A preliminary analysis of high water events in Venice based on multi-decadal observations and clustering

Cardillo Franco Alberto, Andrigo Angela, De Biasio Francesco, Debole Franca, Favaro Marco, Papa Alvise, Straccia Umberto, Vignudelli Stefano

Machine learning; Clustering 

High water events in Venice are a recurrent phenomenon, as the city is located only slightly above mean sea level and is directly in"uenced by water-level variations within the lagoon. Repeated "ooding has signi!cant economic and social impacts, limits pedestrian and naval tra#c and contributes to the degradation of buildings and cultural heritage. Current forecasting systems primarily estimate water levels and peak values, and these are typically estimated at a limited number of locations. Data-driven approaches, in particular Machine Learning (ML) methods, analyze historical data without relying on prede!ned, human-designed model structures. We present a preliminary analysis based on several clustering approaches, including k-means, DBSCAN, and deep learning–based methods, applied to a multi-decadal atmospheric dataset and to the longest available reconstructed hourly sea-level records for the northern Adriatic Sea, specifically developed for this study.