Deep Learning Precipitation Nowcasting for the Netherlands

Abstract

Precipitation nowcasting tries to predict the intensity of rainfall in the near future. Due to the dependency of many industries on accurate predictions of nowcasting methods, the development of such methods has increased in recent years. In this research, we validated a Deep Generative Model of Radar (DGMR) developed by DeepMind on weather data from the Netherlands. The results of the DGMR were compared to a baseline method S-PROG, based on the PySTEPS framework. It was found that the DGMR outperformed the S-PROG method on multiple metrics, scoring significantly higher for Mean Squared Error and Critical Success Index at timestamp $t_0$ + 60. However, the DGMR model often failed to correctly classify predictions at long lead times. Therefore, it was concluded that this model is capable of making predictions for the Netherlands. However, re-training of the model is required to achieve the full capabilities of the model.