ROSERS -Real-time On-Site Estimation of Response Spectra

Various earthquake early warning (EEW) methodologies have been proposed globally for speedily estimating information (i.e., location, magnitude, ground-shaking intensities, and/or potential consequences) about ongoing seismic events for real-time/near real-time earthquake risk management. Conventional EEW methods have often been based on the inferred physics of the fault ruptures combined with simplified empirical models to estimate the source parameters and intensity measures of interest. This approach can lead to significant uncertainties in real-time forecasting and decision-making. Given the recent boost in computational resources, data-driven methods/models are widely accepted as effective alternatives for EEW. This study introduces a highly accurate deep-learning-based computational framework named ROSERS (Real-time On-Site Estimation of Response Spectra) to estimate the acceleration response spectrum (𝑆𝑎(𝑇)) of the expected on-site ground motion waveforms using early non-damage-causing p-waves and site characteristics. The framework is trained using a carefully selected extensive database of ground motions. Due to the well-known correlation of 𝑆𝑎(𝑇) with structures’ seismic response and resulting damage/losses, rapid and accurate knowledge of expected on-site 𝑆𝑎(𝑇) is highly beneficial to various end-users to make well-informed decisions. The framework is thoroughly assessed through multiple statistical tests and the analyses demonstrate that the overall framework leads to excellent prediction power to be implemented in a real-time setting