Subgrid modelling for two-dimensional turbulence using neural networks. (English) Zbl 1415.76405
Summary: In this investigation, a data-driven turbulence closure framework is introduced and deployed for the subgrid modelling of Kraichnan turbulence. The novelty of the proposed method lies in the fact that snapshots from high-fidelity numerical data are used to inform artificial neural networks for predicting the turbulence source term through localized grid-resolved information. In particular, our proposed methodology successfully establishes a map between inputs given by stencils of the vorticity and the streamfunction along with information from two well-known eddy-viscosity kernels. Through this we predict the subgrid vorticity forcing in a temporally and spatially dynamic fashion. Our study is both a priori and a posteriori in nature. In the former, we present an extensive hyper-parameter optimization analysis in addition to learning quantification through probability-density-function-based validation of subgrid predictions. In the latter, we analyse the performance of our framework for flow evolution in a classical decaying two-dimensional turbulence test case in the presence of errors related to temporal and spatial discretization. Statistical assessments in the form of angle-averaged kinetic energy spectra demonstrate the promise of the proposed methodology for subgrid quantity inference. In addition, it is also observed that some measure of a posteriori error must be considered during optimal model selection for greater accuracy. The results in this article thus represent a promising development in the formalization of a framework for generation of heuristic-free turbulence closures from data.
MSC:
| 76F65 | Direct numerical and large eddy simulation of turbulence |
| 76F05 | Isotropic turbulence; homogeneous turbulence |
References:
| [1] | Arakawa, A., Computational design for long-term numerical integration of the equations of fluid motion: two-dimensional incompressible flow. Part I, J. Comput. Phys., 1, 1, 119-143, (1966) · Zbl 0147.44202 · doi:10.1016/0021-9991(66)90015-5 |
| [2] | Beck, A. D.; Flad, D. G.; Munz, C.-D. |
| [3] | Berselli, L. C.; Iliescu, T.; Layton, W. J., Mathematics of Large Eddy Simulation of Turbulent Flows, (2005), Springer · Zbl 1089.76002 |
| [4] | Canuto, V. M.; Cheng, Y., Determination of the Smagorinsky-Lilly constant C_{S}, Phys. Fluids, 9, 5, 1368-1378, (1997) · doi:10.1063/1.869251 |
| [5] | Cohen, K.; Siegel, S.; Mclaughlin, T.; Gillies, E., Feedback control of a cylinder wake low-dimensional model, AIAA J., 41, 7, 1389-1391, (2003) |
| [6] | Cushman-Roisin, B.; Beckers, J.-M., Introduction to Geophysical Fluid Dynamics: Physical and Numerical Aspects, 101, (2011), Academic · Zbl 1319.86001 |
| [7] | Duraisamy, K.; Iaccarino, G.; Xiao, H. |
| [8] | Eden, C.; Greatbatch, R. J., Towards a mesoscale eddy closure, Ocean Model., 20, 3, 223-239, (2008) · doi:10.1016/j.ocemod.2007.09.002 |
| [9] | Faller, W. E.; Schreck, S. J., Unsteady fluid mechanics applications of neural networks, J. Aircraft, 34, 1, 48-55, (1997) · doi:10.2514/2.2134 |
| [10] | Fox-Kemper, B.; Danabasoglu, G.; Ferrari, R.; Griffies, S. M.; Hallberg, R. W.; Holland, M. M.; Maltrud, M. E.; Peacock, S.; Samuels, B. L., Parameterization of mixed layer eddies. III. Implementation and impact in global ocean climate simulations, Ocean Model., 39, 1-2, 61-78, (2011) · doi:10.1016/j.ocemod.2010.09.002 |
| [11] | Frederiksen, J. S.; O’Kane, T. J.; Zidikheri, M. J., Subgrid modelling for geophysical flows, Phil. Trans. R. Soc. Lond. A, 371, 1982, (2013) · Zbl 1353.86009 |
| [12] | Frederiksen, J. S.; Zidikheri, M. J., Theoretical comparison of subgrid turbulence in atmospheric and oceanic quasi-geostrophic models, Nonlinear Process. Geophys., 23, 2, 95-105, (2016) · doi:10.5194/npg-23-95-2016 |
| [13] | Galperin, B.; Orszag, S. A., Large Eddy Simulation of Complex Engineering and Geophysical Flows, (1993), Cambridge University Press |
| [14] | Gamahara, M.; Hattori, Y., Searching for turbulence models by artificial neural network, Phys. Rev. Fluids, 2, 5, (2017) · doi:10.1103/PhysRevFluids.2.054604 |
| [15] | Germano, M.; Piomelli, U.; Moin, P.; Cabot, W. H., A dynamic subgrid-scale eddy viscosity model, Phys. Fluids, 3, 7, 1760-1765, (1991) · Zbl 0825.76334 · doi:10.1063/1.857955 |
| [16] | Ghosal, S.; Lund, T. S.; Moin, P.; Akselvoll, K., A dynamic localization model for large-eddy simulation of turbulent flows, J. Fluid Mech., 286, 229-255, (1995) · Zbl 0837.76032 · doi:10.1017/S0022112095000711 |
| [17] | King, R. N.; Hamlington, P. E.; Dahm, W. J., Autonomic closure for turbulence simulations, Phys. Rev. E, 93, 3, (2016) |
| [18] | Kingma, D. P.; Ba, J. |
| [19] | Kraichnan, R. H., Inertial ranges in two-dimensional turbulence, Phys. Fluids, 10, 7, 1417-1423, (1967) · doi:10.1063/1.1762301 |
| [20] | Kutz, J. N., Deep learning in fluid dynamics, J. Fluid Mech., 814, 1-4, (2017) · Zbl 1383.76380 · doi:10.1017/jfm.2016.803 |
| [21] | Langford, J. A.; Moser, R. D., Optimal LES formulations for isotropic turbulence, J. Fluid Mech., 398, 321-346, (1999) · Zbl 0983.76043 · doi:10.1017/S0022112099006369 |
| [22] | Leith, C. E., Diffusion approximation for two-dimensional turbulence, Phys. Fluids, 11, 3, 671-672, (1968) · doi:10.1063/1.1691968 |
| [23] | Ling, J.; Kurzawski, A.; Templeton, J., Reynolds averaged turbulence modelling using deep neural networks with embedded invariance, J. Fluid Mech., 807, 155-166, (2016) · Zbl 1383.76175 · doi:10.1017/jfm.2016.615 |
| [24] | Ling, J.; Templeton, J., Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier-Stokes uncertainty, Phys. Fluids, 27, 8, (2015) · doi:10.1063/1.4927765 |
| [25] | Mannarino, A.; Mantegazza, P., Nonlinear aeroelastic reduced order modeling by recurrent neural networks, J. Fluid. Struct., 48, 103-121, (2014) · doi:10.1016/j.jfluidstructs.2014.02.016 |
| [26] | Mansfield, J. R.; Knio, O. M.; Meneveau, C., A dynamic LES scheme for the vorticity transport equation: formulation and a priori tests, J. Comput. Phys., 145, 2, 693-730, (1998) · Zbl 0926.76088 · doi:10.1006/jcph.1998.6051 |
| [27] | Marshall, J. S.; Beninati, M. L., Analysis of subgrid-scale torque for large-eddy simulation of turbulence, AIAA J., 41, 10, 1875-1881, (2003) |
| [28] | Maulik, R.; San, O., A neural network approach for the blind deconvolution of turbulent flows, J. Fluid Mech., 831, 151-181, (2017) · Zbl 1421.76134 · doi:10.1017/jfm.2017.637 |
| [29] | Maulik, R.; San, O., A stable and scale-aware dynamic modeling framework for subgrid-scale parameterizations of two-dimensional turbulence, Comput. Fluids, 158, 11-38, (2017) · Zbl 1390.76194 · doi:10.1016/j.compfluid.2016.11.015 |
| [30] | Milano, M.; Koumoutsakos, P., Neural network modeling for near wall turbulent flow, J. Comput. Phys., 182, 1, 1-26, (2002) · Zbl 1090.76535 · doi:10.1006/jcph.2002.7146 |
| [31] | Mohan, A. T.; Gaitonde, D. V. |
| [32] | Moser, R. D.; Malaya, N. P.; Chang, H.; Zandonade, P. S.; Vedula, P.; Bhattacharya, A.; Haselbacher, A., Theoretically based optimal large-eddy simulation, Phys. Fluids, 21, 10, (2009) · Zbl 1183.76363 · doi:10.1063/1.3249754 |
| [33] | Parish, E. J.; Duraisamy, K., A paradigm for data-driven predictive modeling using field inversion and machine learning, J. Comput. Phys., 305, 758-774, (2016) · Zbl 1349.76006 · doi:10.1016/j.jcp.2015.11.012 |
| [34] | Pathak, J.; Wikner, A.; Fussell, R.; Chandra, S.; Hunt, B. R.; Girvan, M.; Ott, E., Hybrid forecasting of chaotic processes: using machine learning in conjunction with a knowledge-based model, Chaos, 28, 4, (2018) · doi:10.1063/1.5028373 |
| [35] | Piomelli, U.; Cabot, W. H.; Moin, P.; Lee, S., Subgrid-scale backscatter in turbulent and transitional flows, Phys. Fluids, 3, 7, 1766-1771, (1991) · Zbl 0825.76335 · doi:10.1063/1.857956 |
| [36] | Raissi, M.; Karniadakis, G. E., Hidden physics models: machine learning of nonlinear partial differential equations, J. Comput. Phys., 357, 125-141, (2018) · Zbl 1381.68248 · doi:10.1016/j.jcp.2017.11.039 |
| [37] | Sagaut, P., Large Eddy Simulation for Incompressible Flows: An Introduction, (2006), Springer · Zbl 1091.76001 |
| [38] | San, O.; Maulik, R., Neural network closures for nonlinear model order reduction, Adv. Comput. Math., (2018) · Zbl 1404.37101 |
| [39] | San, O.; Staples, A. E., High-order methods for decaying two-dimensional homogeneous isotropic turbulence, Comput. Fluids, 63, 105-127, (2012) · Zbl 1365.76064 · doi:10.1016/j.compfluid.2012.04.006 |
| [40] | San, O.; Staples, A. E.; Iliescu, T., Approximate deconvolution large eddy simulation of a stratified two-layer quasigeostrophic ocean model, Ocean Model., 63, 1-20, (2013) · doi:10.1016/j.ocemod.2012.12.007 |
| [41] | Sarghini, F.; De Felice, G.; Santini, S., Neural networks based subgrid scale modeling in large eddy simulations, Comput. Fluids, 32, 1, 97-108, (2003) · Zbl 1009.76512 · doi:10.1016/S0045-7930(01)00098-6 |
| [42] | Schaeffer, H., Learning partial differential equations via data discovery and sparse optimization, Proc. R. Soc. Lond. A, 473, 2197, (2017) · Zbl 1404.35397 |
| [43] | Singh, A. P.; Medida, S.; Duraisamy, K., Machine-learning-augmented predictive modeling of turbulent separated flows over airfoils, AIAA J., 55, 7, 2215-2227, (2017) |
| [44] | Smagorinsky, J., General circulation experiments with the primitive equations. I. The basic experiment, Mon. Weath. Rev., 91, 3, 99-164, (1963) · doi:10.1175/1520-0493(1963)091<0099:GCEWTP>2.3.CO;2 |
| [45] | Tracey, B. D.; Duraisamy, K.; Alonso, J. J., A machine learning strategy to assist turbulence model development, 53rd AIAA Aerospace Sciences Meeting, (2015) |
| [46] | Vorobev, A.; Zikanov, O., Smagorinsky constant in LES modeling of anisotropic MHD turbulence, Theor. Comput. Fluid Dyn., 22, 3-4, 317-325, (2008) · Zbl 1161.76503 · doi:10.1007/s00162-007-0064-z |
| [47] | Vreman, A. W., An eddy-viscosity subgrid-scale model for turbulent shear flow: algebraic theory and applications, Phys. Fluids, 16, 10, 3670-3681, (2004) · Zbl 1187.76543 · doi:10.1063/1.1785131 |
| [48] | Wan, Z. Y.; Vlachas, P.; Koumoutsakos, P.; Sapsis, T., Data-assisted reduced-order modeling of extreme events in complex dynamical systems, PloS One, 13, 5, (2018) |
| [49] | Wang, J.-X.; Wu, J.; Ling, J.; Iaccarino, G.; Xiao, H. |
| [50] | Wang, J.-X.; Wu, J.-L.; Xiao, H., Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data, Phys. Rev. Fluids, 2, 3, (2017) |
| [51] | Weatheritt, J.; Sandberg, R. D., Hybrid Reynolds-averaged/large-eddy simulation methodology from symbolic regression: formulation and application, AIAA J., 55, 11, 3734-3746, (2017) |
| [52] | Wu, J.-L.; Xiao, H.; Paterson, E. |
| [53] | Wu, J.-L.; Xiao, H.; Paterson, E., Physics-informed machine learning approach for augmenting turbulence models: a comprehensive framework, Phys. Rev. Fluids, 3, 7, (2018) |
| [54] | Xiao, H.; Wu, J.-L.; Wang, J.-X.; Sun, R.; Roy, C. J., Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: a data-driven, physics-informed Bayesian approach, J. Comput. Phys., 324, 115-136, (2016) · Zbl 1371.76082 · doi:10.1016/j.jcp.2016.07.038 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
