A spatiotemporal deep learning model ST-LSTM-SA for hourly rainfall forecasting using radar echo images.

• Precipitation up to 3-hour is predicted based on radar echo images of Wuhan station. • ST-LSTM-SA is proposed by 3D convolution, spatiotemporal LSTM and self-attention. • ST-LSTM-SA has a better response to medium and heavy rain events. • ST-LSTM-SA outperforms ConvLSTM and machine learning methods at 1–3 h leads. Accurate and timely short-term forecasting services of precipitation variable are significant for people's lives and property security. The data-driven approaches demonstrate promising performance in the extrapolation of precipitation. In this paper, we proposed a spatiotemporal prediction model, namely the Spatial Temporal Long Short-Term Memory based on the self-attentive mechanism (ST-LSTM-SA). This model enables better aggregation of sequence features inspired by proposed improvements. The encapsulated 3D convolution is developed to fully exploit the short-term spatiotemporal information, and the channel correlation is modeled by self-attention mechanism to further improve representations in the long-term interaction, the effectiveness of which is validated in the ablation study. Comprehensive experiments have been conducted on the radar echo sequence, we successfully predicted future radar reflectivity images for next 3 h with data for previous three hours as inputs in Wuhan, China. Three machine learning methods: multiple linear regression (MLR), support vector regression (SVR) and artificial neural networks (ANN) and deep learning model—ConvLSTM have been chosen as comparative groups to corroborate the nowcasting availability of this model for radar echo extrapolation. Moreover, the supplementary experiment on minute dataset also illustrated the superiority of ST-LSTM-SA. The studies analyzed the forecasting performance in terms of image quality and rainfall error. The experimental results demonstrated the better versatility and performance of ST-LSTM-SA. These conclusions and attempts may provide efficient guidance for precipitation nowcasting in urban areas. [ABSTRACT FROM AUTHOR]