RAP-Net: Region Attention Predictive Network for Precipitation Nowcasting

Natural disasters caused by heavy rainfall often cost huge loss of life and property. To avoid it, the task of precipitation nowcasting is imminent. To solve the problem, increasingly deep learning methods are proposed to forecast future radar echo images and then the predicted maps have converted the distribution of rainfall. The prevailing spatiotemporal sequence prediction methods apply ConvRNN structure which combines the Convolution and Recurrent neural network. Although improvements based on ConvRNN achieve remarkable success, these methods ignore capturing both local and global spatial features simultaneously, which degrades the nowcasting in the region of heavy rainfall. To address this issue, we proposed the Region Attention Block (RAB) and embed it into ConvRNN to enhance the forecast in the area with strong rainfall. Besides, the ConvRNN models are hard to memory longer history representations with limited parameters. Considering it, we propose Recall Attention Mechanism (RAM) to improve the prediction. By preserving longer temporal information, RAM contributes to the forecasting, especially in the middle rainfall intensity. The experiments show that the proposed model Region Attention Predictive Network (RAP-Net) has outperformed the state-of-art method.

[1]  Nicolas Thome,et al.  Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Wang-chun Woo,et al.  Operational Application of Optical Flow Techniques to Radar-Based Rainfall Nowcasting , 2017 .

[3]  Younghae Do,et al.  Improved rainfall nowcasting using Burgers’ equation , 2020 .

[4]  Yunming Ye,et al.  PFST-LSTM: A SpatioTemporal LSTM Model With Pseudoflow Prediction for Precipitation Nowcasting , 2021, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Yunming Ye,et al.  An Energy-Based Generative Adversarial Forecaster for Radar Echo Map Extrapolation , 2022, IEEE Geoscience and Remote Sensing Letters.

[6]  Dit-Yan Yeung,et al.  Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model , 2017, NIPS.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Philip S. Yu,et al.  Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Georg Heigold,et al.  An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale , 2021, ICLR.

[10]  Philip S. Yu,et al.  PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs , 2017, NIPS.

[11]  Mingsheng Long,et al.  MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yunbo Wang,et al.  Eidetic 3D LSTM: A Model for Video Prediction and Beyond , 2019, ICLR.

[13]  Osamu Shouno,et al.  Photo-Realistic Video Prediction on Natural Videos of Largely Changing Frames , 2020, ArXiv.

[14]  Luc Van Gool,et al.  Dynamic Filter Networks , 2016, NIPS.

[15]  Liping Liu,et al.  Application of multi-scale tracking radar echoes scheme in quantitative precipitation nowcasting , 2013, Advances in Atmospheric Sciences.

[16]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[17]  Philip S. Yu,et al.  PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning , 2018, ICML.

[18]  Maomao Li,et al.  Self-Attention ConvLSTM for Spatiotemporal Prediction , 2020, AAAI.