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.

Lack of observation network in the vicinity of oceanic intraplate earthquake lead the estimation of coseismic fault slip with high uncertainty. Satriano et al. [2] and Wei et al. [3] found NNE trending left-lateral slip as the primary features. In another hand, Yue et al. [4] and Hill et al. [5] proposed WNW trending right-lateral faults structure as the main characteristic. Here, we investigate the coseismic fault model that could explain the coseismic offset both vertical and horizontal in a 3-D heterogeneous earth structure. We constructed finite element model that include three-dimensional velocity structure, topography/bathymetry, spherical-earth and subducting slab. In this study, we employed scaling slip to adjust slip amount and total seismic moment. Instead of original slip amount, we preserve seismic moment as a basis comparison. Based on vertical and horizontal observation data, WNW trending right-lateral fault could fit better than NNE trending left-lateral fault. The present study demonstrates best-fit calculation using scaling slip optimized to the horizontal or vertical observation lead the both fault model worsen the misfit of vertical or horizontal component, respectively. This result analysis indicates a trade-off between vertical and horizontal component and reflects the importance of revisiting the fault slip modeling incorporating vertical and horizontal data equally.