Turbulence model reduction by deep learning

Heinonen, R. A.; Diamond, Patrick H.

doi:10.1103/PhysRevE.101.061201

Turbulence model reduction by deep learning

Journal Article · Thu Jun 04 00:00:00 EDT 2020 · Physical Review E

DOI:https://doi.org/10.1103/PhysRevE.101.061201· OSTI ID:1632122

^[1]; ^[2]

Univ. of California, San Diego, CA (United States); UC San Diego
Univ. of California, San Diego, CA (United States)

A defining problem of turbulence theory is to produce a predictive model for turbulent fluxes. These have profound implications for virtually all aspects of the turbulence dynamics. In magnetic confinement devices, drift-wave turbulence produces anomalous fluxes via cross-correlations between fluctuations. In this work, we introduce an alternative, data-driven method for parametrizing these fluxes. The method uses deep supervised learning to infer a reduced mean-field model from a set of numerical simulations. We apply the method to a simple drift-wave turbulence system and find a significant new effect which couples the particle flux to the local gradient of vorticity. Notably, here, this effect is much stronger than the oft-invoked shear suppression effect. We also recover the result via a simple calculation. The vorticity gradient effect tends to modulate the density profile. In addition, our method recovers a model for spontaneous zonal flow generation by negative viscosity, stabilized by nonlinear and hyperviscous terms. We highlight the important role of symmetry to implementation of the new method.

View Accepted Manuscript (DOE)

Research Organization:: Univ. of California, San Diego, CA (United States)

Sponsoring Organization:: National Science Foundation (NSF); USDOE Office of Science (SC), Fusion Energy Sciences (FES) (SC-24)

Grant/Contract Number:: FG02-04ER54738

OSTI ID:: 1632122

Journal Information:: Physical Review E, Journal Name: Physical Review E Journal Issue: 6 Vol. 101; ISSN PLEEE8; ISSN 2470-0045

Publisher:: American Physical Society (APS)Copyright Statement

Country of Publication:: United States

Language:: English

References (26)

7. Bericht über Untersuchungen zur ausgebildeten Turbulenz Prandtl, L. ZAMM - Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik, Vol. 5, Issue 2 https://doi.org/10.1002/zamm.19250050212	journal	January 1925
High-order splitting methods for the incompressible Navier-Stokes equations Karniadakis, George Em; Israeli, Moshe; Orszag, Steven A. Journal of Computational Physics, Vol. 97, Issue 2 https://doi.org/10.1016/0021-9991(91)90007-8	journal	December 1991
Approximation capabilities of multilayer feedforward networks Hornik, Kurt Neural Networks, Vol. 4, Issue 2 https://doi.org/10.1016/0893-6080(91)90009-T	journal	January 1991
Multilayer feedforward networks with a nonpolynomial activation function can approximate any function Leshno, Moshe; Lin, Vladimir Ya.; Pinkus, Allan Neural Networks, Vol. 6, Issue 6 https://doi.org/10.1016/S0893-6080(05)80131-5	journal	January 1993
BOUT++: A framework for parallel plasma fluid simulations Dudson, B. D.; Umansky, M. V.; Xu, X. Q. Computer Physics Communications, Vol. 180, Issue 9 https://doi.org/10.1016/j.cpc.2009.03.008	journal	September 2009
A high-bias, low-variance introduction to Machine Learning for physicists Mehta, Pankaj; Bukov, Marin; Wang, Ching-Hao Physics Reports, Vol. 810 https://doi.org/10.1016/j.physrep.2019.03.001	journal	May 2019
Turbulent Flows Pope, Stephen B. https://doi.org/10.1017/CBO9780511840531	book	July 2012
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Free Energy of a Nonuniform System. I. Interfacial Free Energy Cahn, John W.; Hilliard, John E. The Journal of Chemical Physics, Vol. 28, Issue 2 https://doi.org/10.1063/1.1744102	journal	February 1958
Nonlinear Theory of Drift-Wave Turbulence and Enhanced Diffusion Dupree, T. H. Physics of Fluids, Vol. 10, Issue 5 https://doi.org/10.1063/1.1762220	journal	January 1967
Bifurcation in electrostatic resistive drift wave turbulence Numata, Ryusuke; Ball, Rowena; Dewar, Robert L. Physics of Plasmas, Vol. 14, Issue 10 https://doi.org/10.1063/1.2796106	journal	October 2007
On the emergence of macroscopic transport barriers from staircase structures Ashourvan, Arash; Diamond, P. H. Physics of Plasmas, Vol. 24, Issue 1 https://doi.org/10.1063/1.4973660	journal	January 2017
A collisional drift wave description of plasma edge turbulence Wakatani, Masahiro; Hasegawa, Akira Physics of Fluids, Vol. 27, Issue 3 https://doi.org/10.1063/1.864660	journal	January 1984
Nonlinear oscillations of rarified plasma Vedenov, A. A.; Velikhov, E. P.; Sagdeev, R. Z. Nuclear Fusion, Vol. 1, Issue 2 https://doi.org/10.1088/0029-5515/1/2/003	journal	March 1961
A density rise experiment on PLT Strachan, J. D.; Bretz, N.; Mazzucato, E. Nuclear Fusion, Vol. 22, Issue 9 https://doi.org/10.1088/0029-5515/22/9/002	journal	September 1982
Towards an emerging understanding of non-locality phenomena and non-local transport Ida, K.; Shi, Z.; Sun, H. J. Nuclear Fusion, Vol. 55, Issue 1 https://doi.org/10.1088/0029-5515/55/1/013022	journal	January 2015
Zonal flows in plasma—a review Diamond, P. H.; Itoh, S-I; Itoh, K. Plasma Physics and Controlled Fusion, Vol. 47, Issue 5 https://doi.org/10.1088/0741-3335/47/5/R01	journal	April 2005
Scale selection and feedback loops for patterns in drift wave-zonal flow turbulence Guo, Weixin; Diamond, Patrick H.; Hughes, David W. Plasma Physics and Controlled Fusion, Vol. 61, Issue 10 https://doi.org/10.1088/1361-6587/ab3831	journal	August 2019
On the validity of the local diffusive paradigm in turbulent plasma transport Dif-Pradalier, G.; Diamond, P. H.; Grandgirard, V. Physical Review E, Vol. 82, Issue 2 https://doi.org/10.1103/PhysRevE.82.025401	journal	August 2010
How mesoscopic staircases condense to macroscopic barriers in confined plasma turbulence Ashourvan, Arash; Diamond, P. H. Physical Review E, Vol. 94, Issue 5 https://doi.org/10.1103/PhysRevE.94.051202	journal	November 2016
Finding the Elusive E × B Staircase in Magnetized Plasmas Dif-Pradalier, G.; Hornung, G.; Ghendrih, Ph. Physical Review Letters, Vol. 114, Issue 8 https://doi.org/10.1103/PhysRevLett.114.085004	journal	February 2015
Formation of a High Pressure Staircase Pedestal with Suppressed Edge Localized Modes in the DIII-D Tokamak Ashourvan, Arash; Nazikian, R.; Belli, E. Physical Review Letters, Vol. 123, Issue 11 https://doi.org/10.1103/PhysRevLett.123.115001	journal	September 2019
Stationary Spectrum of Strong Turbulence in Magnetized Nonuniform Plasma Hasegawa, Akira; Mima, Kunioki Physical Review Letters, Vol. 39, Issue 4 https://doi.org/10.1103/PhysRevLett.39.205	journal	July 1977
Plasma Edge Turbulence Hasegawa, Akira; Wakatani, Masahiro Physical Review Letters, Vol. 50, Issue 9 https://doi.org/10.1103/PhysRevLett.50.682	journal	February 1983
XSEDE: Accelerating Scientific Discovery Towns, John; Cockerill, Timothy; Dahan, Maytal Computing in Science & Engineering, Vol. 16, Issue 5 https://doi.org/10.1109/MCSE.2014.80	journal	September 2014
Geostrophic Turbulence Charney, Jule G. Journal of the Atmospheric Sciences, Vol. 28, Issue 6 https://doi.org/10.1175/1520-0469(1971)028%3C1087:GT%3E2.0.CO;2	journal	September 1971

Similar Records

Learning how structures form in drift-wave turbulence

Journal Article · Wed Aug 26 20:00:00 EDT 2020 · Plasma Physics and Controlled Fusion · OSTI ID:1660280

Scale selection and feedback loops for patterns in drift wave-zonal flow turbulence

Journal Article · Thu Aug 01 20:00:00 EDT 2019 · Plasma Physics and Controlled Fusion · OSTI ID:1546784

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
97 MATHEMATICS AND COMPUTING
artificial neural networks
drift waves
machine learning
plasma turbulence
turbulent mixing
weak turbulence

Turbulence model reduction by deep learning

Citation Formats

References (26)

Similar Records

Related Subjects