance R, wherein the value range of the magnitude M-the epicenter distance R of the seismic record database of the primarily selected American Pacific seismic engineering research center is as follows: 5< M <7.9, 10km < R <60 km; the selected earthquake motion has detailed earthquake name, station information, field information, fault type and the like, and can be used for subsequent analysis.
2. And (4) carrying out clustering analysis based on a fuzzy C-means algorithm.
(1) The method comprises the steps of adopting a C-means clustering algorithm, dividing earthquake motion records into different categories through an iterative process, selecting a central point in a data set to have randomness, and introducing a fuzzy set concept into the selected data set when the earthquake motion records can not be strictly divided into a certain category, wherein the characteristic is not that the selected data set has randomness, and finally determining a certain clustering grouping degree according to the membership degree of a data point.
(2) Let sample space X ═ X1,x2,…,xn}TDividing the earthquake motion data into four classes, wherein each clustering center is { c1,c2,c3,c4}, element uijRepresenting the degree of membership that the ith data point belongs to the jth class, such that the objective function of euclidean distance achieves the smallest function value:
Figure BDA0003263359090000051
in the formula (I), the compound is shown in the specification,
Figure BDA0003263359090000052
(3) and (3) giving a clustering center and a data membership:
Figure BDA0003263359090000053
Figure BDA0003263359090000054
(4) repeatedly modifying the clustering center and the data membership according to the formulab(t+1)-JbAnd (t) | < 1e-6, the algorithm converges to obtain the membership of each clustering center and each sample, the fuzzy clustering division is completed, the algorithm is ended, otherwise, iteration is performed until the maximum iteration frequency reaches 20 times, and the algorithm is ended. FIG. 2 shows the result of the seismic record clustering analysis based on the fuzzy C-means algorithm.
3. And (4) carrying out clustering analysis based on a genetic simulated annealing algorithm.
If the initial value is not properly selected, the clustering analysis result can be converged to a local optimal solution, a genetic algorithm optimizing solution is introduced on the basis, the solution space of the clustering analysis is encoded, a fitness function is constructed, and the value of each control parameter is determined through selection, intersection and variation of a genetic operator. However, the genetic algorithm is easy to generate the premature convergence problem, the fitness tends to be consistent in the later stage of the genetic algorithm, and a simulated annealing algorithm needs to be introduced to keep good individuals and maintain the diversity of the population.
The simulated annealing algorithm is combined with the genetic algorithm, when the temperature is continuously reduced, the individual fitness difference of fitness is amplified, so that the advantages of excellent individuals are more obvious, fuzzy cluster analysis is combined on the basis, wherein the change of energy is an objective function, the obtained optimal solution is the energy lowest state, and the seismic motion record cluster analysis result based on the genetic simulated annealing algorithm is shown in figure 3.
4. And (4) primarily selecting the seismic motion record of the clustering group.
The earthquake motion records are divided into four groups according to the magnitude of the earthquake magnitude and the magnitude of the epicenter distance, the earthquake motion acceleration time course is normalized, and the acceleration response spectrum is obtained, namely the dynamic amplification coefficient curve. In order to fully consider the influence of different clustering groups on the seismic motion spectrum characteristics, fig. 4 shows the seismic motion acceleration response spectrum mean comparison result of different clustering groups.
5. And (4) primarily selecting the seismic motion record in consideration of the field category.
The field classification is performed according to the seismic norm according to the equivalent shear wave velocity of the underground 30m depth, and the clustering grouping result based on the field category is given by considering each clustering grouping result as shown in table 1.
TABLE 1 field Category based earthquake motion record clustering grouping results
Figure BDA0003263359090000061
At least 11 earthquake motion records are selected for analysis during FEMA P-1050 specified time-course analysis, and the influence of the fourth field type on earthquake motion frequency spectrum characteristics cannot be fully considered due to too few earthquake motion records of the fourth field type, so that the earthquake motion records of the type are not continuously analyzed subsequently. FIG. 5 shows the result of comparing the mean of the seismic acceleration response spectra based on different field categories.
The method overcomes the defect that only fixed earthquake magnitude and earthquake-centre distance grouping are considered in the prior art, can objectively reflect the characteristics of earthquake motion records, deeply excavates the influence of the earthquake motion records on clustering analysis results, realizes the self-adaptive classification of the earthquake motion record database, and provides technical support for the subsequent power time-course analysis.
The above description is only an embodiment of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims (6)

1. A seismic record selection method based on cluster analysis is characterized by comprising the following steps: the seismic record selection method comprises the following steps:
step 1: selecting earthquake motion records based on a strong earthquake database;
step 2: selecting the range of the seismic level and the seismic distance strip, and giving specific seismic information of each seismic record;
and step 3: according to a fuzzy C-means clustering algorithm, taking the mean value of the magnitude and the epicenter distance of each earthquake motion record as a clustering center, repeatedly modifying the clustering center and the data membership degree through an iterative process, and giving a preliminary trial calculation clustering analysis result;
and 4, step 4: introducing a simulated annealing algorithm to converge to global optimal clustering analysis;
and 5: and on the basis of clustering analysis according to the magnitude and the epicenter distance, combining the soil layer shear wave velocity and the thickness of the soil covering layer of the field to give reaction spectrum curves of each group of earthquake motion records under different field types.
2. The method of selecting seismic motion record based on cluster analysis according to claim 1, wherein: the step 3 specifically comprises the following steps:
step 3-1: adopting a C-means clustering algorithm, dividing the seismic motion records into different categories through an iterative process, introducing a fuzzy set concept into the seismic motion records on the basis, and finally determining a certain clustering grouping degree according to the membership degree of data points;
step 3-2: let sample space X ═ X1,x2,…,xn}TDividing the earthquake motion data into four classes, wherein each clustering center is { c1,c2,c3,c4}, element uijRepresenting the degree of membership that the ith data point belongs to the jth class, such that the objective function of euclidean distance achieves the smallest function value:
Figure FDA0003263359080000011
in the formula (I), the compound is shown in the specification,
Figure FDA0003263359080000012
step 3-3: and (3) giving a clustering center and a data membership:
Figure FDA0003263359080000021
Figure FDA0003263359080000022
step 3-4: repeatedly modifying the clustering center and the data membership according to the formulab(t+1)-JbAnd (t) | < 1e-6, the algorithm converges to obtain the membership of each clustering center and each sample, the fuzzy clustering division is completed, the algorithm is ended, otherwise, iteration is performed until the maximum iteration frequency reaches 20 times, and the algorithm is ended.
3. The method of selecting seismic motion record based on cluster analysis according to claim 1, wherein: the step 4 of introducing a simulated annealing algorithm to converge to the global optimal clustering analysis specifically comprises the following steps: when the temperature is continuously reduced, the individual fitness difference of the fitness is amplified, fuzzy clustering analysis is combined on the basis, wherein the change of energy is an objective function, and the obtained optimal solution is the energy lowest state.
4. The method of selecting seismic motion record based on cluster analysis according to claim 1, wherein: the seismic record in step 1 needs to be subjected to baseline shift correction and filtering processing.
5. The method of selecting seismic motion record based on cluster analysis according to claim 1, wherein: in step 2, the band range of magnitude M is: 5< M <7.9, epicenter R-banding range: 10km < R <60 km.
6. The method of selecting seismic motion record based on cluster analysis according to claim 1, wherein: in the step 2, the specific seismic information of the seismic record comprises an earthquake name, a station, an earthquake magnitude, an earthquake center distance, a fault type and a field condition.
CN202111079292.9A 2021-09-15 2021-09-15 Earthquake motion record selection method based on cluster analysis Withdrawn CN113791444A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111079292.9A CN113791444A (en) 2021-09-15 2021-09-15 Earthquake motion record selection method based on cluster analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111079292.9A CN113791444A (en) 2021-09-15 2021-09-15 Earthquake motion record selection method based on cluster analysis

Publications (1)

Publication Number Publication Date
CN113791444A true CN113791444A (en) 2021-12-14

Family

ID=79183387

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111079292.9A Withdrawn CN113791444A (en) 2021-09-15 2021-09-15 Earthquake motion record selection method based on cluster analysis

Country Status (1)

Country Link
CN (1) CN113791444A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114443883A (en) * 2022-02-10 2022-05-06 北京永利信达科技有限公司 Data processing method, system and medium based on big data and cloud computing
CN114779329A (en) * 2022-04-24 2022-07-22 福州大学 Near-fault sea area seismic oscillation response spectrum calibration method
CN116630676A (en) * 2022-09-01 2023-08-22 中国地震局地球物理研究所 Large-scale-range field classification processing method and device and electronic equipment

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114443883A (en) * 2022-02-10 2022-05-06 北京永利信达科技有限公司 Data processing method, system and medium based on big data and cloud computing
CN114779329A (en) * 2022-04-24 2022-07-22 福州大学 Near-fault sea area seismic oscillation response spectrum calibration method
CN116630676A (en) * 2022-09-01 2023-08-22 中国地震局地球物理研究所 Large-scale-range field classification processing method and device and electronic equipment
CN116630676B (en) * 2022-09-01 2024-02-09 中国地震局地球物理研究所 Large-scale-range field classification processing method and device and electronic equipment

Similar Documents

Publication Publication Date Title
CN113791444A (en) Earthquake motion record selection method based on cluster analysis
Sambridge et al. Earthquake hypocenter location using genetic algorithms
US11215719B2 (en) Performance-level seismic motion hazard analysis method based on three-layer dataset neural network
US20210026031A1 (en) Dolomite reservoir prediction method and system based on well and seismic combination, and storage medium
CN101266299B (en) Method for forecasting oil gas utilizing earthquake data object constructional features
CN108732620B (en) Multi-wave earthquake oil and gas reservoir prediction method under unsupervised and supervised learning
CN108897975A (en) Coalbed gas logging air content prediction technique based on deepness belief network
CN110344824B (en) Acoustic curve generation method based on random forest regression
CN106569272B (en) A kind of seismic attribute fusion method that dimension is risen based on data character space
CN106056577B (en) SAR image change detection based on MDS-SRM Mixed cascading
CN113343574A (en) Mishrif group lithology logging identification method based on neural network
CN115130375A (en) Rock burst intensity prediction method
CN108280289A (en) Bump danger classes prediction technique based on local weighted C4.5 algorithms
CN117272841B (en) Shale gas dessert prediction method based on hybrid neural network
CN111611422A (en) SVC-based method and system for automatically generating qualitative graph in earthquake disaster risk assessment
CN110009024A (en) A kind of data classification method based on ID3 algorithm
CN115545543A (en) Multi-disaster integrated natural disaster risk assessment and analysis system
Cho et al. Development of locally specified soil stratification method with CPT data based on machine learning techniques
CN112434878A (en) Cascade sample equalization-based seismic fluid prediction method
Whitley et al. Comparing the niches of CMA-ES, CHC and pattern search using diverse benchmarks
CN110488350B (en) Seismic inversion big data generation method based on convolutional neural network
CN113361619B (en) Convolutional neural network lithology identification method based on rough set attribute reduction
Sinaga et al. Spatial Variation in Infant Mortality with Geographically Weighted Poisson Regression (GWPR) Approach
Alimoradi et al. Ga-based selection and scaling of strong ground motion records for structural design
CN116070148A (en) Oil source classification method and system based on deep neural network model

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20211214

WW01 Invention patent application withdrawn after publication