Earthquake Early Warning System Using Ncheck and Hard-Shared Orthogonal Multitarget Regression on Deep Learning

Realizing an effective earthquake early warning system (EEWS) in the case of extensive regions and noisy signals is challenging, particularly in East Java, Indonesia. This letter proposes the rapid detection of the p-wave arrival and determination of the earthquake's hypocenter and magnitude using deep learning. The Ncheck algorithm is used for noise handling for picking the p-arrival on a multistation waveform as a form of picking target window prediction (PTWP). Then, multitarget regression (MTR) with a hard-shared orthogonal optimization model is proposed for earthquake parameter determination. The data sets used contained data of earthquakes recorded at three stations from the Indonesian seismic network in East Java; 2009-2017 data were used for training and validation, and 2019 data were used for real-time testing. The results show that the PTWP for picking p-arrival has a mean absolute error (MAE) of 0.12 s, and the MTR for earthquake magnitude, longitude, latitude, depth, and origin time detection shows MAEs of 0.21 M, 9.44, 18.72, 27.81 km, and 2.78 s, respectively.