Prediction of storm surge on evolving landscapes under climate change

Abstract

Planners who wish to manage coastal flood risk with long-lived infrastructure (e.g., levees, floodwalls) under a constrained computational budget face a tradeoff. Simulating a large number of future time periods or scenarios with different assumptions about land subsidence, sea level rise, land accretion, imposes a limit on how many storm simulations can be run in each scenario and time period. Machine learning approaches have been developed to reduce the computational burden of predicting storm surge from many tropical cyclone events, but prior efforts focus on predicting surge as a function of storm parameters on a single landscape. In this analysis, we present a deep learning model that also incorporates landscape characteristics and boundary conditions (e.g., mean sea level). The model is informed by a dataset of peak surge elevations from Advanced Circulation (ADCIRC) hydrodynamic simulations of coastal Louisiana in eleven scenarios: a 2020 baseline and decadal time slices from 2030 to 2070 under two scenarios varying land subsidence and sea level rise rates. Training on ten scenarios to make predictions on the eleventh yields a grand RMSE of 0.086 m and grand MAE of 0.050 m over 90 storms per scenario and over 94,000 geospatial locations. We also aggregated the 90 storms in each scenario to generate an annual exceedance probability distribution; a two-sided Kolmogorov-Smirnov test comparing AEP estimates from the model predictions to the original ADCIRC simulations rejected the null hypothesis that the predictions and ADCIRC AEP values were drawn from the same distribution only 1.1% of the time.