Deep Learning for Improving Numerical Weather Prediction of Rainfall Extremes
In one sentence. Deep networks trained on an NWP ensemble with a frequency-weighted loss correct rainfall, improving extreme-event forecast skill by factors of two to above six.
Abstract
The accurate prediction of rainfall, and in particular rainfall extremes, remains challenging for numerical weather prediction models. This can be attributed to subgrid-scale parameterizations of processes that play a crucial role in the multi-scale dynamics, as well as the strongly intermittent nature and the highly skewed, non-Gaussian distribution of rainfall. Here we show that a specific type of deep neural networks can learn rainfall extremes from a numerical weather prediction ensemble. A frequency-based weighting of the loss function is proposed to enable the learning of extreme values in the distributions' tails. We apply our framework in a post-processing step to correct for errors in the model-predicted rainfall. Our method yields a much more accurate representation of relative rainfall frequencies and improves the forecast skill of extremes by factors ranging from two to above six, depending on the event magnitude.
Labels
- Topic
- Post-processing & calibration, Extremes & hazards
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1002/essoar.10507827.1 OpenAlex:W3196443665
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.