Fengqing V1.0 — China's fully self-developed AI weather ensemble forecasting system
China's National Meteorological Center put Fengqing V1.0, an AI ensemble forecasting system, into operational service — trained entirely on a 100,000-accelerator domestic supercomputing cluster.
Why it matters
11-day effective global forecast horizon beating ECMWF's AIFS-CRPS; the first Chinese operational weather AI with fully domestic data, model, and compute, blending Swin Transformer with physical conservation constraints.
What you could build with it
A disaster-management agency or logistics operator could license Fengqing's probability forecasts to pre-position relief supplies or reroute freight ahead of typhoons and heavy-rainfall events, replacing coarse deterministic forecasts with uncertainty-aware guidance.
Does it hold up?
Too early to judge — operational since Oct 17 in China's national meteorological service; no public API or independent verification of the ECMWF comparison outside official reports.
Built with Fengqing V1.0
- iFeng: 中国AI气象预报世界先进,滨城算力硬核支撑ifeng · Details the 100k-card AI4S cluster, >85% parallel scaling efficiency, and how domestic compute underpins the model.
- Sina Finance: 我国首个全自主可控气象AI集合预报系统正式投入业务运行sina · Reports the 11-day horizon, outperformance vs ECMWF AIFS-CRPS, and minutes-scale global inference.
- Report: 100,000 Computing Cards Trained China's New AI Weather Modeldailyinference.news · English-language analysis of the Oct 17 operational review: up-to-11-day effective forecast reach claimed via Wen Wei Po, outperforming ECMWF's latest AI ensemble on several measures - with explicit caveats that the underlying results are unpublished and unconfirmed by any primary source.
Learn more
First spotted on article: source.
More AI models
OpenAI publishes 722 AI-generated math manuscripts from an unreleased modelOpenAI released 722 mathematical manuscripts in 372 result families to GitHub under Apache-2.0, produced by an…models · JEV 0.74Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73StepFun Step-5-Preview — open BF16 weights releasedStepFun published the full BF16 weights for its flagship Step-5-Preview agentic model (600B-parameter sparse MoE, 27B…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.