Rapid on-site peak ground acceleration estimation based on support vector regression and P-wave features in Taiwan

NCUIR > College of Earth Sciences > Department of Earth Sciences > journal & Dissertation > Item 987654321/104019

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/104019

Title:	Rapid on-site peak ground acceleration estimation based on support vector regression and P-wave features in Taiwan
Authors:	郭俊翔;Hsu, Ting-Yu;Huang, Shieh-Kung;Chang, Yu-Weng;Kuo, Chun-Hsiang;Lin, Che-Min;Chang, Tao-Ming;Wen, Kuo-Liang;Loh, Chin-Hsiung
Contributors:	地球科學學院地球科學學系
Keywords:	Acceleration;Amplitudes;earthquakes;Ground stations;instrumentation;Mathematical analysis;Mathematical models;prediction;Regression;regression analysis;Seismic phenomena;Taiwan;Vectors (mathematics)
Date:	2013-06-01
Issue Date:	2026-04-23 11:41:56 (UTC+8)
Publisher:	Elsevier BV;Elsevier Ltd
Abstract:	摘要： This study extracted some P-wave features from the first few seconds of vertical ground acceleration of a single station. These features include the predominant period, peak acceleration amplitude, peak velocity amplitude, peak displacement amplitude, cumulative absolute velocity and integral of the squared velocity. The support vector regression was employed to establish a regression model which can predict the peak ground acceleration according to these features. Some representative earthquake records of the Taiwan Strong Motion Instrumentation Program from 1992 to 2006 were used to train and validate the support vector regression model. Then the constructed model was tested using the whole earthquake records of the same period as well as the 2010 Kaohsiung earthquake with 6.4 ML. The effects on the performance of the regression models using different P-wave features and different length of time window to extract these features are studied. The results illustrated that, if the first 3s of the vertical ground acceleration was used, the standard deviation of the predicted peak ground acceleration error of the whole tested 15-years earthquake records is 20.89gal.The length of time window could be shortened, e.g. 1s, and the prediction error is slightly sacrificed, in order to prolong the lead-time before destructive S-waves reaches. ► PGA was estimated by support vector regression models. ► The necessary information is the P-wave features of vertical record on a single station. ► The proposed approach was validated by 15-years earthquake records of TSMIP in Taiwan. ► Another earthquake event was tested to illustrate the feasibility and possible acquired lead-time. 出版者： Elsevier Ltd 出版日期： 2013-06 出處： Soil dynamics and earthquake engineering (1984), 2013-06, Vol.49, p.210-217 資源來源： Access articles in the ScienceDirect collection 版權： 2013 Elsevier Ltd 識別號： ISSN: 0267-7261 識別號： EISSN: 1879-341X 識別號： DOI: 10.1016/j.soildyn.2013.03.001
Appears in Collections:	[Department of Earth Sciences ] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	20	View/Open

社群 sharing

Loading...