Improved Storm Surge Prediction and Extreme Sea Level Future Projections in the Indian Ocean using Deep Learning

LSTM-Based Storm Surge Data Reconstruction and Climate Projections for 29 Tide Gauge Locations in the Indian Ocean IOSSR – Indian Ocean Storm Surge Reconstruction:This dataset provides hourly storm surge reconstructions from 1979 to 2021 at 29 tide gauge locations across the Indian Ocean. Reconstructions are generated using a data-driven Long Short-Term Memory (LSTM) deep learning model. The model uses atmospheric predictors from the ERA5 reanalysis dataset, including wind speed, sea-level pressure, and air temperature. Historical and Future Climate Projections:Storm surge projections (1979-2100) are produced using the LSTM model driven by bias-corrected predictors from Coupled Model Intercomparison Project Phase 6 (CMIP6) climate model ensemble. The predictor data for CMIP6 models are sourced from Xu et al., 2021, who compiled an ensemble dataset using outputs from 18 CMIP6 models. The projections include: Hist: Historical period simulation using CMIP6 predictors. SSP2-4.5: A moderate-emissions scenario reflecting middle-of-the-road development pathways. SSP5-8.5: A high-emissions scenario based on continued reliance on fossil fuels. Reference : Xu, Z., Han, Y., Tam, CY. et al. Bias-corrected CMIP6 global dataset for dynamical downscaling of the historical and future climate (1979–2100). Sci Data 8, 293 (2021). https://doi.org/10.1038/s41597-021-01079-3