Recurrent Convolutional Neural Networks help to predict location of Earthquakes

Code

• github.com/romakail/Earthquake_prediction_DNN
  OfficialIn paperpytorch★ 12

Abstract

We examine the applicability of modern neural network architectures to the midterm prediction of earthquakes. Our data-based classification model aims to predict if an earthquake with the magnitude above a threshold takes place at a given area of size 10 10 kilometers in 10-60 days from a given moment. Our deep neural network model has a recurrent part (LSTM) that accounts for time dependencies between earthquakes and a convolutional part that accounts for spatial dependencies. Obtained results show that neural networks-based models beat baseline feature-based models that also account for spatio-temporal dependencies between different earthquakes. For historical data on Japan earthquakes our model predicts occurrence of an earthquake in 10 to 60 days from a given moment with magnitude M_c > 5 with quality metrics ROC AUC 0.975 and PR AUC 0.0890, making 1.18 10^3 correct predictions, while missing 2.09 10^3 earthquakes and making 192 10^3 false alarms. The baseline approach has similar ROC AUC 0.992, number of correct predictions 1.19 10^3, and missing 2.07 10^3 earthquakes, but significantly worse PR AUC 0.00911, and number of false alarms 1004 10^3.

Reproductions