期刊
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
卷 13, 期 9, 页码 -出版社
AMER GEOPHYSICAL UNION
DOI: 10.1029/2021MS002521
关键词
neural network; data assimilation; tangent-linear; adjoint
资金
- Royal Society [955513, 101016798]
- European Union [823988]
- Office of Naval Research Global
The study shows that neural networks can be used to quickly obtain the tangent-linear and adjoint versions of physical parametrization schemes, which is important for 4D-Var data assimilation in weather forecasting.
We assess the ability of neural network emulators of physical parametrization schemes in numerical weather prediction models to aid in the construction of linearized models required by four-dimensional variational (4D-Var) data assimilation. Neural networks can be differentiated trivially, and so if a physical parametrization scheme can be accurately emulated by a neural network then its tangent-linear and adjoint versions can be obtained with minimal effort, compared with the standard paradigms of manual or automatic differentiation of the model code. Here we apply this idea by emulating the non-orographic gravity wave drag parametrization scheme in an atmospheric model with a neural network, and deriving its tangent-linear and adjoint models. We demonstrate that these neural network-derived tangent-linear and adjoint models not only pass the standard consistency tests but also can be used successfully to do 4D-Var data assimilation. This technique holds the promise of significantly easing maintenance of tangent-linear and adjoint codes in weather forecasting centers, if accurate neural network emulators can be constructed.
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