Precipitaion Nowcasting using Deep Neural Network
This work addresses the need for fast and accurate short-term precipitation forecasts for users like event organizers and airport managers, but it appears incremental as it builds on existing deep learning methods without claiming major breakthroughs.
The authors tackled precipitation nowcasting by proposing a deep learning approach using U-net, ConvLSTM, and SVG-LP models trained on 2D precipitation maps, with an algorithm for patch extraction and a loss function to address blurry images and zero-value pixel issues, but no concrete results or numbers are provided.
Precipitation nowcasting is of great importance for weather forecast users, for activities ranging from outdoor activities and sports competitions to airport traffic management. In contrast to long-term precipitation forecasts which are traditionally obtained from numerical models, precipitation nowcasting needs to be very fast. It is therefore more challenging to obtain because of this time constraint. Recently, many machine learning based methods had been proposed. We propose the use three popular deep learning models (U-net, ConvLSTM and SVG-LP) trained on two-dimensional precipitation maps for precipitation nowcasting. We proposed an algorithm for patch extraction to obtain high resolution precipitation maps. We proposed a loss function to solve the blurry image issue and to reduce the influence of zero value pixels in precipitation maps.