Intelligent Reconstruction of Radar Composite Reflectivity Based on Satellite Observations and Deep Learning

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 2; p. 275
• Main Authors: Zhao, Jianyu, Tan, Jinkai, Chen, Sheng, Huang, Qiqiao, Gao, Liang, Li, Yanping, Wei, Chunxia
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2024
• Subjects: Accuracy; Artificial satellites; composite reflectivity; Data processing; Decision making; Deep learning; Emergency warning programs; False alarms; geostationary satellites; Meteorological radar; Meteorological satellites; Meteorological stations, Radar; Observational learning; Precipitation; Radar; Radar echoes; Rain; Reconstruction; Reflectance; Remote sensing; Root-mean-square errors; Satellite observation; Semantics; Severe weather; Synchronous satellites; Wavelet transforms; Weather; Weather forecasting; China
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16020275

Weather radar is a useful tool for monitoring and forecasting severe weather but has limited coverage due to beam blockage from mountainous terrain or other factors. To overcome this issue, an intelligent technology called “Echo Reconstruction UNet (ER-UNet)” is proposed in this study. It reconstructs radar composite reflectivity (CREF) using observations from Fengyun-4A geostationary satellites with broad coverage. In general, ER-UNet outperforms UNet in terms of root mean square error (RMSE), mean absolute error (MAE), structural similarity index (SSIM), probability of detection (POD), false alarm rate (FAR), critical success index (CSI), and Heidke skill score (HSS). Additionally, ER-UNet provides the better reconstruction of CREF compared to the UNet model in terms of the intensity, location, and details of radar echoes (particularly, strong echoes). ER-UNet can effectively reconstruct strong echoes and provide crucial decision-making information for early warning of severe weather.