Features Engineering and Features Extraction of Volcano-Tectonic (VT) Earthquake Martanto (a*,c), Andri Dian Nugraha (b), David P. Sahara (b), Zulfakriza (b), Devy Kamil Syahbana (c), Imam C. Priambodo (a, c), Puput P. Rahsetyo (a), Ardianto (a)
a) Master Program of Geophysical Engineering, Faculty of Mining and Petroleum Engineering, Institut Teknologi Bandung, Bandung, Indonesia.
* martanto[at]live.com
b) Global Geophysics Research Group, Faculty of Mining and Petroleum Engineering, Institut Teknologi Bandung, Bandung, Indonesia.
c) Center for Volcanology and Geological Hazards Mitigation, Geological Agency, Ministry of Energy and Mineral Resources, Indonesia.
Abstract
Volcano-Tectonic earthquake or commonly referred to as VT is an earthquake caused by magma intrusion that increases the pressure below the surface of the volcano. The accumulation of stress that continuously affects the elasticity of rocks causes fractures when the elasticity limit of rocks is exceeded. VT is one of the earthquakes that is used as a parameter to determine the level of volcanic activity. To understand the characteristics of VT, it is necessary to do features engineering which is a process of extraction features so that the characteristics of VT are obtained. The data used in this study were 2,726 VT events and 11,533 waveforms of Agung volcano during the 2017 crisis. The extraction process is conducted by performing statistics calculations in temporal and spectral domains. Waveform of VT is univariate time series data and to perform the extraction features, this study using changes in amplitude value to the time taken from the waveform. Features that were successfully extracted from this study are as many as 102 features for each domain. The result of the extraction of these features can then be used as input parameters in performing auto classification of VT using machine learning.
Keywords: volcanology, volcano-tectonic, machine learning, features engineering, features extraction
