LFW2BBP: Broadband Ground‐Motion Parameters Estimation Using Physics‐Based Simulated Low‐Frequency Waveforms and Deep Learning

Abstract Accurate prediction of broadband ground motion parameters is important for earthquake disaster prevention and mitigation. Due to the lack of high wave number components in the source rupture process and velocity models, physics‐based ground motion simulation methods can only reliably produce low‐frequency ground motions (1 Hz). In this study, we developed a deep learning network, LFW2BBP, which maps physics‐based simulated low‐frequency ground motion waveforms to broadband ground motion parameters. The LFW2BBP extracts features of low‐frequency ground motion in time domain waveform, time‐frequency domain spectrum, and spectral acceleration and integrates these features to establish a relationship with high‐frequency ground motion parameters. Sensitivity tests were conducted to verify the stability and robustness of the LFW2BBP. Finally, we combined physics‐based simulation and LFW2BBP to predict broadband ground motion parameters for the 2016 7.0 Kumamoto earthquake. The predicted results show good agreement with the observations.