ML subseasonal forecast model published in Nature, open access with downloadable model

LesterMackey · x · 2026-10-15

A contest-winning AI subseasonal (2–6 week ahead) weather forecasting model from Lester Mackey's team is now published open access in Nature, with the model available for download.

• Physics-based and AI forecasts are accurate up to 2 weeks, but skill drops sharply at subseasonal scales due to compounding errors, systematic biases, and atmospheric chaos.
• The paper introduces probabilistic bias correction, an ML framework that learns to correct historical probabilistic forecasts, substantially reducing systematic error.
• The work targets decisions like crop planting, wildfire management, and water/energy allocation.

Related event: Microsoft's PBC machine learning bias-correction method published in Nature boosts 2-6 week forecasts(10 posts)→

Original post →

More from Research

• Initialization matters far more than expected in LLM-driven scientific discovery, new study finds — BenBlaiszik · 2026-10-15
• RLVR is just RL — RLHF is the weird one, argues lateinteraction — lateinteraction · 2026-10-15
• Mathematician models OpenAI's 372-theorem drop as a self-organized criticality collapse — littmath · 2026-10-15
• RoPE long-context failures proven inevitable; training-free RoPE Profiler boosts accuracy up to 25% — zhaofeng_wu · 2026-10-15
• OpenAI's Quasi-Riemann proof sparks chain of results, Bhargava proves primitive root theorem — Singularitarian · 2026-10-15
• Applied Compute's Spork post-training recipe doubles chess puzzle solve-rate vs GRPO — ypatil125 · 2026-10-15

Research channel →