LASSE: Learning Active Sampling for Storm Tide Extremes in Non-Stationary Climate Regimes
This work addresses the computational intractability of risk assessment for storm tides in climate studies, offering a scalable solution for disaster management and climate adaptation.
The paper tackles the problem of efficiently identifying tropical cyclones that cause extreme storm tides in non-stationary climate regimes, using an active learning approach that achieves 100% precision in retrieving rare destructive storms with less than 20% of the required simulations.
Identifying tropical cyclones that generate destructive storm tides for risk assessment, such as from large downscaled storm catalogs for climate studies, is often intractable because it entails many expensive Monte Carlo hydrodynamic simulations. Here, we show that surrogate models are promising from accuracy, recall, and precision perspectives, and they "generalize" to novel climate scenarios. We then present an informative online learning approach to rapidly search for extreme storm tide-producing cyclones using only a few hydrodynamic simulations. Starting from a minimal subset of TCs with detailed storm tide hydrodynamic simulations, a surrogate model selects informative data to retrain online and iteratively improves its predictions of damaging TCs. Results on an extensive catalog of downscaled TCs indicate 100% precision in retrieving rare destructive storms using less than 20% of the simulations as training. The informative sampling approach is efficient, scalable to large storm catalogs, and generalizable to climate scenarios.