Journal
INTERNATIONAL JOURNAL OF HEAT AND FLUID FLOW
Volume 90, Issue -, Pages -Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ijheatfluidflow.2021.108816
Keywords
Dynamical systems; Machine learning; Data-driven modeling; Recurrent neural networks; Koopman operator
Categories
Funding
- Swedish e-Science Research Centre (SeRC)
- Goran Gustafsson Foundation
- Knut and Alice Wallenberg (KAW) Foundation
- Swedish National Infrastructure for Computing (SNIC) at PDC
Ask authors/readers for more resources
The study evaluated the capabilities of recurrent neural networks and Koopman-based frameworks in predicting the temporal dynamics of the low-order model of near-wall turbulence. The results showed that properly trained LSTM networks could achieve excellent reproductions of long-term statistics and dynamic behavior of the chaotic system, while the KNF framework offered the same level of accuracy in statistics at a lower computational cost.
The capabilities of recurrent neural networks and Koopman-based frameworks are assessed in the prediction of temporal dynamics of the low-order model of near-wall turbulence by Moehlis et al. (New J. Phys. 6, 56, 2004). Our results show that it is possible to obtain excellent reproductions of the long-term statistics and the dynamic behavior of the chaotic system with properly trained long-short-term memory (LSTM) networks, leading to relative errors in the mean and the fluctuations below 1%. Besides, a newly developed Koopman-based framework, called Koopman with nonlinear forcing (KNF), leads to the same level of accuracy in the statistics at a significantly lower computational expense. Furthermore, the KNF framework outperforms the LSTM network when it comes to short-term predictions. We also observe that using a loss function based only on the instantaneous predictions of the chaotic system can lead to suboptimal reproductions in terms of long-term statistics. Thus, we propose a model-selection criterion based on the computed statistics which allows to achieve excellent statistical reconstruction even on small datasets, with minimal loss of accuracy in the instantaneous predictions.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available