DeepRain: Machine Learning Methods for Precipitation Forecasts
The three-year BMBF-funded joint project DeepRain is coordinated by JSC and aims to apply modern methods of machine learning to improve precipitation forecasts in Germany. Precise predictions of rain and snow with a reliable indication of the expected amount of precipitation are still an extreme challenge for weather modelling. Through the use of radar data, high-resolution topographic data, and ensemble forecast data, researchers at JSC and DWD, in collaboration with the Universities of Osnabrück and Bonn and Jacobs University in Bremen, plan to achieve significant improvements here. The DeepRain project started in October 2018 with a kick-off meeting at JSC.
Contact: Dr. Martin Schultz
from JSC News No. 263, 5 February 2019