<p>Precipitation forecasting plays a key role in meteorological disaster prediction, and accurate weather forecasting can help to mitigate the adverse impacts of severe weather events on livelihoods and productivity. Radar precipitation images have complex spatiotemporal coupling characteristics. In order to improve the ability of spatiotemporal feature extraction in radar precipitation images, a spatiotemporal cooperative attention network (STC-UNet) is proposed in this study. In particular, we put forward a spatiotemporal feature extraction residual block (STRB) to extract multi-scale spatiotemporal features from the UNet encoder. The STRB module integrates channel and spatial parallel attention mechanism (CSPA) to enhance spatial feature capture. At the same time, the STRB module integrates the ConvLSTM network to improve the spatiotemporal feature extraction ability of precipitation images. Ultimately, an efficient sub-pixel convolutional neural network refines the decoder of UNet. We validate our approach using precipitation data from the Netherlands and cloud cover datasets from France, achieving future 30, 60, and 120-min precipitation forecasts. The results indicate the superiority of the proposed STC-UNet approach over the comparative models for precipitation nowcasting. The precipitation image predicted by this method is closer to the ground truth and can accurately capture the precipitation rain group, demonstrating good forecasting skills.</p>