Enhancing severe weather predictions with the I-ConvGRU model: An iterative approach for radar echo time series through ConvGRU and RainNet integration

• Published in: Journal of hydroinformatics Vol. 26; no. 9; pp. 2197 - 2215
• Main Authors: Yang, Rong, Wang, Hao, Zhang, Fugui, Zeng, Qiangyu, Xiong, Taisong, Liu, Zhihao, Jin, Hongfei
• Format: Journal Article
• Language: English
• Published: London IWA Publishing 01.09.2024
• Subjects: Accuracy; Algorithms; Correlation analysis; Deep learning; Echoes; Emergency preparedness; Image enhancement; Information processing; Methods; Mitigation; Neural networks; Nowcasting; Precipitation; Prediction models; Predictions; R&D; Radar; Radar clutter; Radar data; Radar echoes; Radar imaging; Rainfall; Research & development; Severe weather; Spatial data; Time series; Weather forecasting; China
• ISSN: 1464-7141; 1465-1734
• DOI: 10.2166/hydro.2024.068

Precipitation nowcasting plays a crucial role in disaster prevention and mitigation. Existing forecasting models often underutilize output data, leading to suboptimal forecasting performance. To tackle this issue, we introduce the I-ConvGRU model, a novel radar echo timing prediction model that synergizes the temporal dynamics optimization of ConvGRU with the spatial feature enhancement capabilities of RainNet. The model forecasts future scenarios by processing 10 sequential time-series images as input while employing skip connections to boost its spatial feature representation further. Evaluation of the radar echo data set from the Hong Kong Hydrological and Meteorological Bureau spanning from 2009 to 2015 demonstrates the I-ConvGRU model's superiority, with reductions of 17(3.8%) and 49(3.2%) in MSE and MAE metrics, respectively, compared with the TrajGRU model; meanwhile, the I-ConvGRU model had 52(5.8%) and 144(3.8%) lower values on the B-MSE and B-MAE metrics, respectively, than the slightly better performing TrajGRU model. Notably, it significantly improves the prediction of severe precipitation events, with the CSI and HSS metrics increasing by 0.0251(9.6%) and 0.0277(6.8%). These results affirm the model's enhanced effectiveness in radar echo forecasting, particularly in predicting heavy rainfall events.