ECMWF

Headlines · 3

1. 2d
   China's Fengqing AI ensemble weather forecast system goes operational with 11-day lead

   Fengqing, an AI global short- and medium-range ensemble weather forecasting system (V1.0), has passed an operational review and entered nationwide weather service in China, according to IT之家 and 36Kr. The system was led by the National Meteorological Center with universities and research institutes, and its full training pipeline ran on a 100,000-card AI4S cluster at the National Supercomputing Center in Tianjin; the developers call it China's first operational weather AI ensemble model with fully self-controlled data, models and compute. It combines a vision Transformer architecture with meteorological physical constraints and reaches an effective global forecast lead time of 11 days, with the developers claiming better core metrics, probabilistic accuracy and spread-error control than the European Centre for Medium-Range Weather Forecasts' (ECMWF) latest AI ensemble system. It will support disaster prevention, transport, energy scheduling and ecological protection.

   IT之家 AI · 🔥 0
2. 5d
   Microsoft open-sources PBC, an ML tool to sharpen 2–6 week forecasts

   Microsoft researchers published a method called Probabilistic Bias Correction (PBC) in the journal Nature, using machine learning to spot and correct systematic bias in existing weather models rather than building a new standalone model; the tool is now open-source. The study says PBC improved a leading physics-based model from the European Centre for Medium-Range Weather Forecasts (ECMWF) for 98 percent of precipitation and 92 percent of temperature targets, and doubled the accuracy of ECMWF's AI forecasting system in the paper's analysis. The researchers say PBC is lightweight and can run on CPUs, aiming to make AI-enhanced forecasting more accessible to resource-strapped agencies.

   The Verge AI · 🔥 0
3. 7d
   WindBorne wins US Air Force contract worth up to $49M for balloon data

   WindBorne Systems has secured a US Air Force contract worth up to roughly $49 million under which the military buys atmospheric readings from its global fleet of autonomous weather balloons on demand. The award was made without competitive bidding; the Air Force has so far placed orders worth about $1.7 million and can request data for specific regions and time windows. WindBorne operates about 700 balloons whose measurements are sold to customers and also feed its WeatherMesh 6 deep-learning forecasting model, which the company says outperforms the European Centre for Medium-Range Weather Forecasts' physics-based model — a claim not independently verified here.

   TechCrunch AI · 🔥 4

Experience and discussion from the community

Share my ECMWF experienceAsk about ECMWF