search for




 

Prediction of earthquake magnitude for return period using generalized extreme value distribution: Korea, Japan, China and Taiwan
Journal of the Korean Data & Information Science Society 2020;31:97-108
Published online January 31, 2020;  https://doi.org/10.7465/jkdi.2020.31.1.97
© 2020 Korean Data and Information Science Society.

Il Do Ha1 · Dae-Heung Jang2 · Kun Woo Rhee3 · Jae Eun Lee4 · Seung Jae Lee5 · Nak Gyeong Ko6 · Jun Cheol Kim7 ·

124567Department of Statistics, Pukyong National University
3Department of History, Pukyong National University
Correspondence to: Professor, Department of Statistics, Pukyong National University, Busan 48513, Korea. E-mail: dhjang@pknu.ac.kr
This work was supported by the Korea Institute of Energy Technology Evaluation and Planning( KETEP) and the Ministry of Trade, Industry & Energy(MOTIE) of the Republic of Korea (No. 20171510101960).
Received December 31, 2019; Revised January 13, 2020; Accepted January 13, 2020.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
In this paper, we first present the basic data analysis of recent earthquake magnitude data of Korea, Japan, China and Taiwan. We also present the predicted return levels of maximum earthquake magnitudes using the extreme value theory with generalized extreme value (GEV) distribution. The data sets used are the years from 1978 to 2019 for Korea, Japan and China, and they are from 1990 to 2019 for Taiwan. For the estimation of parameters in the GEV distribution, we use maximum likelihood and L-moments methods. In particular, we show the fact that the GEV distribution can be a reasonable model for the earthquake data via the model checking methods.
Keywords : Earthquake, generalized extreme value distribution, goodness-of-fit test, predicted return levels.