Earthquake Early Warning with Deep Learning: Application to the 2016 Central Apennines, Italy Earthquake Sequence

Abstract:

Earthquake early warning (EEW) systems detect hazardous earthquakes, estimate their source parameters, and transmit warnings to the public. Conventional EEW algorithms depend on picking and analyzing the first seismic compressional wave (i.e., P wave). Seismic waveforms contain more information and can potentially be used to estimate earthquake source parameters with the fewest possible number of stations and to promptly transmit warning information. Deep learning techniques provide opportunities for extracting and exploiting the features behind seismic waveforms. In this study, we develop a fully automatic real-time EEW system by directly mapping seismic waveform data to earthquake source parameters using deep learning techniques. We designed a multi-branch fully convolutional network. One branch network is designed for earthquake location and the other for magnitude estimation. Earthquake source parameters are solved starting from the earliest stations receiving effective earthquake signals. The solutions are then improved by receiving more data in an evolutionary way. We apply the system to monitor the 2016 Central Apennines, Italy earthquake sequence. The result shows earthquake locations and magnitudes can be reliably determined as early as four seconds after the earliest P phase, with mean error ranges of 6.8–3.7 km and 0.31–0.23, respectively. Our work demonstrates the feasibility of using deep learning techniques for real-time earthquake early warning.