Knowledge Management System Of Institute of process engineering,CAS
| Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models | |
| Cheng, Sibo1; Chen, Jianhua2,3; Anastasiou, Charitos4; Angeli, Panagiota4; Matar, Omar K. K.2; Guo, Yi-Ke1; Pain, Christopher C. C.5; Arcucci, Rossella1,5 | |
| 2023 | |
| Source Publication | JOURNAL OF SCIENTIFIC COMPUTING
 |
| ISSN | 0885-7474 |
| Volume | 94Issue:1Pages:37 |
| Abstract | Reduced-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. |
| Keyword | Deep learning Data assimilation Reduced-order-modelling Explainable AI Recurrent neural networks |
| DOI | 10.1007/s10915-022-02059-4 |
| Language | 英语 |
| WOS Keyword | FORECAST ; NETWORKS |
| Funding Project | Leverhulme Centre for Wildfires, Environment and Society through the Leverhulme Trust[EP/T000414/1] ; CAS scholarship[RC-2018-023] ; RELIANT ; INHALE[EP/V036777/1] ; Wave-Suite[EP/T003189/1] ; MUFFINS[EP/V040235/1] ; [EP/P033180/1] |
| WOS Research Area | Mathematics |
| WOS Subject | Mathematics, Applied |
| Funding Organization | Leverhulme Centre for Wildfires, Environment and Society through the Leverhulme Trust ; CAS scholarship ; RELIANT ; INHALE ; Wave-Suite ; MUFFINS |
| WOS ID | WOS:000912076900002 |
| Publisher | SPRINGER/PLENUM PUBLISHERS |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ipe.ac.cn/handle/122111/56533 |
| Collection | 中国科学院过程工程研究所 |
| Corresponding Author | Arcucci, Rossella |
| Affiliation | 1.Imperial Coll London, Data Sci Inst, Dept Comp, London SW7 2AZ, England 2.Imperial Coll London, Dept Chem Engn, London SW7 2AZ, England 3.Chinese Acad Sci, Inst Proc Engn, State Key Lab Multiphase Complex Syst, Beijing 100190, Peoples R China 4.UCL, Dept Chem Engn, London WC1E 6BT, England 5.Imperial Coll London, Dept Earth Sci & Engn, London SW7 2AZ, England |
| Recommended Citation GB/T 7714 | Cheng, Sibo,Chen, Jianhua,Anastasiou, Charitos,et al. Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models[J]. JOURNAL OF SCIENTIFIC COMPUTING,2023,94(1):37. |
| APA | Cheng, Sibo.,Chen, Jianhua.,Anastasiou, Charitos.,Angeli, Panagiota.,Matar, Omar K. K..,...&Arcucci, Rossella.(2023).Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models.JOURNAL OF SCIENTIFIC COMPUTING,94(1),37. |
| MLA | Cheng, Sibo,et al."Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models".JOURNAL OF SCIENTIFIC COMPUTING 94.1(2023):37. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment