Toward enhanced coastal flooding forecasting using deterministic and probabilistic models

This study focuses on the application of advanced data‐driven modeling techniques to assess and predict high‐tide flooding (HTF) risks in Oman. The research analyzes the duration, frequency, and economic impacts of HTF and employs machine learning (ML) and deep learning (DL) models as practical tools for improving local flood prediction and management. Coastal flooding refers to the temporary inundation of low-lying coastal areas caused by the combined effects of high tides, storm surges, and wave-driven water level rise

This applicative study identified pronounced seasonal variability in flooding, with Salalah and Muscat exhibiting a strong increase in HTF events during the summer months, while Masirah experiences peak events in winter. Decomposition of the still water levels into tidal and non-tidal components showed that meteorological forcing predominantly controls HTF in Salalah and Masirah, whereas the flood events in Muscat are governed by tidal dynamics. Furthermore, the pattern of rising HTF frequency since 2009, in tandem with increasing sea level, underscores the accelerating vulnerability of these coastal areas.