Harvard undergrad's ML subseasonal weather forecasting work, started at Microsoft Research, lands in Nature
LesterMackey · x · 2026-10-22
Hannah Guan, a fourth-year applied math undergraduate at Harvard SEAS, spent a summer internship at Microsoft Research developing machine learning algorithms that correct errors in existing models for subseasonal weather prediction—the critical 2–6 week horizon that matters for farmers planning harvests and city planners allocating grid power, but where current physics-based and AI foundation models remain inaccurate. She continued the work after the internship and became first author on a paper published in Nature.
More from Research
- Research Progress Graph: modeling authentic research trajectories, 35 agents found incomplete — ZhiyuChen4 · 2026-10-22
- EMNLP 2026 paper uses prediction-powered inference to quantify how much human annotation LLM judges save — shi_weiyan · 2026-10-22
- Ask-to-Distill: synthesizing questions for answer-free on-policy distillation — UIUC-CS · 2026-10-22
- RFD4 team swaps self-conditioning for recurrent updates, echoing looped flows — AllThingsApx · 2026-10-22
- MIT ML technique breaks records for 2-6 week weather forecasts by learning to correct model errors — LesterMackey · 2026-10-22
- Chatlet: generative UI that emerges from group chats to power collaborative decisions — HaijunXia · 2026-10-22