Variational Data Assimilation with a Learned Inverse Observation Operator

Variational Data Assimilation with a Learned Inverse Observation Operator
复制标题

使用学习逆观测算子进行变分数据同化

DOI:
--
复制
发表时间:
2021
期刊:
International Conference on Machine Learning
影响因子:
--
通讯作者:
Stephan Hoyer
Stephan Hoyer
中科院分区:
--
文献类型:
--
作者:
Thomas Frerix;Dmitrii Kochkov;Jamie A. Smith;D. Cremers;M. Brenner;Stephan Hoyer

文献摘要

参考文献

被引文献

相似文献

变分数据同化优化动力系统的初始状态,使其演变符合观测数据。物理模型随后可以演化到未来进行预测。这一原则是大规模预报应用的基石,如数值天气预报。因此,它已在全球各地天气预报机构的当前操作系统中实施。地球仪。然而,找到一个好的初始状态提出了一个困难的优化问题,部分原因是物理状态和它们相应的观测之间的不可逆关系。我们学习从观测数据到物理状态的映射,并展示如何使用它来提高可优化性。我们采用这种映射在两个方面:更好地初始化非凸优化问题,并重新制定的目标函数在更好的表现物理空间,而不是观察空间。对Lorenz96模型和二维湍流的实验结果表明,该方法可以显著提高混沌系统的预测质量。
Variational data assimilation optimizes for an initial state of a dynamical system such that its evolution fits observational data. The physical model can subsequently be evolved into the future to make predictions. This principle is a cornerstone of large scale forecasting applications such as numerical weather prediction. As such, it is implemented in current operational systems of weather forecasting agencies across the globe. However, finding a good initial state poses a difficult optimization problem in part due to the non-invertible relationship between physical states and their corresponding observations. We learn a mapping from observational data to physical states and show how it can be used to improve optimizability. We employ this mapping in two ways: to better initialize the non-convex optimization problem, and to reformulate the objective function in better behaved physics space instead of observation space. Our experimental results for the Lorenz96 model and a two-dimensional turbulent fluid flow demonstrate that this procedure significantly improves forecast quality for chaotic systems.
DOI: 10.1515/nanoph-2020-0376
发表时间: 2021-01-01
期刊: NANOPHOTONICS
影响因子: 7.5
作者:
Kudyshev, Zhaxylyk A.;Kildishev, Alexander, V;Boltasseva, Alexandra
通讯作者: Boltasseva, Alexandra
DOI: 10.1103/physrevfluids.6.064605
发表时间: 2020-04
影响因子: 2.7
作者:
J. Zhuang;Dmitrii Kochkov;Yohai Bar-Sinai;M. Brenner;Stephan Hoyer
通讯作者: J. Zhuang;Dmitrii Kochkov;Yohai Bar-Sinai;M. Brenner;Stephan Hoyer
DOI: 10.1080/16000870.2019.1696646
发表时间: 2020
期刊: Dynamic Meteorology and Oceanography
影响因子: --
作者:
Tabeart J
通讯作者: Tabeart J
DOI: 10.1073/pnas.1814058116
发表时间: 2019-07-30
影响因子: 11.1
作者:
Bar-Sinai, Yohai;Hoyer, Stephan;Brenner, Michael P.
通讯作者: Brenner, Michael P.
DOI: 10.1017/jfm.2013.122
发表时间: 2013-05-01
影响因子: 3.7
作者:
Chandler, Gary J.;Kerswell, Rich R.
通讯作者: Kerswell, Rich R.