Using Deep Learning to Identify Circulation Patterns of Intense Rainfall in the Beijing–Tianjing–Hebei Region

• Published in: Atmosphere Vol. 14; no. 6; p. 930
• Main Authors: Jing, Linguo, Zhong, Qi, Li, Xiaojie, Wang, Xiuming, Shen, Lili, Cao, Yong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2023
• Subjects: Accuracy; Agricultural production; Atmospheric circulation; Beijing–Tianjing–Hebei Region; circulation pattern; Circulation patterns; Classification; Deep learning; Environmental aspects; Floods; Forecasting; High pressure; intense rainfall; Machine learning; Methods; objective classification; Precipitation; Precipitation (Meteorology); Rain; Rainfall; Rainfall forecasting; Vortices; Weather forecasting; Weather patterns; China; Beijing China
• ISSN: 2073-4433; 2073-4433
• DOI: 10.3390/atmos14060930

The properties and distributions of precipitation are often determined by specific synoptic patterns. Hence, the objective identification of corresponding impact patterns is an important field of research for improving rain forecasting. However, the identification of the weather patterns producing intense rainfall is much more challenging. Since they are violent and local, impact patterns tend to be meso- or smaller-scale systems and are often incompletely presented or only presented in limited regions. In this paper, a deep learning network with a feature cross-fusion module, FConvNeXt, was proposed to address this difficulty and showed great potential. Four major patterns corresponding to intense rainfall in the Beijing–Tianjing–Hebei Region were studied. Statistical testing showed that FConvNeXt performed better than ConvNeXt and ResNet and that the model could identify the weak synoptic forcing type, the subtropical high-pressure type, and the low-vortex pattern with high accuracy. Furthermore, a strictly independent 2021 dataset was tested, and FConvNeXt maintained an equal if not even slightly better performance in spite of a decrease in the subtropical high-pressure type. Meanwhile, the study showed that the accuracy in identifying the upper-level trough type is the lowest for the three deep learning methods, which may be because the northeast vortex was intercepted in the limited region, making it difficult to distinguish from the shallow upper-level trough type. This study is useful for improving the fine objective of forecasting intense rainfall.