GraphCast: Learning skillful medium-range global weather forecasting · HackerPapers discussions

GraphCast: Learning skillful medium-range global weather forecasting — mentioned by tcumulus

Sat, 08 Aug 2026 13:56:43 GMT

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 efficient (inference). Most are based on multi scale (hierarchical) Graph Neural Networks, an architecture which is not often talked about. The original Graphcast paper is worth a read if you think this is interesting: https://arxiv.org/abs/2212.12794

Paper and discussion history. A mention is not an endorsement.

GraphCast: Learning skillful medium-range global weather forecasting — mentioned by lukeschlather

Fri, 19 Dec 2025 23:27:03 GMT

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 not scale well with very large inputs (e.g., the 1 million-plus grid points in GraphCast’s global inputs) because of the quadratic memory complexity induced by computing all-to-all interactions. Contemporary extensions of Transformers often sparsify possible interactions to reduce the complexity, which in effect makes…

Paper and discussion history. A mention is not an endorsement.

GraphCast: Learning skillful medium-range global weather forecasting — mentioned by ben_w

Tue, 05 Dec 2023 15:41:27 GMT

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

Paper and discussion history. A mention is not an endorsement.

GraphCast: Learning skillful medium-range global weather forecasting — mentioned by T-A

Wed, 16 Aug 2023 18:08:21 GMT

> 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 resolution globally, in under one minute

Paper and discussion history. A mention is not an endorsement.

GraphCast: Learning skillful medium-range global weather forecasting — HN submission

Mon, 23 Jan 2023 09:55:48 GMT

GraphCast: Learning skillful medium-range global weather forecasting

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

GraphCast: Learning skillful medium-range global weather forecasting — HN submission

Thu, 29 Dec 2022 03:31:06 GMT

End-to-end deep learning methods beat production weather forecast accuracy

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.