Hybrid Deep-Learning Network for Rapid On-Site Peak Ground Velocity Prediction

Rapidly and accurately predicting on-site peak ground velocity (PGV) is important for earthquake hazard mitigation. Traditional methods used to predict PGV involve a single physics-based parameter, such as the peak displacement (Pd) or squared velocity integral (IV2) techniques; deep-learning methods involve a single neural network model, such as the convolutional neural network (CNN) or recurrent neural network (RNN) models, to extract feature for estimating the PGV. Here, based on the training dataset from earthquake events that occurred in Japan, we construct a hybrid deep-learning network (HybridNet) for predicting on-site PGV, which consists of CNN and RNN feature extraction blocks. We use physics-based feature time series, waveforms, and a site feature from a single station as the input of HybridNet model. In addition, we concatenate the features from the CNN block, RNN block, and site feature to predict the on-site PGV. We show that concerning the standard deviation of error, the mean absolute error, and the coefficient of determination for PGV prediction, the HybridNet model exhibits better performance on the test dataset than the baseline models. In addition, the potential damage zone (PDZ) can be predicted by interpolating the predicted PGVs at the stations. Based on the predicted PGV of the HybridNet model, we investigate the feasibility of PDZ estimation on five earthquakes (
$M \ge6.5$
). Also, we find that within a few seconds after the arrival of P-wave, the predicted PDZ is consistent well with the PGV ShakeMap obtained from the U.S. Geological Survey.