Corpus ID: 218516844

Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence

@article{Eivazi2020RecurrentNN,
  title={Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence},
  author={Hamidreza Eivazi and L. Guastoni and P. Schlatter and Hossein Azizpour and R. Vinuesa},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.02762}
}
  • Hamidreza Eivazi, L. Guastoni, +2 authors R. Vinuesa
  • Published 2020
  • Computer Science, Physics
  • ArXiv
  • The prediction capabilities of recurrent neural networks and Koopman-based frameworks are assessed in 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 predictions of the turbulence statistics and the dynamic behavior of the flow 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… CONTINUE READING
    4 Citations

    References

    SHOWING 1-10 OF 80 REFERENCES
    Predictions of turbulent shear flows using deep neural networks.
    • 51
    • PDF
    A Koopman-based framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings
    • 4
    • Highly Influential
    • PDF
    Deep learning for multi-year ENSO forecasts
    • 65
    Synthetic turbulent inflow generator using machine learning
    • 45
    • PDF
    Deep learning in fluid dynamics
    • 230
    • PDF
    A perspective on machine learning in turbulent flows
    • 11
    Study of dynamics in post-transient flows using Koopman mode decomposition
    • 43
    • Highly Influential
    • PDF