Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)

One of the purposes of earthquake engineering is to mitigate the damages in buildings and infrastructures and, therefore, reduce the impact of earthquakes on society. Seismic ground response analysis refers to the process of evaluating the ground surface motions based on the bedrock motion. On the o...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Seokgyeong Hong, Huyen-Tram Nguyen, Jongwon Jung, Jaehun Ahn
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	earthquake seismic ground response analysis convolutional neural networks physical analysis software acceleration response spectrum Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/d573fc207a6247b0a7536e9dfa7b713c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d573fc207a6247b0a7536e9dfa7b713c
record_format	dspace
spelling	oai:doaj.org-article:d573fc207a6247b0a7536e9dfa7b713c2021-11-25T16:37:53ZSeismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)10.3390/app1122107602076-3417https://doaj.org/article/d573fc207a6247b0a7536e9dfa7b713c2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10760https://doaj.org/toc/2076-3417One of the purposes of earthquake engineering is to mitigate the damages in buildings and infrastructures and, therefore, reduce the impact of earthquakes on society. Seismic ground response analysis refers to the process of evaluating the ground surface motions based on the bedrock motion. On the other hand, deep learning techniques have been developing fast, and they are establishing their application in the civil engineering field. This study proposes two convolutional neural network (CNN) models to estimate the seismic response of the surface based on the seismic motion measured at 100 m level beneath the surface, and selected the one which outperforms the other as the main model. The performances of the main model are compared with those of a physical software SHAKE2000. Twelve sites that include 100 earthquake datasets, whose moment magnitude is higher than 6 and PGA is higher than 0.1 g, were selected. In addition, the corresponding earthquake datasets are used for the CNN model. Whereas the conventional software overestimated the values of the amplitudes for most of the sites, the proposed CNN model predicts fairly well both the values of the amplitudes and the natural periods where responses amplify the most with few exceptions. The proposed model especially outperforms the conventional software when the natural periods range from 0.01 to 0.3 s. For specific sites, the average mean squared errors of the proposed model are even dozens of times lower than those of the conventional physical software.Seokgyeong HongHuyen-Tram NguyenJongwon JungJaehun AhnMDPI AGarticleearthquakeseismic ground response analysisconvolutional neural networksphysical analysis softwareacceleration response spectrumTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10760, p 10760 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	earthquake seismic ground response analysis convolutional neural networks physical analysis software acceleration response spectrum Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	earthquake seismic ground response analysis convolutional neural networks physical analysis software acceleration response spectrum Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Seokgyeong Hong Huyen-Tram Nguyen Jongwon Jung Jaehun Ahn Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)
description	One of the purposes of earthquake engineering is to mitigate the damages in buildings and infrastructures and, therefore, reduce the impact of earthquakes on society. Seismic ground response analysis refers to the process of evaluating the ground surface motions based on the bedrock motion. On the other hand, deep learning techniques have been developing fast, and they are establishing their application in the civil engineering field. This study proposes two convolutional neural network (CNN) models to estimate the seismic response of the surface based on the seismic motion measured at 100 m level beneath the surface, and selected the one which outperforms the other as the main model. The performances of the main model are compared with those of a physical software SHAKE2000. Twelve sites that include 100 earthquake datasets, whose moment magnitude is higher than 6 and PGA is higher than 0.1 g, were selected. In addition, the corresponding earthquake datasets are used for the CNN model. Whereas the conventional software overestimated the values of the amplitudes for most of the sites, the proposed CNN model predicts fairly well both the values of the amplitudes and the natural periods where responses amplify the most with few exceptions. The proposed model especially outperforms the conventional software when the natural periods range from 0.01 to 0.3 s. For specific sites, the average mean squared errors of the proposed model are even dozens of times lower than those of the conventional physical software.
format	article
author	Seokgyeong Hong Huyen-Tram Nguyen Jongwon Jung Jaehun Ahn
author_facet	Seokgyeong Hong Huyen-Tram Nguyen Jongwon Jung Jaehun Ahn
author_sort	Seokgyeong Hong
title	Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)
title_short	Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)
title_full	Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)
title_fullStr	Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)
title_full_unstemmed	Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)
title_sort	seismic ground response estimation based on convolutional neural networks (cnn)
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d573fc207a6247b0a7536e9dfa7b713c
work_keys_str_mv	AT seokgyeonghong seismicgroundresponseestimationbasedonconvolutionalneuralnetworkscnn AT huyentramnguyen seismicgroundresponseestimationbasedonconvolutionalneuralnetworkscnn AT jongwonjung seismicgroundresponseestimationbasedonconvolutionalneuralnetworkscnn AT jaehunahn seismicgroundresponseestimationbasedonconvolutionalneuralnetworkscnn
_version_	1718413106203328512

Seismic Ground Response Estimation Based on Convolutional Neural Networks (CNN)

Ejemplares similares