LodeHQ
AI news for people who shipFree, by email

AI · arxiv.org · Friday, 20 November 2026

GraphCast’s hidden features can improve cyclone forecasts by 51%

Researchers found a way to audit and alter GraphCast’s internal weather dynamics, reducing intensity error by a median 51% across seven storms when they amplified features associated with convection. Sparse autoencoders expose recurring internal patterns, then researchers turn those features up or down during the forecast rollout. The tests also show that a feature tied to the model’s computational mesh can be causally important even without an obvious physical meaning.

Read the source: arxiv.org ↗In the 20 November issue →