Two-Stage UA-GAN for Precipitation Nowcasting

• Published in: Remote sensing (Basel, Switzerland) Vol. 14; no. 23; p. 5948
• Main Authors: Xu, Liujia, Niu, Dan, Zhang, Tianbao, Chen, Pengju, Chen, Xunlai, Li, Yinghao
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2022
• Subjects: Accuracy; Algorithms; Artificial intelligence; attention mechanism; Emergency preparedness; GAN; Generative adversarial networks; Indicators; Long short-term memory; Neural networks; Nowcasting; Optical flow (image analysis); Precipitation; precipitation nowcasting; Predictions; Radar; Radar echoes; Rain; Rainfall; Recurrent neural networks; Remote sensing; spatiotemporal prediction; Statistical methods; Variational methods; Weather forecasting; Hong Kong China; China
• DOI: 10.3390/rs14235948
• ISSN: 2072-4292

Short-term rainfall prediction by radar echo map extrapolation has been a very hot area of research in recent years, which is also an area worth studying owing to its importance for precipitation disaster prevention. Existing methods have some shortcomings. In terms of image indicators, the predicted images are not clear enough and lack small-scale details, while in terms of precipitation accuracy indicators, the prediction is not accurate enough. In this paper, we proposed a two-stage model (two-stage UA-GAN) to achieve more accurate prediction echo images with more details. For the first stage, we used the Trajectory Gated Recurrent Unit (TrajGRU) model to carry out a pre-prediction, which proved to have a good ability to capture spatiotemporal movement of rain field. In the second stage, we proposed a spatiotemporal attention enhanced Generative Adversarial Networks (GAN) model with a U-Net structure and a new deep residual attention module in order to carry out the refinement and improvement of the first-stage prediction. Experimental results showed that our model outperforms the optical-flow based method Real-Time Optical Flow by Variational Methods for Echoes of Radar (ROVER), and some well-known Recurrent Neural Network (RNN)-based models (TrajGRU, PredRNN++, ConvGRU, Convolutional Long Short-Term Memory (ConvLSTM)) in terms of both image detail indexes and precipitation accuracy indexes, and is visible to the naked eye to have better accuracy and more details.