AI & ML Efficiency Breakthrough

Achieves high-fidelity sub-seasonal weather forecasting with a 276M parameter model that matches 1.6B parameter baselines in accuracy and speed.

March 26, 2026

Original Paper

Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching

Arsen Kuzhamuratov, Mikhail Zhirnov, Andrey Kuznetsov, Ivan Oseledets, Konstantin Sobolev

arXiv · 2603.24428

The Takeaway

By using latent flow matching and optimized positional embeddings, Marchuk overcomes the chaotic divergence typical of long-range weather predictions. It provides a highly efficient, open-source alternative for 30-day global forecasting that runs on standard hardware.

From the abstract

Accurate subseasonal weather forecasting remains a major challenge due to the inherently chaotic nature of the atmosphere, which limits the predictive skill of conventional models beyond the mid-range horizon (approximately 15 days). In this work, we present \textit{Marchuk}, a generative latent flow-matching model for global weather forecasting spanning mid-range to subseasonal timescales, with prediction horizons of up to 30 days. Marchuk conditions on current-day weather maps and autoregressi