Enhanced Tropical Cyclone Precipitation Prediction in the Northwest Pacific Using Deep Learning Models and Ensemble Techniques
Water · 25.02.2024 · 16 (5) · 671
DOI: 10.3390/w16050671 ↗Kurz gefasst
Fachartikel in der Zeitschrift Water, online erschienen am 25.02.2024. Verfasst von Lunkai He und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Municipal Committee of Science and Technology Innovation.
Abstract (Originalsprache)
This study focuses on optimizing precipitation forecast induced by tropical cyclones (TCs) in the Northwest Pacific region, with lead times ranging from 6 to 72 h. The research employs deep learning models, such as U-Net, UNet3+, SE-Net, and SE-UNet3+, which utilize precipitation forecast data from the Global Forecast System (GFS) and real-time GFS environmental background data using a U-Net structure. To comprehensively make use of the precipitation forecasts from these models, we additionally use probabilistic matching (PM) and simple averaging (AVR) in rainfall prediction. The precipitation data from the Global Precipitation Measurement (GPM) Mission serves as the rainfall observation. The results demonstrate that the root mean squared errors (RMSEs) of U-Net, UNet3+, SE-UNet, SE-UNet3+, AVR, and PM are lowered by 8.7%, 10.1%, 9.7%, 10.0%, 11.4%, and 11.5%, respectively, when compared with the RMSE of the GFS TC precipitation forecasts, while the mean absolute errors are reduced by 9.6%, 11.3%, 9.0%, 12.0%, 12.8%, and 13.0%, respectively. Furthermore, the neural network model improves the precipitation threat scores (TSs). On average, the TSs of U-Net, UNet3+, SE-UNet, SE-UNet3+, AVR, and PM are raised by 12.8%, 21.3%, 19.3%, 20.7%, 22.5%, and 22.9%, respectively, compared with the GFS model. Notably, AVR and PM outperform all other individual models, with PM’s performance slightly better than AVR’s. The most important feature variables in optimizing TC precipitation forecast in the Northwest Pacific region based on the UNet-based neural network include GFS precipitation forecast data, land and sea masks, latitudinal winds at 500 hPa, and vertical winds at 500 hPa.
Förderung
- Shenzhen Municipal Committee of Science and Technology Innovation
Zitieren
APA
He, L., Li, Q., Zhang, J., Deng, X., Wu, Z., Wang, Y., Chan, P., & Li, N. (2024). Enhanced Tropical Cyclone Precipitation Prediction in the Northwest Pacific Using Deep Learning Models and Ensemble Techniques. Water, 16(5), 671. https://doi.org/10.3390/w16050671
Vancouver
He L, Li Q, Zhang J, Deng X, Wu Z, Wang Y, et al. Enhanced Tropical Cyclone Precipitation Prediction in the Northwest Pacific Using Deep Learning Models and Ensemble Techniques. Water. 2024;16(5):671. doi:10.3390/w16050671
BibTeX
@article{He2024,
author = {He, Lunkai and Li, Qinglan and Zhang, Jiali and Deng, Xiaowei and Wu, Zhijian and Wang, Yaoming and Chan, Pak-Wai and Li, Na},
title = {Enhanced Tropical Cyclone Precipitation Prediction in the Northwest Pacific Using Deep Learning Models and Ensemble Techniques},
journal = {Water},
year = {2024},
volume = {16},
number = {5},
pages = {671},
doi = {10.3390/w16050671}
}
EUVIMED