Earthquake Prediction Model Based on Geomagnetic Field Data Using Automated Machine Learning

The observation of geomagnetic anomalies appearing prior to earthquakes (EQs) is theorized to be generated by underground seismic processes. However, these pre EQ anomalies can only provide “postdiction” and are still inadequate for practical applications. So, this study was conducted to pursue the long-term quest for real EQ prediction models through the adoption of automated machine learning (AutoML), which automates many laborious routines of model development. In this study, more than 50 years of geomagnetic field data recorded at 131 magnetometer observatories globally were acquired. Several features were extracted from them through wavelet scattering transform (WST). The features were used as the input to model optimization, of which the strategy for automatic algorithm selection and hyperparameter tuning was performed based on the asynchronous successive halving algorithm (ASHA). From the implementation of five classification algorithms, neural network (NN) yielded the best-performing model with an accuracy of 83.29%. The results showed that practical EQ prediction models could be achievable even for complex systems like lithospheric and seismo-induced geomagnetic processes by employing AutoML.