Microsoft has a new machine learning tool to improve weather forecasts

Microsoft researchers have developed a machine learning tool called Probabilistic Bias Correction (PBC) that corrects systematic biases in existing weather models, improving accuracy for forecasts two to six weeks ahead. Published in Nature and released as open-source software, PBC can run on CPUs, making it accessible to resource-strapped weather agencies. In tests, PBC improved a leading physics-based model from the European Centre for Medium-Range Weather Forecasts (ECMWF) for 98% of precipitation and 92% of temperature targets, and doubled the accuracy of ECMWF's AI forecasting system. The work, a collaboration with MIT, ECMWF, and others, is already being tested by the nonprofit Rhiza Research with the Kenya Meteorological Service Authority to improve early warnings ahead of an extreme rainy season.

(Source：The Verge)