mlsanityData to 14 Oct 2026

FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead

arXiv 2304.02948 ↗First posted 6 Apr 2023cs.AI cs.LG physics.ao-phcited by 175

Not on the map. Why?

Abstract (arXiv)

We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI). Different from existing data-driven weather forecast methods, FengWu solves the medium-range forecast problem from a multi-modal and multi-task perspective. Specifically, a deep learning architecture equipped with model-specific encoder-decoders and cross-modal fusion Transformer is elaborately designed, which is learned under the supervision of an uncertainty loss to balance the optimization of different predictors in a region-adaptive manner. Besides this, a replay buffer mechanism is introduced to improve medium-range forecast performance. With 39-year data training based on the ERA5 reanalysis, FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25deg latitude-longitude resolution. Hindcasts of 6-hourly weather in 2018 based on ERA5 demonstrate that FengWu performs better than GraphCast in predicting 80% of the 880 reported predictands, e.g., reducing the root mean square error (RMSE) of 10-day lead global z500 prediction from 733 to 651 m2/s2. In addition, the inference cost of each iteration is merely 600ms on NVIDIA Tesla A100 hardware. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead (with ACC of z500 > 0.6) for the first time.

Key facts. Cited by 175 papers in the map (data through 14 Oct 2026). Builds on 23 of its 54 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

23 of 54 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  9. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  10. 2015Prioritized Experience Replaycited by 1,099
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  12. 2017A Survey on Multi-Task Learningcited by 840
11 more
  1. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  2. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  4. 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 275
  5. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
  6. 2021Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformerscited by 248
  7. 2023TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddingscited by 202
  8. 2022FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operatorscited by 188
  9. 2022Forecasting Global Weather with Graph Neural Networkscited by 168
  10. 2022Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecastcited by 166
  11. 2022SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbationcited by 32

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 25; 2024: 78; 2025: 45; 2026: 27.

175 papers.

Sort:

By area:

  1. 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 241
  2. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 239
  3. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 236
  4. 2025InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modelingcited by 211
  5. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
  6. 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 110
  7. 2023PreDiff: Precipitation Nowcasting with Latent Diffusion Modelscited by 98
  8. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  9. 2023Deep Learning for Day Forecasts from Sparse Observationscited by 72
  10. 2023ACE: A fast, skillful learned global atmospheric model for climate predictioncited by 56
  11. 2023AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learningcited by 40
  12. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
38 more
  1. 2023Foundation Models for Weather and Climate Data Understanding: A Comprehensive Surveycited by 34
  2. 2025OneForecast: A Universal Framework for Global and Regional Weather Forecastingcited by 34
  3. 2024On the Foundations of Earth and Climate Foundation Modelscited by 33
  4. 2024Prithvi WxC: Foundation Model for Weather and Climatecited by 31
  5. 2024Probabilistic Weather Forecasting with Hierarchical Graph Neural Networkscited by 30
  6. 2024Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignmentcited by 29
  7. 2023Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Meshcited by 28
  8. 2023AI-GOMS: Large AI-Driven Global Ocean Modeling Systemcited by 27
  9. 2024Uncertainty quantification for data-driven weather modelscited by 26
  10. 2023ClimateSet: A Large-Scale Climate Model Dataset for Machine Learningcited by 25
  11. 2024A Practical Probabilistic Benchmark for AI Weather Modelscited by 25
  12. 2025Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedbackcited by 25
  13. 2025Foundation Models for Spatio-Temporal Data Science: A Tutorial and Surveycited by 24
  14. 2023FengWu-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilationcited by 23
  15. 2024Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modelingcited by 23
  16. 2023Graph-based Neural Weather Prediction for Limited Area Modelingcited by 22
  17. 2024WeatherQA: Can Multimodal Language Models Reason about Severe Weather?cited by 22
  18. 2023Towards an end-to-end artificial intelligence driven global weather forecasting systemcited by 21
  19. 2024Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Modelcited by 21
  20. 2024Probabilistic Emulation of a Global Climate Model with Spherical DYffusioncited by 21
  21. 2024FuXi Weather: A data-to-forecast machine learning system for global weathercited by 21
  22. 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilationcited by 20
  23. 2024ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecastcited by 19
  24. 2024Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operatorscited by 18
  25. 2024Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Predictioncited by 15
  26. 2026Demystifying Data-Driven Probabilistic Medium-Range Weather Forecastingcited by 15
  27. 2023WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correctioncited by 14
  28. 2024Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Eventscited by 14
  29. 2025CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformercited by 14
  30. 2023When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence Systemcited by 13
  31. 2024FuXi-ENS: A machine learning model for medium-range ensemble weather forecastingcited by 13
  32. 2023Fourier neural operator for real-time simulation of 3D dynamic urban microclimatecited by 12
  33. 2024DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modelingcited by 12
  34. 2024MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modelingcited by 12
  35. 2024WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learningcited by 12
  36. 2025NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulationcited by 12
  37. 2025OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scalescited by 12
  38. 2024Uncertainty Quantification of Surrogate Models using Conformal Predictioncited by 11

50 most cited of 175 All 175 (JSON)