ConvLSTM Neural Networks for seismic event prediction in Chile

Alex Gonzalez Fuentes, Orietta Nicolis, Billy Peralta, Marcello Chiodi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 2021 IEEE 28th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665412216
DOIs
Publication statusPublished - 5 Aug 2021
Event28th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2021 - Virtual, Lima, Peru
Duration: 5 Aug 20217 Aug 2021

Publication series

NameProceedings of the 2021 IEEE 28th International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2021

Conference

Conference28th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2021
Country/TerritoryPeru
CityVirtual, Lima
Period5/08/217/08/21

Keywords

  • Deep learning
  • ETAS
  • prediction
  • seismic risk

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)
  • Information Systems and Management
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'ConvLSTM Neural Networks for seismic event prediction in Chile'. Together they form a unique fingerprint.

Cite this