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, like the peak displacement (Pd) or squared velocity integral (IV2) techniques; deep-learning methods involve a single neural network model, like 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 occurred in Japan, we construct hybrid deep-learning network (HybridNet) for predicting on-site PGV, which is consist 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; additionally, 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, HybridNet model exhibits better performance on the test dataset than the baseline models. Additionally, 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≥6.5). And 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.

Magnitude estimation is a vital task within earthquake early warning (EEW) systems (EEWSs). To improve the magnitude determination accuracy after P-wave arrival, we introduce an advanced magnitude prediction model that uses a deep convolutional neural network for earthquake magnitude estimation (DCNN-M). In this paper, we use the inland strong-motion data obtained from the Japan Kyoshin Network (K-NET) to calculate the input parameters of the DCNN-M model. The DCNN-M model uses 12 parameters extracted from 3 s of seismic data recorded after P-wave arrival as the input, four convolutional layers, four pooling layers, four batch normalization layers, three fully connected layers, the Adam optimizer, and an output. Our results show that the standard deviation of the magnitude estimation error of the DCNN-M model is 0.31, which is significantly less than the values of 1.56 and 0.42 for the τ_c method and P_d method, respectively. In addition, the magnitude prediction error of the DCNN-M model is not affected by variations in the epicentral distance. The DCNN-M model has considerable potential application in EEWSs in Japan.

Accurately estimating the magnitude within the initial seconds after the P‐wave arrival is of great significance in earthquake early warning (EEW). Over the past few decades, single‐parameter approaches such as the $τc$ and $Pd$ methods have been applied to EEW magnitude estimation studies considering the first 3 s after the P‐wave onset. However, these methods present considerable scatter and are affected by the signal‐to‐noise ratio (SNR) and epicentral distance. In this study, using Japanese K‐NET strong‐motion data, we propose a machine‐learning method comprising multiple parameter inputs, namely, the support vector machine magnitude estimation (SVM‐M) model, to determine earthquake magnitudes and resolve the aforementioned problems. Our results using a single seismological station record show that the standard deviation of the magnitude prediction errors of the SVM‐M model is 0.297, which is less than those of the $τc$ (1.637) and $Pd$ (0.425) methods. The magnitudes estimated by the SVM‐M model within 3 s after the P‐wave arrival are not obviously affected by the SNR or epicentral distance, and not overestimated for $MJMA≤5$⁠. In addition, in an offline EEW application, the magnitude estimation error of the SVM‐M model gradually decreases with increasing time after the first station is triggered, and the underestimation of event magnitudes for $6.5≤MJMA$ gradually improves. These results demonstrate that the proposed SVM‐M model can robustly estimate earthquake magnitudes and has potential for EEW.

The Sichuan–Yunnan region is one of the most seismically vulnerable areas in China. Accordingly, an earthquake early warning (EEW) system for the region is essential to reduce future earthquake hazards. This research analyses the utility of two early warning parameters (τ_c and P_d) for magnitude estimation using 273 events that occurred in the Sichuan–Yunnan region during 2007–2015. We find that τ_c can more reliably predict high-magnitude events during a short P-wave time window (PTW) but produces greater uncertainty in the low-magnitude range, whereas P_d is highly correlated with the event magnitude depending on the selection of an appropriate PTW. Here, we propose a threshold-based evolutionary magnitude estimation method based on a specific combination of τ_c and P_d that both offers more robust advance magnitude estimates for large earthquakes and ensures the estimation accuracy for low-magnitude events. The advantages of the proposed approach are validated using data from 2016–2017 and the Ms 8.0 Wenchuan earthquake in an offline simulation. The proposed concept provides a useful basis for the future implementation of an EEW system in the Sichuan–Yunnan region.

The Sichuan–Yunnan region is a seismically active area. To explore the feasibility of using the support vector machine (SVM) method for magnitude estimation in the area and to improve the rapid magnitude estimation accuracy, we construct an SVM magnitude estimation model using transfer learning (TLSVM‐M model) based on a single‐station record in this study. We find that the magnitude estimation of a single station shows that for the test dataset, within the 3 s time window after the P‐wave arrival, the average absolute error (which reflects the size of the estimated magnitude error as a whole) and standard deviation (which reflects the scatter of magnitude estimation error) of the magnitudes estimated by the TLSVM‐M model are 0.31 and 0.41, respectively, which are less than those of the SVM magnitude estimation model without transfer learning (0.44 and 0.55, respectively), the $τc$ method (1.35 and 1.74, respectively) and the $Pd$ method (0.44 and 0.56, respectively). In addition, in test involving five earthquake events via the TLSVM‐M model, at 1 s after the first station is triggered, the magnitudes of three events (⁠ $Ms$ 4.2, 5.2, and 6.3) are estimated within an error range of ±0.3 magnitude units. For the other two earthquakes (⁠ $Ms$ 6.6 and 7.0), there is an obvious magnitude underestimation problem at 1 s after the first station is triggered, with less underestimation by increasing time after the first station is triggered. Meanwhile, for these two events (⁠ $Ms$ 6.6 and 7.0), within 13 s after the first station was triggered, the magnitude estimation errors are both within ±0.3 magnitude units. The TLSVM‐M model has the capability of rapid magnitude estimation for small‐to‐moderate events in the Sichuan–Yunnan region. Meanwhile, we infer that the proposed model may have potential in earthquake early warning.