mlsanityData to 14 Oct 2026

Skillful joint probabilistic weather forecasting from marginals

arXiv 2506.10772 ↗First posted 12 Jun 2025cs.LG physics.ao-phcited by 63

Not on the map. Why?

Abstract (arXiv)

Machine learning (ML)-based weather models have rapidly risen to prominence due to their greater accuracy and speed than traditional forecasts based on numerical weather prediction (NWP), recently outperforming traditional ensembles in global probabilistic weather forecasting. This paper presents FGN, a simple, scalable and flexible modeling approach which significantly outperforms the current state-of-the-art models. FGN generates ensembles via learned model-perturbations with an ensemble of appropriately constrained models. It is trained directly to minimize the continuous rank probability score (CRPS) of per-location forecasts. It produces state-of-the-art ensemble forecasts as measured by a range of deterministic and probabilistic metrics, makes skillful ensemble tropical cyclone track predictions, and captures joint spatial structure despite being trained only on marginals.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Jun 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 47.

63 papers.

Sort:

By area:

  1. 2026Demystifying Data-Driven Probabilistic Medium-Range Weather Forecastingcited by 15
  2. 2025Swift: An Autoregressive Consistency Model for Efficient Weather Forecastingcited by 13
  3. 2025Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical featurescited by 12
  4. 2026U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecastercited by 12
  5. 2025EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rulescited by 10
  6. 2025High-Resolution Probabilistic Data-Driven Weather Modeling with a Stretched-Gridcited by 9
  7. 2026Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecastingcited by 8
  8. 2026Probabilistic Retrofitting of Learned Simulatorscited by 7
  9. 2025Probing forced responses and causality in data-driven climate emulators: conceptual limitations and the role of reduced-order modelscited by 6
  10. 2026Learning Probabilistic Filters with Strictly Proper Scoring Rulescited by 6
  11. 2026(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Modelscited by 5
  12. 2025Warm Starts Accelerate Conditional Diffusioncited by 3
38 more
  1. 2025Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscalingcited by 3
  2. 2025AI-boosted rare event sampling to characterize extreme weathercited by 3
  3. 2025Controllable Probabilistic Forecasting with Stochastic Decomposition Layerscited by 3
  4. 2026EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecastingcited by 3
  5. 2026Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attentioncited by 3
  6. 2026Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weathercited by 3
  7. 2026Tyche: One Step Flow for Efficient Probabilistic Weather Forecastingcited by 3
  8. 2025Point-wise Diffusion Models for Physical Systems with Shape Variations: Application to Spatio-temporal and Large-scale systemcited by 2
  9. 2025MoWE : A Mixture of Weather Expertscited by 2
  10. 2025Improved probabilistic regression using diffusion modelscited by 2
  11. 2025Uncertainty Quantification for Regression: A Unified Framework based on kernel scorescited by 2
  12. 2025Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Modelscited by 2
  13. 2026On Neural Scaling Laws for Weather Emulation through Continual Trainingcited by 2
  14. 2026The physics of AI weather modelscited by 2
  15. 2026Probabilistic Precipitation Nowcasting with Rectified Flow Transformerscited by 2
  16. 2026Bridging short- and medium-range weather forecasting with machine learningcited by 2
  17. 2026WeatherNext 3: Increasing resolution and performance of global weather models with raw observationscited by 2
  18. 2025Learning more physically realistic dynamics in machine-learning based weather forecasting with latent-space constraintscited by 1
  19. 2025On the Predictive Skill of Artificial Intelligence-based Weather Models for Extreme Events using Uncertainty Quantificationcited by 1
  20. 2026Probabilistic Transformers for Joint Modeling of Global Weather Dynamics and Decision-Centric Variablescited by 1
  21. 2026Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecastingcited by 1
  22. 2026Towards a Foundation Model for the Martian Atmospherecited by 1
  23. 2026Evaluating Skill and Stability of ArchesWeather and ArchesWeatherGen under Multi-Decadal Climate Simulationscited by 1
  24. 2026Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecastingcited by 1
  25. 2026STIPP: Space-time in situ postprocessing over the French Alps using proper scoring rulescited by 0
  26. 2026Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulationscited by 0
  27. 2026FlowDA: Accurate, Low-Latency Weather Data Assimilation via Flow Matchingcited by 0
  28. 2026Partial recovery of meter-scale surface weathercited by 0
  29. 2026Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecastingcited by 0
  30. 2026Emulating the Forced Response of Climate Models with Generative Machine Learningcited by 0
  31. 2026The Perception-Physics Paradox: Probing Scientific Alignment with TC-Benchcited by 0
  32. 2026Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictionscited by 0
  33. 2026Reliability of Probabilistic Emulation of Physical Systemscited by 0
  34. 2026Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulationscited by 0
  35. 2026Timestep-Conditioned Transformers for Global Weather Forecastingcited by 0
  36. 2026Diffusion Distillation for Efficient Weather Ensemblescited by 0
  37. 2026From the Loss Landscape to Diverse Feature Learning in Neural Networkscited by 0
  38. 2026TC-Next: Zero-Shot Multimodal Cyclone Forecastingcited by 0

50 most cited of 63 All 63 (JSON)