Distributional Regression U-Nets for the Postprocessing of Precipitation Ensemble Forecasts
This work addresses the need for accurate precipitation forecasts for decision-making in fields like transport and farming, though it is incremental as it builds on existing U-Net and postprocessing methods.
The authors tackled the problem of improving precipitation ensemble forecasts by proposing a U-Net-based distributional regression method for postprocessing, which achieved performance comparable to quantile regression forests in continuous ranked probability score and outperformed them for heavy precipitation events.
Accurate precipitation forecasts have a high socio-economic value due to their role in decision-making in various fields such as transport networks and farming. We propose a global statistical postprocessing method for grid-based precipitation ensemble forecasts. This U-Net-based distributional regression method predicts marginal distributions in the form of parametric distributions inferred by scoring rule minimization. Distributional regression U-Nets are compared to state-of-the-art postprocessing methods for daily 21-h forecasts of 3-h accumulated precipitation over the South of France. Training data comes from the Météo-France weather model AROME-EPS and spans 3 years. A practical challenge appears when consistent data or reforecasts are not available. Distributional regression U-Nets compete favorably with the raw ensemble. In terms of continuous ranked probability score, they reach a performance comparable to quantile regression forests (QRF). However, they are unable to provide calibrated forecasts in areas associated with high climatological precipitation. In terms of predictive power for heavy precipitation events, they outperform both QRF and semi-parametric QRF with tail extensions.