Application of Markov Chain for Estimating Earthquake Magnitude Pattern Around Java Island
Afif Amrullah Taufiq, Udjianna Sekteria Pasaribu*, RR Kurnia Novita Sari

Statistics Research Division, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Indonesia
*Corresponding Author: udjianna[at]math.itb.ac.id

Abstract

The purpose of this study is to apply a Markov chain model in analyzing the behaviour magnitude of earthquakes around Java Island. A 3x3 transition probability matrix is constructed by data from Indonesian Agency for Meteorology, Climatology, and Geophysics from January 1, 2015 to December 20, 2022. The data is divided into three states, namely minor earthquake (magnitude <5), moderate earthquake (5<= magnitude <6), and strong earthquake (magnitude >=6). The study shows that: 1) number of communication class is one since there are transitions between all pairs of states in the matrix and therefore it is possible to reach any state from any other state , 2) type of each state is recurrent since the Markov chain is irreducible and has at least one state is recurrent.

Keywords: Markov Chain, Transition Probability Matrix, Classification of States, Earthquake Magnitude

Topic: MATHEMATICS AND STATISTICS