Articles | Volume 26, issue 7
https://doi.org/10.5194/nhess-26-3129-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-26-3129-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Evaluation of AI-based seasonal weather ensembles as input for fluvial flood risk estimation: a case study over the Elbe basin
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
Alison Poulston
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
Marius Koch
Nvidia Corporation, 2788 San Tomas Expressway, Santa Clara, CA 95051, USA
Georg Ertl
Nvidia Corporation, 2788 San Tomas Expressway, Santa Clara, CA 95051, USA
Kirsty Brown
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
James Butler
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
Anthony Hammond
JBA Consulting, Skipton, BD23 3FD, United Kingdom
Owen Jordan
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
Sarah Warren
JBA Consulting, Skipton, BD23 3FD, United Kingdom
JBA Trust, Skipton, BD23 3FD, United Kingdom
Lancaster Environment Centre, Lancaster University, Lancaster, LA1 4YQ, United Kingdom
Paul J. Young
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
School of Engineering, Newcastle University, Newcastle, NE1 7RU, United Kingdom
David Wood
JBA Risk Management, Skipton, BD23 3FD, United Kingdom
Model code and software
NVIDIA Earth2Studio PhysicsNeMo Contributors https://github.com/NVIDIA/earth2studio
Rainfall-Runoff modelling playground Ondřej Čertík et al. https://github.com/kratzert/RRMPG
Short summary
Floods cause major social and economic losses, but estimating risk is difficult because extreme events are rare. We used artificial intelligence to generate over a thousand realistic winter weather seasons and river flows for the Elbe basin. The approach reproduced observed patterns and produced a wider range of extreme storms, showing that artificial intelligence can expand plausible flood scenarios for improved risk assessment.
Floods cause major social and economic losses, but estimating risk is difficult because extreme...
Altmetrics
Final-revised paper
Preprint