MLP, Recurrent, Convolutional and LSTM Neural Networks detect Seismo-TEC anomalies potentially related to the Iran Sarpol-e Zahab (Mw=7.3) earthquake of 12 November 2017

Abstract

A strong earthquake (M_w=7.3) in Iran Sarpol-e Zahab (34.911 N, 45.959 E, ~19 km depth) occurred on November 12, 2017, at 18:18:17 UTC (LT=UTC+03:30). Six different Neural Network (NN) algorithms including Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), Long-Short Term Memory (LSTM) and CNN-LSTM were implemented to survey the four months of GPS Total Electron Content (TEC) measurements during the period of 01 August to 30 November 2017 around the epicenter of the mentioned earthquake. By considering the quiet solar-geomagnetic conditions, every six methods detect anomalous TEC variations 9 days prior to earthquake. Since time-series of TEC variations follow a nonlinear and complex behavior, therefore intelligent algorithms such as NN can be considered as an appropriate tool for modelling and prediction of TEC time-series. Moreover, multi-methods analyses beside the multi precursor’s analyses decrease uncertainty and false alarms and consequently lead to confident anomalies.