Sökning: WFRF:(Eivazi Hamidreza)
> (2021) >
Recurrent neural ne...
Recurrent neural networks and Koopman-based frameworks for temporal predictions in a low-order model of turbulence
-
- Eivazi, Hamidreza (författare)
- Univ Tehran, Fac New Sci & Technol, Tehran, Iran.
-
- Guastoni, Luca (författare)
- KTH,Linné Flow Center, FLOW,SeRC - Swedish e-Science Research Centre
-
- Schlatter, Philipp (författare)
- KTH,Linné Flow Center, FLOW,SeRC - Swedish e-Science Research Centre,Strömningsmekanik och Teknisk Akustik
-
visa fler...
-
- Azizpour, Hossein, 1985- (författare)
- KTH,Science for Life Laboratory, SciLifeLab,Robotik, perception och lärande, RPL
-
- Vinuesa, Ricardo (författare)
- KTH,Linné Flow Center, FLOW,SeRC - Swedish e-Science Research Centre,Strömningsmekanik och Teknisk Akustik
-
visa färre...
-
Univ Tehran, Fac New Sci & Technol, Tehran, Iran Linné Flow Center, FLOW (creator_code:org_t)
- Elsevier BV, 2021
- 2021
- Engelska.
-
Ingår i: International Journal of Heat and Fluid Flow. - : Elsevier BV. - 0142-727X .- 1879-2278. ; 90
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Dynamical systems
- Machine learning
- Data-driven modeling
- Recurrent neural networks
- Koopman operator
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas