- Access by Xinjiang University
Solver-in-the-loop approach to closure of shell models of turbulence
Phys. Rev. Fluids 10, 044602 – Published 10 April, 2025
DOI: https://doi.org/10.1103/PhysRevFluids.10.044602
Abstract
This work studies an a posteriori data-driven approach (known as solver-in-the-loop) for subgrid modeling of a shell model for turbulence. This approach takes advantage of the differentiable physics paradigm of deep learning, allowing a neural network model to interact with the differential equation solver over time during the training process. The closure model is, then, naturally exposed to equations-informed input distributions by accounting for prior corrections over the temporal evolution in training. Such a characteristic makes this approach depart from the conventional a priori instantaneous training paradigm and often leads to a more accurate and stable closure model. Our study demonstrates that the closure learned via this a posteriori approach is able to reproduce high-order statistical moments of interest also in closures of high Reynolds number turbulence. Moreover, we investigate the performance of the learned model by experimenting with the effect of unrolling in time, which has remained for the most part unexplored in the literature. Finally, we discuss potential extensions of this approach to Navier-Stokes equations.
Physics Subject Headings (PhySH)
Article Text
References (43)
- U. Frisch, Turbulence: The legacy of A. N. Kolmogorov (Cambridge University Press, Cambridge, UK, 1995).
- A. Alexakis and L. Biferale, Cascades and transitions in turbulent flows, Phys. Rep. 767, 1 (2018).
- C. Meneveau and J. Katz, Scale-invariance and turbulence models for large-eddy simulation, Annu. Rev. Fluid Mech. 32, 1 (2000).
- P. C. M. Lesieur and O. Metáis, Large-Eddy Simulations of Turbulence (Cambridge Unversity Press, Cambridge, UK, 2005).
- S. B. Pope, Turbulent Flows (IOP Publishing, Bristol, UK, 2001).
- P. Sagaut, Large Eddy Simulation for Incompressible Flows: An Introduction (Springer, Berlin, 2006).
- A. A. Mailybaev, Hidden scale invariance of intermittent turbulence in a shell model, Phys. Rev. Fluids 6, L012601 (2021).
- A. A. Mailybaev and S. Thalabard, Hidden scale invariance in Navier–Stokes intermittency, Philos. Trans. R. Soc. A 380, 20210098 (2022).
- R. Maulik, O. San, A. Rasheed, and P. Vedula, Sub-grid modelling for two-dimensional turbulence using neural networks, J. Fluid Mech. 858, 122 (2019).
- R. Maulik, O. San, J. D. Jacob, and C. Crick, Sub-grid scale model classification and blending through deep learning, J. Fluid Mech., 870, 784 (2019).
- A. Beck, D. Flad, and C.-D. Munz, Deep neural networks for data-driven LES closure models, J. Comput. Phys. 398, 108910 (2019).
- H. Frezat, G. Balarac, J. L. Sommer, R. Fablet, and R. Lguensat, Physical invariance in neural networks for subgrid-scale scalar flux modeling, Phys. Rev. Fluids 6, 024607 (2021).
- G. Novati, H. L. de Laroussilhe, and P. Koumoutsakos, Automating turbulence modelling by multi-agent reinforcement learning, Nat. Mach. Intell. 3, 87 (2021).
- M. Kurz, P. Offenhauser, and A. Beck, Deep reinforcement learning for turbulence modeling in large eddy simulations, Int. J. Heat Fluid Flow 99, 109094 (2023).
- L. Biferale, Shell models of energy cascade in turbulence, Annu. Rev. Fluid Mech. 35, 441 (2003).
- V. S. L'vov, E. Podivilov, A. Pomyalov, I. Procaccia, and D. Vandembroucq, Improved shell model of turbulence, Phys. Rev. E 58, 1811 (1998).
- Y. Hattori, R. Rubinstein, and A. Ishizawa, Shell model for rotating turbulence, Phys. Rev. E 70, 046311 (2004).
- Jiang Mingshun and Liu Shida, Scaling behavior of velocity and temperature in a shell model for thermal convective turbulence, Phys. Rev. E 56, 441 (1997).
- D. H. Wacks and C. F. Barenghi, Shell model of superfluid turbulence, Phys. Rev. B 84, 184505 (2011).
- F. Plunian, R. Stepanov, and P. Frick, Shell models of magnetohydrodynamic turbulence, Phys. Rep. 523, 1 (2013).
- R. Benzi, L. Biferale, R. M. Kerr, and E. Trovatore, Helical shell models for three-dimensional turbulence, Phys. Rev. E 53, 3541 (1996).
- M. H. Jensen, G. Paladin, and A. Vulpiani, Shell model for turbulent advection of passive-scalar fields, Phys. Rev. A 45, 7214 (1992).
- A. A. Mailybaev, Spontaneously stochastic solutions in one-dimensional inviscid systems, Nonlinearity 29, 2238 (2016).
- D. Bandak, A. A. Mailybaev, G. L. Eyink, and N. Goldenfeld, Spontaneous stochasticity amplifies even thermal noise to the largest scales of turbulence in a few eddy turnover times, Phys. Rev. Lett. 132, 104002 (2024).
- P. Constantin, B. Levant, and E. S. Titi, Regularity of inviscid shell models of turbulence, Phys. Rev. E 75, 016304 (2007).
- I. Daumont, T. Dombre, and J.-L. Gilson, Instanton calculus in shell models of turbulence, Phys. Rev. E 62, 3592 (2000).
- R. Vinuesa and S. L. Brunton, Enhancing computational fluid dynamics with machine learning, Nat. Comput. Sci. 2, 358 (2022).
- C. Cho, J. Park, and H. Choi, A recursive neural-network-based subgrid-scale model for large eddy simulation: Application to homogeneous isotropic turbulence, J. Fluid Mech. 1000, A76 (2024).
- K. Duraisamy, Perspectives on machine learning-augmented Reynolds-averaged and large eddy simulation models of turbulence, Phys. Rev. Fluids 6, 050504 (2021).
- L. Biferale, A. A. Mailybaev, and G. Parisi, Optimal subgrid scheme for shell models of turbulence, Phys. Rev. E 95, 043108 (2017).
- G. Ortali, A. Corbetta, G. Rozza, and F. Toschi, Numerical proof of shell model turbulence closure, Phys. Rev. Fluids 7, L082401 (2022).
- J. Domingues Lemos and A. A. Mailybaev, Data-based approach for time-correlated closures of turbulence models, Phys. Rev. E 109, 025101 (2024).
- K. Um, R. Brand, Y. Fei, P. Holl, and N. Thuerey, Solver-in-the-loop: Learning from differentiable physics to interact with iterative PDE-solvers, Advances in Neural Information Processing Systems (2020), Vol. 33, pp. 6111–6122.
- B. List, L.-W. Chen, K. Bali, and N. Thuerey, How temporal unrolling supports neural physics simulators, Comput. Methods Appl. Mech. Eng. 433, 117441 (2025).
- K. Fukushima, Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern. 36, 193 (1980).
- J. Sirignano, J. F. MacArt, and J. B. Freund, DPM: A deep learning PDE augmentation method with application to large-eddy simulation, J. Comput. Phys. 423, 109811 (2020).
- V. Shankar, V. Puri, R. Balakrishnan, R. Maulik, and V. Viswanathan, Differentiable physics-enabled closure modeling for Burgers' turbulence, Machine Learning: Sci. Technol. 4, 015017 (2023).
- V. Shankara, D. Chakrabortya, V. Viswanathana, and R. Maulik, Differentiable turbulence: Closure as a PDE-constrained optimization, Phys. Rev. Fluids 10, 024605 (2025).
- B. Cheng and D. M. Titterington, Neural networks: A review from a statistical perspective, Stat. Sci. 9, 2 (1994).
- A. N. Kolmogorov, The local structure of turbulence in incompressible viscous fluid for very large Reynolds numbers, Proc. Math. Phys. Eng. Sci 434, 9 (1991).
- Z.-S. She and E. Leveque, Universal scaling laws in fully developed turbulence, Phys. Rev. Lett. 72, 336 (1994).
- S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Comput. 9, 1735 (1997).
- R. M. Larsen and T. Shpeisman, Tensorflow Graph Optimizations (2019), https://research.google/pubs/tensorflow-graph-optimizations/.
