Time Series Analysis on Earthquakes Using EDA and Machine Learning

An earthquake is a sudden, rapid shaking of the ground caused by the shifting of the Earth's tectonic plates. Earthquakes pose serious threats that cause economic losses and casualties. To mitigate such risks, it is crucial to better understand earthquakes through data-driven analysis. In this paper, we propose an approach to time series analysis over earthquake data, consisting of two steps: exploration and prediction. The exploration step relies on exploratory data analysis (EDA) comprising descriptive statistics and data visualization, whereas the prediction step focuses on how to predict the number of earthquakes for the following years. We perform our time series analysis using various machine learning techniques over a global earthquake dataset from 1965-2016 and report insights as well as lessons learned from the study.

I. Introduction

An earthquake is a natural phenomenon occurring when there is a sudden, rapid shaking of the ground. Earthquakes are usually caused by the breaking and displacement of rocks below Earth’s crust [1]. The deadliest earthquake ever recorded happened in 1556, striking the province of Shaanxi, China, and claiming the lives of about 830,000 people at the time.¹ In Indonesia, over 200,000 people lost their lives in the 2004 Indian Ocean earthquake and tsunami. Without a doubt, earthquakes may bring tremendous (negative) impacts to human lives and also the economy. ¹

http://content.time.eom/time/specials/packages/completelist/0,29569,1953425,00.html