Research related to the SERIOUS project was presented at the 49th MIPRO ICT and Electronics Convention in Opatija, Croatia, held from 25 to 29 May 2026. The paper, “Comparative Assessment of Unsupervised Machine Learning Methods for Flood Wave Shape Analysis”, was authored by Maksim Kos, Damir Pintar, Fran Vuić and Kristina Potočki. https://doi.org/10.1109/MIPRO70003.2026.11591532
The study compares three machine learning methods, K-means, hierarchical cluster analysis (HCA) and self-organising maps (SOM), for classifying flood wave shapes using historical hydrological data from the Sava River Basin in Croatia.
The research contributes to the development of data-driven approaches for flood wave classification and supports the SERIOUS project’s work on synthetic design hydrographs under current and future climate conditions.
