mlsanityData to 7 Oct 2026

Distributional Regression U-Nets for the Postprocessing of Precipitation Ensemble Forecasts

arXiv 2407.02125 ↗First posted 2 Jul 2024stat.ML cs.LG stat.APcited by 2

Not on the map. Why?

Abstract (arXiv)

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 M'et'eo-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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 76 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

21 of 76 references.

References · 21

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  4. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  5. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 748
  6. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 261
  7. 2015ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and Rcited by 171
  8. 2023FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Leadcited by 170
  9. 2022Forecasting Global Weather with Graph Neural Networkscited by 165
  10. 2018Neural networks for post-processing ensemble weather forecastscited by 95
  11. 2020Deep Learning for Post-Processing Ensemble Weather Forecastscited by 52
  12. 2021Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparisoncited by 34
9 more
  1. 2013Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Couplingcited by 21
  2. 2015Forecaster's Dilemma: Extreme Events and Forecast Evaluationcited by 20
  3. 2018Distributional Regression Forests for Probabilistic Precipitation Forecasting in Complex Terraincited by 19
  4. 2022Neural Networks for Extreme Quantile Regression with an Application to Forecasting of Flood Riskcited by 19
  5. 2023Deep graphical regression for jointly moderate and extreme Australian wildfirescited by 8
  6. 2015Censored and shifted gamma distribution based EMOS model for probabilistic quantitative precipitation forecastingcited by 5
  7. 2017Forest-based methods and ensemble model output statistics for rainfall ensemble forecastingcited by 5
  8. 2022Aggregating distribution forecasts from deep ensemblescited by 5
  9. 2022Convolutional autoencoders for spatially-informed ensemble post-processingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecastscited by 3
  2. 2026Forecasting threshold exceedance of atmospheric variables at a specific locationcited by 0