AI and HPC for intense rain event early warning leveraging real-time weather radar
Global changes are increasing the frequency and intensity of extreme weather events, posing challenges for forecasting localized phenomena with sub-grid resolution. The Hi-WeFAI project addresses this by combining high-performance computing, Federated Artificial Intelligence, and heterogeneous sensor networks to improve short-term precipitation forecasting and flood nowcasting. In this paper, we present preliminary results using a transformer-based radar prediction model coupled with a flood model to generate high-resolution early warning maps. The results from the Naples pilot site improved accuracy and detail, highlighting the potential of the hybrid AI and HPC approach to support quasi-real-time decision-making and disaster risk reduction.
Authors
- Pasquale De Luca (ORCID: https://orcid.org/0000-0001-7031-920X)
- Diana Di Luccio (ORCID: https://orcid.org/0000-0002-0810-2250)
- Dante D. Sánchez‐Gallegos (ORCID: https://orcid.org/0000-0003-0944-9341)
- Ciro Giuseppe De Vita (ORCID: https://orcid.org/0000-0002-3828-0170)
- Gennaro Mellone (ORCID: https://orcid.org/0000-0002-9545-9978)
- Emanuel Di Nardo (ORCID: https://orcid.org/0000-0002-6589-9323)
- M. Sarno
- Vincenzo Capozzi (ORCID: https://orcid.org/0000-0002-8279-9922)
- Raffaele Montella (ORCID: https://orcid.org/0000-0002-4767-2045)
- Vincenzo Bucciero
- Pasquale Corvino
Institutions
- Parthenope University of Naples (IT)
- FIT Consulting (Italy) (IT)
- R2M Solution (Italy) (IT)
- Universidad Carlos III de Madrid (ES)
Publication Details
- Published
- 2025-09-15
- DOI
- https://doi.org/10.1109/escience65000.2025.00048
- Primary Topic
- Precipitation Measurement and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00