Pith. sign in

REVIEW 17 cited by

GraphCast: Learning skillful medium-range global weather forecasting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.12794 v2 pith:R5JKARN5 submitted 2022-12-24 cs.LG physics.ao-ph

Remi Lam , Alvaro Sanchez-Gonzalez , Matthew Willson , Peter Wirnsberger , Meire Fortunato , Ferran Alet , Suman Ravuri , Timo Ewalds
show 10 more authors
Zach Eaton-Rosen Weihua Hu Alexander Merose Stephan Hoyer George Holland Oriol Vinyals Jacklynn Stott Alexander Pritzel Shakir Mohamed Peter Battaglia
This is my paper · ORCID
classification cs.LGphysics.ao-ph
keywords weathergraphcastforecastingaccuratedatadirectlyglobalimprove
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute resources to improve forecast accuracy, but cannot directly use historical weather data to improve the underlying model. We introduce a machine learning-based method called "GraphCast", which can be trained directly from reanalysis data. It predicts hundreds of weather variables, over 10 days at 0.25 degree resolution globally, in under one minute. We show that GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures. GraphCast is a key advance in accurate and efficient weather forecasting, and helps realize the promise of machine learning for modeling complex dynamical systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 170 citations worldwide. Full citation record

  1. FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale

    cs.LG 2025-07 conditional novelty 7.0 of 10

    A purely convolutional, spherical-geometry weather model trained with a combined spatial and spectral CRPS loss delivers GenCast-level skill, IFS-beating accuracy, and stable spectra out to 60 days.

  2. Skillful joint probabilistic weather forecasting from marginals

    cs.LG 2025-06 conditional novelty 7.0 of 10

    FGN, a neural weather model trained only on per-location forecast scores, produces more accurate global ensemble forecasts than GenCast and captures realistic spatial correlations.

  3. HourGlass: A probabilistic data-driven temporal downscaler for global and regional weather forecasting

    physics.ao-ph 2026-07 accept novelty 6.5 of 10

    HourGlass probabilistically reconstructs hourly weather evolution between 6-hourly forecast states using CRPS training on NWP trajectories, preserving skill and small-scale variability better than deterministic downscalers.

  4. A PMP-inspired Evaluation Framework for Assessing Deep-Learning Earth System Models

    physics.ao-ph 2026-04 unverdicted novelty 6.0 of 10

    The paper presents a PMP-based evaluation framework to test deep-learning Earth system models on climatology and modes of variability using observational data.

  5. On the under-reaching phenomenon in message-passing neural PDE solvers: revisiting the CFL condition

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Graph neural network PDE solvers require at least a CFL-like number of message passes for hyperbolic problems and domain-spanning passes for parabolic and elliptic problems.

  6. Generative Lagrangian data assimilation for ocean dynamics under extreme sparsity

    physics.ao-ph 2025-07 conditional novelty 6.0 of 10

    A neural operator-conditioned diffusion model reconstructs ocean surface states with high-wavenumber fidelity from 99% to 99.9% sparse observations, outperforming standard UNET and FNO baselines.

  7. LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A latent diffusion model generates medium-range global weather ensembles at 1.5 degrees that match ECMWF IFS-ENS deterministic skill at lower compute, with weaker probabilistic spread and anecdotal cyclone advantages.

  8. DEF: Diffusion-augmented Ensemble Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A conditional diffusion model that generates perturbed initial states can turn any deterministic neural weather forecast model into an ensemble, with measured error reduction on a single ERA5 case study.

  9. PEAR: Equal Area Weather Forecasting on the Sphere

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A transformer weather model operating natively on the equal-area HEALPix grid beats an equiangular-grid counterpart at longer lead times with 2.6x fewer parameters.

  10. A robust and stable hybrid neural network/finite element method for 2D flows that generalizes to different geometries

    math.NA 2026-01 conditional novelty 5.0 of 10

    Replay training on the DNN-MG's own perturbed trajectories removes the long-time instability of the hybrid Navier-Stokes solver, while Transformers or larger patches improve accuracy on unseen geometries.

  11. Finetuning AI Foundation Models to Develop Subgrid-Scale Parameterizations: A Case Study on Atmospheric Gravity Waves

    physics.ao-ph 2025-09 conditional novelty 5.0 of 10

    Fine-tuning Prithvi WxC to predict gravity wave fluxes beats an Attention U-Net baseline on one month of ERA5 validation, including in upper stratospheric levels absent from the pre-training data.

  12. Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    PhyDL-NWP trains neural surrogates with a fitted PDE regularizer and a latent force term, improving weather downscaling and fine-tuning forecasts over 17 baselines.

  13. Enhancing a high resolution data-driven weather prediction model with surface descriptors

    physics.ao-ph 2026-07 conditional novelty 4.5 of 10

    Surface descriptors cut 2 m temperature and 10 m wind MAE by 1.9% and 3.0% domain-wide (about 12% for urban temperature) in a stretched-grid data-driven weather model, and glacier removal raises temperature without re...

  14. The Virtuous Cycle of Quantum-Classical Machine Learning

    quant-ph 2026-07 accept novelty 4.0 of 10

    Classical ML and quantum computing mutually accelerate each other through error correction, control, simulation data, and quantum-native learning, forming a virtuous cycle toward quantum intelligence.

  15. Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A 7-million-parameter convolutional weather model trains in 12 hours on one GPU and is reported to match or beat much larger AI and numerical weather models in medium-range forecasts.

  16. Structure of System-Specific Hazard Modeling for Physical Infrastructures in a Climate Change Context

    physics.soc-ph 2026-07 conditional novelty 3.0 of 10

    A hazard is defined as any intensity exceeding a system-specific threshold, and the paper uses this to generate wind and temperature hazard maps for different infrastructure types.

  17. Exploratory Analysis of Deep Learning Models for Forecasting Meteorological Parameters in the Agricultural Sector

    cs.LG 2026-07 conditional novelty 3.0 of 10

    On Ioannina ERA5 hourly data, hybrid 1D-CNN–RNN models raise a composite WQS by 1.22–1.63% at 24 h and 0.44–0.45% at 168 h over the best single-layer GRU/LSTM baselines.

Pith tools