Data for: In-Depth Comparison of Deep Artificial Neural Network Architectures on Seismic Events Classification

Published: 19-01-2020| Version 1 | DOI: 10.17632/dv8nwdd36k.1
João Paulo Canário,
Rodrigo de Mello,
Ricardo Rios,
Fernando Huenupan,
Millaray Curilem


This dataset includes the signals that were collected from LAV, one of the seven seismic stations of the Llaima volcano located at the western edge of Andes in Araucania Region (S 38º41' - W 71º44'), Chile. These signals were being recorded from 2010 to 2016, sampled at 100Hz and filtered using a 10th-order Butterworth bandpass filter in range 1-10 Hz to preserve the bandwidth that contains the range of interest. Moreover, it was normalized using their maximal values and labelled by the specialists from the Observatorio Vulcanológico de los Andes Sur (OVDAS) into four classes: Long Period (LP); Tremor (TR); Volcano-Tectonic; and Tectonic (TC). Finally, this data can be used to help to improve the analysis of volcano seismic signals. This directory contains the following datasets: SEISMIC EVENTS DATASET lp.hdf5, tr.hdf5, vt.hdf5, tc.hdf5 - each file contain the correspondig seismic event class