ConCast: a CBAM-enhanced SimVP with temporal consistency regularization for precipitation nowcasting

Abstract

Precipitation nowcasting is essential for weather warning and rapid-response decision-making, yet existing deep spatiotemporal models often struggle to emphasize meteorologically salient echo structures and to keep their predictions coherent across future frames. We address these issues with ConCast, an enhanced SimVP for radar-based precipitation nowcasting that couples convolutional block attention module (CBAM) refinement with temporal consistency regularization (TCR). The CBAM stage strengthens channel-wise and spatial feature selection so that the network attends to informative precipitation patterns, whereas an auxiliary cosine consistency term constrains the relationship between successive predictions during training. On the Shanghai-Radar and SEVIR datasets, ConCast improves forecasting quality over representative baselines and produces sharper and temporally steadier echo fields. Ablation studies show that the two components act on different aspects of the problem, with attention sharpening spatial discrimination and the consistency term improving sequence coherence, and that their gains do not overlap. Because ConCast adds only marginal overhead to SimVP, attention refinement combined with TCR is a practical option for nowcasting.

Keywords

Precipitation nowcasting / very short-term precipitation forecasting / SimVP / radar echo data / temporal consistency regularization / attention mechanisms

References

[1] Sun J.,Xue M.,Wilson J. W..et al. Use of NWP for nowcasting convective precipitation: recent progress and challenges Bull. Am. Meteorol. Soc. 2014 95 409 26

[2] Liang Q. Q.,Feng Y. R.,Deng W. J..et al. A composite approach of radar echo extrapolation based on TREC vectors in combination with model-predicted winds Adv. Atmos. Sci. 2010 27 1119 30

[3] Bechini R.,Chandrasekar V.. An enhanced optical flow technique for radar nowcasting of precipitation and winds J. Atmos. Ocean. Technol. 2017 34 2637 58

[4] Chen M. X.,Qin R.,Song L. Y..et al. SMART2022: a project supporting weather forecasting and services for the Beijing 2022 Olympic and Paralympic Winter Games - a success story of precise observations, accurate forecasting, and meticulous service in the field of meteorology Bull. Am. Meteorol. Soc. 2025 106 E1401 33

[5] Bi K.,Xie L.,Zhang H.,Chen X.,Gu X.,Tian Q.. Accurate medium-range global weather forecasting with 3D neural networks Nature 2023 619 533 38

[6] Ravuri S.,Lenc K.,Willson M..et al. Skilful precipitation nowcasting using deep generative models of radar Nature 2021 597 672 7

[7] Zhang Y.,Long M.,Chen K..et al. Skilful nowcasting of extreme precipitation with NowcastNet Nature 2023 619 526 32

[8] Ayzel G.,Scheffer T.,Heistermann M.. RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting Geosci. Model Dev. 2020 13 2631 44

[9] Chen L.,Cao Y.,Ma L.,Zhang J.. A deep learning-based methodology for precipitation nowcasting with radar Earth Space Sci. 2020 7 e2019EA000812