HackerPapers

arXiv:2212.12794cs.LG

GraphCast: Learning skillful medium-range global weather forecasting

Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson, Peter Wirnsberger, Meire Fortunato, Ferran Alet, Suman Ravuri, Timo Ewalds, Zach Eaton-Rosen, Weihua Hu, Alexander Merose, Stephan Hoyer, George Holland, Oriol Vinyals, Jacklynn Stott, Alexander Pritzel, Shakir Mohamed, Peter Battaglia

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.

arXiv comments
GraphCast code and trained weights are available at: https://github.com/deepmind/graphcast
Journal reference
DOI
Subjects
cs.LGMachine Learning physics.ao-phAtmospheric and Oceanic Physics

On Hacker News

Linked by 4 identifiable commenters in 4 comments across 4 threads, from Aug 2023 to Aug 2026. Found in 2 HN submissions from Dec 2022 to Jan 2023. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments4 threads

  1. DeepMind's WeatherNext model achieves breakthrough forecasting cyclones 1 comment

    • Everything in AI seems to be focused on LLMs lately. But in my opinion, powerful problem-specific models like this are even more interesting. The SOTA AI models used in weather forecasting are already outperforming the classic NWP models while being orders of magnitude more…

      tcumulusView on HNParent context

  2. NOAA deploys new generation of AI-driven global weather models 1 comment

    • I used GAN to mean graph attention network in my comment, which is how the GraphCast paper defines transformers. https://arxiv.org/pdf/2212.12794 I was looking at this part in particular: > And while Transformers [48] can also compute arbitrarily long-range computations, they do…

      lukeschlatherView on HNParent context

  3. Sequential modeling enables scalable learning for large vision models 1 comment

    • Yes, several. • https://arxiv.org/pdf/2106.14742.pdf • https://rmets.onlinelibrary.wiley.com/doi/full/10.1002/met.2... • https://ieeexplore.ieee.org/document/9671442 Also non-transformer models, because of the scaling complexity on input: https://arxiv.org/pdf/2212.12794.pdf

      ben_wView on HNParent context

  4. Ask HN: If we train an LLM with “data” instead of “language” tokens 1 comment

    • > a weather continuation model could take in all the available weather data up to the present moment and provide a continuation of that And it turns out to work really well: https://arxiv.org/abs/2212.12794 predicts hundreds of weather variables, over 10 days at 0.25 degree…

      T-AView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.