MIT's Nature paper breaks records for 2-6 week weather forecasts with ML error correction
LesterMackey · x · 2026-10-15
MIT News covers a new Nature paper by Lester Mackey and colleagues: a lightweight ML method that learns to correct predictable errors in physics-based and AI weather forecasts over the 2-6 week lead time — a window critical for emergency planning (e.g. events like the 2021 Texas grid failure) — setting new records for subseasonal forecasting. The article traces the team's multi-year progress on this hard problem.
Related event: MIT machine learning doubles accuracy of 2-6 week forecasts(2 posts)→
More from Research
- 1-gram wireless mesoscope images cortex-wide activity in freely moving mice — KordingLab · 2026-10-23
- Reversible computing veteran poses open problem: universal BARCS primitives from unbiased Josephson junctions — MikePFrank · 2026-10-23
- Arc Institute uses genomic language model to map 376M prokaryotic noncoding sequences into 5.14M clusters — tedgreenwald · 2026-10-23
- The rise of AI-assisted peer review: reviewers are making it into the appendix — abursuc · 2026-10-23
- Anthropic uses Claude to formally verify security properties in 100+ open-source libraries at RISC-V assembly level — AnthropicAI · 2026-10-23
- Researchers test 9 strategies to pick LLM teams, beating random selection by up to 36.1% — shangbinfeng · 2026-10-23