ConvLSTM Neural Networks for seismic event prediction in Chile

Predicting seismic risk is a challenging task in order to avoid catastrophic effects. In this work, two models based on Convolutional Network (CNN) and Long Short Term Memory (LSTM) networks are proposed to predict the seismic risk in Chile. In particular, a ConvLSTM and a Multi-column ConvLSTM network are used for the prediction of the average number of seismic events greater than 2,8 magnitude on the Richter scale, in the Chilean regions of Coquimbo and Araucania between the years 2010 and 2017. For this model, the values of the intensity function estimated through an ETAS model and the accumulated displacement prior to a the seismic events are used as inputs. In particular, given the spatial and temporal characteristics of the seismic data, matrices of size 20x20 of the last 20 days are considered to predict the average number of seismic events of the next day in a given area. From the results obtained, the Multi-column ConvLSTM network achieved a coefficient of determination of 0,804 and a lower MSE than other networks.