Earthquake detection and location for Earthquake Early Warning Using Deep Learning

Abstract Earthquake Early Warning System (EEWS) is a warning system that provides information about the estimated S wave arrival time, which can cause significant and destructive seismic energy using carried by P wave. Technological advances in analyzing data supported big data, interconnection between networks, high-performance computing systems era of 4.0 industrial revolution have posed challenges to process analyze earthquake early modern seismological techniques. identification events key time efficiency accelerate dissemination information. Here, we implement deep learning for detection classification noise signals raw historical from 3 component BMKG single station (2014 -2020) subduction zone West Sumatra. The feature selection waveform only selected earthquakes distance cluster close centroid. Statistically, results training testing show good convergent performance. This result preliminary study learning, targeted at p its association estimate location record channels.