Radar-Based Precipitation Nowcasting Based on Improved U-Net Model
Open Access
- 9 May 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (10) , 1681
Abstract
Rainfall nowcasting is the basis of extreme rainfall monitoring, flood prevention, and water resource scheduling. Based on the structural features of the U-Net model, we proposed the Double Recurrent Residual Attention Gates U-Net (DR2A-UNet) deep-learning model to carry out radar echo extrapolation. The model was trained with mean square error (MSE) and balanced mean square error (BMSE) as loss functions, respectively. The dynamic Z-R relationship was applied for quantitative rainfall estimation. The reference U-Net model, U-Net++, and the ConvLSTM were used as control experiments to carry out radar echo extrapolation. The results showed that the model trained by BMSE had better extrapolation. For 1 h lead time, the rainfall nowcasted by each model could reflect the actual rainfall process. DR2A-UNet performed significantly better than other models for intense rainfall, with a higher extrapolation accuracy for echo intensity and variability processes. At the 2 h lead time, the nowcast accuracy of each model was significantly reduced, but the echo extrapolation and rainfall nowcasting of DR2A-UNet were better.Keywords
Funding Information
- National Key Research and Development Program of China (2023YFC3006501, 52279022, 52079086)
- National Natural Science Foundation of China (2023YFC3006501, 52279022, 52079086)
This publication has 40 references indexed in Scilit:
- Historical and comparative overview of sponge campus construction and future challengesScience of The Total Environment, 2023
- Real-time bias correction of rainfall nowcasts using biward tracking methodJournal of Hydrology, 2023
- Scale‐dependent blending of ensemble rainfall nowcasts and numerical weather prediction in the open‐source pysteps libraryQuarterly Journal of the Royal Meteorological Society, 2023
- A quantitative analysis of research trends in flood hazard assessmentStochastic Environmental Research and Risk Assessment, 2022
- A comparison of correction factors for the systematic gauge-measurement errors to improve the global land precipitation estimateJournal of Hydrology, 2022
- A spatiotemporal deep learning model ST-LSTM-SA for hourly rainfall forecasting using radar echo imagesJournal of Hydrology, 2022
- Broad-UNet: Multi-scale feature learning for nowcasting tasksNeural Networks, 2021
- Application of a Radar Echo Extrapolation‐Based Deep Learning Method in Strong Convection NowcastingEarth and Space Science, 2021
- Relevance of merging radar and rainfall gauge data for rainfall nowcasting in urban hydrologyJournal of Hydrology, 2021
- Short-Term Dynamic Radar Quantitative Precipitation Estimation Based on Wavelet Transform and Support Vector MachineJournal of Meteorological Research, 2020