Skilful Precipitation Nowcasting Using NowcastNet
This work addresses the challenge of accurate precipitation nowcasting for public and private institutions to mitigate disasters from extreme weather, though it is incremental as it builds on an existing model.
The paper tackled short-term precipitation forecasting by applying NowcastNet, a physics-conditioned deep generative network, to satellite images across Europe, achieving realistic predictions that outperformed baselines for unseen regions and years.
Designing early warning system for precipitation requires accurate short-term forecasting system. Climate change has led to an increase in frequency of extreme weather events, and hence such systems can prevent disasters and loss of life. Managing such events remain a challenge for both public and private institutions. Precipitation nowcasting can help relevant institutions to better prepare for such events as they impact agriculture, transport, public health and safety, etc. Physics-based numerical weather prediction (NWP) is unable to perform well for nowcasting because of large computational turn-around time. Deep-learning based models on the other hand are able to give predictions within seconds. We use recently proposed NowcastNet, a physics-conditioned deep generative network, to forecast precipitation for different regions of Europe using satellite images. Both spatial and temporal transfer learning is done by forecasting for the unseen regions and year. Model makes realistic predictions and is able to outperform baseline for such a prediction task.