Deep-learning-based post-processing for probabilistic precipitation forecasting

Deep-learning-based post-processing for probabilistic precipitation forecasting

Ensemble prediction systems (EPSs) serve as a popular technique to provide probabilistic precipitation prediction in short- and medium-range forecasting. However, numerical models still suffer from imperfect configurations associated with data assimilation and physical parameterization, which can le...

Cijeli opis

Bibliografski detalji
Glavni autori: Yan Ji, Xiefei Zhi, Luying Ji, Yingxin Zhang, Cui Hao, Ting Peng
Format: Članak
Jezik:English
Izdano: Frontiers Media S.A. 2022-09-01
Serija:Frontiers in Earth Science
Teme:
deep learning
probabilistic precipitation forecasting
post-processing
loss function
ensemble model output statistics
Online pristup:https://www.frontiersin.org/articles/10.3389/feart.2022.978041/full

Internet

https://www.frontiersin.org/articles/10.3389/feart.2022.978041/full

Slični predmeti