Identification of Electromagnetic Pre-Earthquake Perturbations from the DEMETER Data by Machine Learning

Are the Significant Ionospheric Anomalies Associated with the 2007 Great Deep-Focus Undersea Jakarta–Java Earthquake?

This work is an attempt to critically analyze the correlation between great deep-focus undersea earthquake and possible ionospheric anomalies. The significant TEC (total electron content) temporal and spatial anomalies were detected over the epicenter of 2007 Mw7.5 Jakarta–Java earthquake, and they coincide well with the striking plasma anomalies in the ionosphere in situ observed by the LEO (low Earth orbit) satellite. The localization and synchronization of the disturbances during the earthquake suggest that these ionospheric anomalies are highly related to this large undersea earthquake. In order to identify this correlation, we made efforts to distinguish seismo-associated signals from large electromagnetic noise due to solar and geomagnetic activities, natural non-seismic sources and known artificial signals. Nevertheless, the difficulties of this work should be recognized and approached with caution. This special (deep-focus and undersea) case study here provides us with valuable information on the study of lithosphere–atmosphere–ionosphere (LAI) coupling process and reminds us that deep-focus undersea seismic events need to be treated more carefully and discreetly in the future.

SafeNet: SwArm for Earthquake Perturbations Identification Using Deep Learning Networks

Low Earth orbit satellites collect and study information on changes in the ionosphere, which contributes to the identification of earthquake precursors. Swarm, the European Space Agency three-satellite mission, has been launched to monitor the Earth geomagnetic field, and has successfully shown that in some cases it is able to observe many several ionospheric perturbations that occurred as a result of large earthquake activity. This paper proposes the SafeNet deep learning framework for detecting pre-earthquake ionospheric perturbations. We trained the proposed model using 9017 recent (2014–2020) independent earthquakes of magnitude 4.8 or greater, as well as the corresponding 7-year plasma and magnetic field data from the Swarm A satellite, and excellent performance has been achieved. In addition, the influence of different model inputs and spatial window sizes, earthquake magnitudes, and daytime or nighttime was explored. The results showed that for electromagnetic pre-earthquake data collected within a circular region of the epicenter and with a Dobrovolsky-defined radius and input window size of 70 consecutive data points, nighttime data provided the highest performance in discriminating pre-earthquake perturbations, yielding an F1 score of 0.846 and a Matthews correlation coefficient of 0.717. Moreover, SafeNet performed well in identifying pre-seismic ionospheric anomalies with increasing earthquake magnitude and unbalanced datasets. Hypotheses on the physical causes of earthquake-induced ionospheric perturbations are also provided. Our results suggest that the performance of pre-earthquake ionospheric perturbation identification can be significantly improved by utilizing SafeNet, which is capable of detecting precursor effects within electromagnetic satellite data.