当前位置: X-MOL 学术Q. J. R. Meteorol. Soc. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Using machine learning to correct model error in data assimilation and forecast applications
Quarterly Journal of the Royal Meteorological Society ( IF 8.9 ) Pub Date : 2021-07-02 , DOI: 10.1002/qj.4116
Alban Farchi 1 , Patrick Laloyaux 2 , Massimo Bonavita 2 , Marc Bocquet 1
Affiliation  

The idea of using machine learning (ML) methods to reconstruct the dynamics of a system is the topic of recent studies in the geosciences, in which the key output is a surrogate model meant to emulate the dynamical model. In order to treat sparse and noisy observations in a rigorous way, ML can be combined with data assimilation (DA). This yields a class of iterative methods in which, at each iteration, a DA step assimilates the observations and alternates with a ML step to learn the underlying dynamics of the DA analysis. In this article, we propose to use this method to correct the error of an existing, knowledge-based model. In practice, the resulting surrogate model is a hybrid model between the original (knowledge-based) model and the ML model. We demonstrate the feasibility of the method numerically using a two-layer, two-dimensional, quasi-geostrophic channel model. Model error is introduced by the means of perturbed parameters. The DA step is performed using the strong-constraint 4D-Var algorithm, while the ML step is performed using deep learning tools. The ML models are able to learn a substantial part of the model error and the resulting hybrid surrogate models produce better short- to mid-range forecasts. Furthermore, using the hybrid surrogate models for DA yields a significantly better analysis than using the original model.

中文翻译:

使用机器学习纠正数据同化和预测应用中的模型错误

使用机器学习 (ML) 方法重建系统动力学的想法是地球科学最近研究的主题,其中关键输出是用于模拟动力学模型的替代模型。为了以严格的方式处理稀疏和嘈杂的观察,ML 可以与数据同化 (DA) 相结合。这产生了一类迭代方法,其中在每次迭代中,DA 步骤同化观察结果并与 ML 步骤交替,以了解 DA 分析的潜在动态。在本文中,我们建议使用这种方法来纠正现有的、基于知识的模型的错误。在实践中,生成的代理模型是原始(基于知识的)模型和 ML 模型之间的混合模型。我们使用两层、二维、准地转通道模型。模型误差是通过扰动参数引入的。DA 步骤使用强约束 4D-Var 算法执行,而 ML 步骤使用深度学习工具执行。ML 模型能够学习模型误差的很大一部分,由此产生的混合替代模型可以产生更好的中短期预测。此外,对 DA 使用混合代理模型会产生比使用原始模型更好的分析。ML 模型能够学习模型误差的很大一部分,由此产生的混合替代模型可以产生更好的中短期预测。此外,对 DA 使用混合代理模型会产生比使用原始模型更好的分析。ML 模型能够学习模型误差的很大一部分,由此产生的混合替代模型可以产生更好的中短期预测。此外,对 DA 使用混合代理模型会产生比使用原始模型更好的分析。
更新日期:2021-09-06
down
wechat
bug