Deep Learning approach towards Precipitation Nowcasting: RADOLAN

In this repository you can find the converted images of the RADOLAN Product provided by the German Weather Service (DWD). This data was used as input data to train the models in the paper "Deep Learning Approach Towards Precipitation Nowcasting: Evaluating Regional Extrapolation Capabilities".

Due to file size, the data set is split up into years. All years need to be placed in the same directory, so for example a correct directory structure would be /radarPNG/2017/, /radarPNG/2018/ etc.

The raw RADOLAN data is available at https://opendata.dwd.de/weather/radar/radolan/

More details at https://github.com/Nakroma/Precipitation-Nowcasting