期刊
NATURE COMMUNICATIONS
卷 12, 期 1, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41467-021-23406-3
关键词
-
资金
- NSF [AGS-1652289]
- Brain Pool program - Ministry of Science and ICT through the National Research Foundation of Korea (NRF) [2019H1D3A2A01102234]
- NRF [NRF-2020R1A2C2101025]
- Korea Meteorological Administration Research and Development Program [KMI2020-01010]
- Korea Meteorological Institute (KMI) [KMI2020-01010] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
- National Research Foundation of Korea [4199990514254, 2019H1D3A2A01102234] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
The authors introduced a deep learning bias correction method that significantly improves multi-model forecasts of the MJO amplitude and phase, sustaining up to four weeks.
Producing accurate weather prediction beyond two weeks is an urgent challenge due to its ever-increasing socioeconomic value. The Madden-Julian Oscillation (MJO), a planetary-scale tropical convective system, serves as a primary source of global subseasonal (i.e., targeting three to four weeks) predictability. During the past decades, operational forecasting systems have improved substantially, while the MJO prediction skill has not yet reached its potential predictability, partly due to the systematic errors caused by imperfect numerical models. Here, to improve the MJO prediction skill, we blend the state-of-the-art dynamical forecasts and observations with a Deep Learning bias correction method. With Deep Learning bias correction, multi-model forecast errors in MJO amplitude and phase averaged over four weeks are significantly reduced by about 90% and 77%, respectively. Most models show the greatest improvement for MJO events starting from the Indian Ocean and crossing the Maritime Continent. The Madden-Julian Oscillation (MJO) is a crucial component of the tropical weather system, but forecasting it has been challenging. Here, the authors present a deep learning bias correction method that significantly improves multi-model forecasts of the MJO amplitude and phase for up to four weeks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据