Rapid and accurate prediction of peak storm surges across an extensive coastal region is necessary to inform assessments used to design the systems that protect coastal communities' life and property. Significant advances in high-fidelity, physics-based numerical models have been made in recent years, but use of these models for probabilistic forecasting and probabilistic hazard assessment is computationally intensive. Several surrogate modeling approaches based on existing databases of high-fidelity synthetic storm surge simulations have been recently suggested to reduce computational burden without substantial loss of accuracy. In these previous studies, however, the surrogate modeling approaches relied on a tropical cyclone condition at one moment (usually at or near landfall), which is not always most correlated with the peak storm surge. In this study, a new one-dimensional convolutional neural network model combined with principal component analysis and a k-means clustering (C1PKNet) is presented that can rapidly predict peak storm surge across an extensive coastal region from time-series of tropical cyclone conditions, namely the storm track. The C1PKNet model was trained and cross-validated for the Chesapeake Bay area of the United States using existing database of 1031 high-fidelity storm surge simulations, including both landfalling and bypassing storms. Moreover, the performance of the C1PKNet model was evaluated based on observations from three historical hurricanes (Hurricane Isabel in 2003, Hurricane Irene in 2011, and Hurricane Sandy in 2012. The results indicate that the C1PKNet model is computationally e cient and can predict peak storm surges from realistic tropical cyclone track time-series. We believe that this new surrogate model can enhance coastal resilience by providing rapid storm surge predictions.

Rapid prediction of the spatial distribution of the run-up from nearfield tsunamis is critically important for tsunami hazard characterization. Even though significant advances have been made over the last decade, physicsbased numerical models are still computationally intensive. Here, we present a response surface methodology (RSM)-based model called the tsunami run-up response function (TRRF). Derived from a discrete set of tsunami simulations, TRRF can produce a rapid prediction of a near-field tsunami run-up distribution that takes into account the influence of variable local topographic and bathymetric characteristics in a given region. This new method reduces the number of simulations required to build an RSM model by separately modeling the leading order contribution and the residual part of the tsunami run-up distribution. Using the northern region of Puerto Rico as a case study, we investigated the performance (accuracy, computational time) of the TRRF. The results reveal that the TRRF achieves reliable prediction while reducing the prediction time by six orders of magnitude (computational time: < 1 second per earthquake).

Abstract. Timely detection of tsunamis with water level records is a critical but logistically challenging task because of outliers and gaps. Since tsunami detection algorithms require several hours of past data, outliers could cause false alarms, and gaps can stop the tsunami detection algorithm even after the recording is restarted. In order to avoid such false alarms and time delays, we propose the Tsunami Arrival time Detection System (TADS), which can be applied to discontinuous time series data with outliers. TADS consists of three algorithms, outlier removal, gap filling, and tsunami detection, which are designed to update whenever new data are acquired. After calibrating the thresholds and parameters for the Ulleung-do surge gauge located in the East Sea (Sea of Japan), Korea, the performance of TADS was discussed based on a 1-year dataset with historical tsunamis and synthetic tsunamis. The results show that the overall performance of TADS is effective in detecting a tsunami signal superimposed on both outliers and gaps.

Rapid and accurate prediction of peak storm surges across an extensive coastal region is necessary to inform assessments used to design the systems that protect coastal communities’ life and property. Significant advances in high-fidelity, physics-based numerical models have been made in recent years, but use of these models for probabilistic forecasting and probabilistic hazard assessment is computationally intensive. Several surrogate modeling approaches based on existing databases of high-fidelity synthetic storm surge simulations have been recently suggested to reduce computational burden without substantial loss of accuracy. In these previous studies, however, the surrogate modeling approaches relied on a tropical cyclone condition at one moment (usually at or near landfall), which is not always most correlated with the peak storm surge. In this study, a new one-dimensional convolutional neural network model combined with principal component analysis and a k-means clustering (C1PKNet) is presented that can rapidly predict peak storm surge across an extensive coastal region from time-series of tropical cyclone conditions, namely the storm track. The C1PKNet model was trained and cross-validated for the Chesapeake Bay area of the United States using existing database of 1031 high-fidelity storm surge simulations, including both landfalling and bypassing storms. Moreover, the performance of the C1PKNet model was evaluated based on observations from three historical hurricanes (Hurricane Isabel in 2003, Hurricane Irene in 2011, and Hurricane Sandy in 2012). The results indicate that the C1PKNet model is computationally e cient and can predict peak storm surges from realistic tropical cyclone track time-series. We believe that this new surrogate model can enhance coastal resilience by providing rapid storm surge predictions.

Tsunamis, mainly caused by shallow subduction-zone earthquakes, can cause severe damage to coastal communities once they occur, especially to near-field areas. To mitigate the tsunami damage and increase the resiliency of coastal communities, it is crucial to better understand a tsunami source and assess its impact. To better understand the tsunami source, tsunami inversion models, which can infer a tsunami source from observed data, have been widely developed (Satake, 2009). Depending on the input data, tsunami inversion models can be divided into three types. The first type is a tsunami inversion model that relies on seismic waveform data alone or combined with other data such as local strong motion, GPS (Global Positioning System), InSAR (Interferometric Synthetic Aperture Radar), and DART (Deep-ocean Assessment and Reporting of Tsunamis) data (e.g., Lay et al., 2011;Yokota et al., 2011;Yue et al., 2014). Instead of relying on seismic waveform data, the second type is a tsunami inversion model that uses tsunami waveforms (such as DART, tide gauge data) alone or combined with GPS and/or InSAR data (e.g.,