Generalized Neural Networks for Real-Time Earthquake Early Warning
This enables global real-time EEW with reduced empirical configurations, though it is incremental as it builds on existing deep learning approaches for seismic monitoring.
The paper tackles the problem of neural networks for earthquake early warning (EEW) generalizing poorly across regions by using a data recombination method to train models on generalized earthquakes, enabling application to diverse areas like Japan and California with mean location errors of 2.6-6.3 km and magnitude errors of 0.05-0.17 within 4 seconds.
Deep learning enhances earthquake monitoring capabilities by mining seismic waveforms directly. However, current neural networks, trained within specific areas, face challenges in generalizing to diverse regions. Here, we employ a data recombination method to create generalized earthquakes occurring at any location with arbitrary station distributions for neural network training. The trained models can then be applied to various regions with different monitoring setups for earthquake detection and parameter evaluation from continuous seismic waveform streams. This allows real-time Earthquake Early Warning (EEW) to be initiated at the very early stages of an occurring earthquake. When applied to substantial earthquake sequences across Japan and California (US), our models reliably report earthquake locations and magnitudes within 4 seconds after the first triggered station, with mean errors of 2.6-6.3 km and 0.05-0.17, respectively. These generalized neural networks facilitate global applications of real-time EEW, eliminating complex empirical configurations typically required by traditional methods.