On-site alert-level earthquake early warning using machine-learning-based prediction equations

Abstract

Summary To rapidly and accurately provide alerts at target sites near the epicenter, we develop an on-site alert-level earthquake early warning (EEW) strategy involving P-wave signals and machine-learning-based prediction equations. These prediction equations are established for magnitude estimation and peak ground velocity (PGV) prediction accounting for multiple feature inputs and the support vector machine (SVM). These prediction equations are called SVM-M model for estimating magnitude and SVM-PGV model for predicting PGV, respectively. According to comparison between the predicted magnitude and PGV values with the predicted threshold values (M = 5.7 and PGV = 9.12 cm/s, respectively), different alert level (0, 1, 2, 3) is issued at the different recording site when the predicted magnitude or PGV values exceed the given threshold values. Alert level 3 means that both the predicted magnitude and the predicted PGV exceed a given threshold, and there may be serious damage in this recording site. We apply the method to three destructive earthquake events (M ≥ 6.5) occurred in Japan, and our results indicate that with regard to the performance of SVM-PGV model for predicting PGV, at 3 s after P-wave arrival, the percentage of successful alarms (SAs) for these three events is higher than 95 per cent, 73 per cent and 94 per cent, respectively, and the percentage of false alarms approaches 0. Additionally, with regard to the performance of SVM-M model for estimating magnitude, at 3 s after P-wave arrival, the percentage of SAs for these three events exceeds 95 per cent, and the percentage of missed alarms approaches 0. Moreover, almost all stations in the areas PGV ≥ 16 cm/s (IMM ≥ Ⅶ) near the epicenter issue alert level 3. The proposed method provides potential applications in EEW system.

Real-Time Seismic Intensity Measurements Prediction for Earthquake Early Warning: A Systematic Literature Review

“…Song et al [69] used the least squares support vector machine model to construct a continuous prediction model of the PGV by selecting seven characteristic parameter inputs of the P wave. Chiang et al [24] proposed the use of intelligent strong motion prediction to predict IMs, whereby a CNN is used to determine the relationship between the features extracted from the initial P wave and the strong motion is used to predict whether the GPA of subsequent waves exceeds a predetermined threshold. To reduce the complexity of multiparameter calculations, Hsu et al [70] selected the two parameters of the first 3 s of two P wave signals and used an artificial neural network algorithm with the introduction of different Site Characteristic Parameters for PGA prediction.…”

“…For example, the length and width of ruptures were taken into account to obtain more accurate IMs predictions [20,21]. Various advanced neural network algorithms were used to improve the efficiency of early warning systems [22][23][24].…”

Earthquake Detection Using Stacked Normalized Recurrent Neural Network (SNRNN)

“…Ref. [4] proposed an on-site EES for magnitude and ground velocity detection using multiple features and the SVM method. The early warning system issues alerts at different levels when the magnitude of an event exceeds a threshold value.…”

Early Earthquake Detection Using Batch Normalization Graph Convolutional Neural Network (BNGCNN)

“…Ref. [10] designed an earthquake early warning system using SVM to predict magnitude and peak ground velocity. The proposed system can effectively generate an alert at different levels from 0 to 3.…”