Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models
-
Published:2022-12-01
Issue:1
Volume:94
Page:
-
ISSN:0885-7474
-
Container-title:Journal of Scientific Computing
-
language:en
-
Short-container-title:J Sci Comput
Author:
Cheng Sibo, Chen Jianhua, Anastasiou Charitos, Angeli Panagiota, Matar Omar K., Guo Yi-Ke, Pain Christopher C., Arcucci RossellaORCID
Abstract
AbstractReduced-order modelling and low-dimensional surrogate models generated using machine learning algorithms have been widely applied in high-dimensional dynamical systems to improve the algorithmic efficiency. In this paper, we develop a system which combines reduced-order surrogate models with a novel data assimilation (DA) technique used to incorporate real-time observations from different physical spaces. We make use of local smooth surrogate functions which link the space of encoded system variables and the one of current observations to perform variational DA with a low computational cost. The new system, named generalised latent assimilation can benefit both the efficiency provided by the reduced-order modelling and the accuracy of data assimilation. A theoretical analysis of the difference between surrogate and original assimilation cost function is also provided in this paper where an upper bound, depending on the size of the local training set, is given. The new approach is tested on a high-dimensional (CFD) application of a two-phase liquid flow with non-linear observation operators that current Latent Assimilation methods can not handle. Numerical results demonstrate that the proposed assimilation approach can significantly improve the reconstruction and prediction accuracy of the deep learning surrogate model which is nearly 1000 times faster than the CFD simulation.
Funder
Engineering and Physical Sciences Research Council Leverhulme Wildfires Centre
Publisher
Springer Science and Business Media LLC
Subject
Computational Theory and Mathematics,General Engineering,Theoretical Computer Science,Software,Applied Mathematics,Computational Mathematics,Numerical Analysis
Reference67 articles.
1. Nakamura, T., Fukami, K., Hasegawa, K., Nabae, Y., Fukagata, K.: Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow. Phys. Fluids 33(2), 025116 (2021) 2. Mohan, A.T., Gaitonde, D.V.: A deep learning based approach to reduced order modeling for turbulent flow control using LSTM neural networks. arXiv preprint arXiv:1804.09269 (2018) 3. Casas, C.Q., Arcucci, R., Wu, P., Pain, C., Guo, Y.-K.: A reduced order deep data assimilation model. Physica D 412, 132615 (2020) 4. Fu, R., Xiao, D., Navon, I., Wang, C.: A data driven reduced order model of fluid flow by auto-encoder and self-attention deep learning methods. arXiv preprint arXiv:2109.02126 (2021) 5. Carrassi, A., Bocquet, M., Bertino, L., Evensen, G.: Data assimilation in the geosciences: an overview of methods, issues, and perspectives. Wiley Interdiscip. Rev. Clim. Change 9(5), 535 (2018)
Cited by
46 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|