Skip to main content
SpringerLink
Log in

A Data-Driven Wall-Shear Stress Model for LES Using Gradient Boosted Decision Trees

  • Conference paper
  • First Online:
High Performance Computing (ISC High Performance 2021)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12761))

Included in the following conference series:

Abstract

With the recent advances in machine learning, data-driven strategies could augment wall modeling in large eddy simulation (LES). In this work, a wall model based on gradient boosted decision trees is presented. The model is trained to learn the boundary layer of a turbulent channel flow so that it can be used to make predictions for significantly different flows where the equilibrium assumptions are valid. The methodology of building the model is presented in detail. The experiment conducted to choose the data for training is described. The trained model is tested a posteriori on a turbulent channel flow and the flow over a wall-mounted hump. The results from the tests are compared with that of an algebraic equilibrium wall model, and the performance is evaluated. The results show that the model has succeeded in learning the boundary layer, proving the effectiveness of our methodology of data-driven model development, which is extendable to complex flows.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Choi, H., Moin, P.: Grid-point requirements for large eddy simulation: Chapman’s estimates revisited. Phys. Fluids 24(1), 011702 (2012)

    Article  Google Scholar 

  2. Calafell, J., Trias, F.X., Lehmkuhl, O., Oliva, A.: A time-average filtering technique to improve the efficiency of two-layer wall models for large eddy simulation in complex geometries. Comput. Fluids 188, 44–59 (2019)

    Article  MathSciNet  Google Scholar 

  3. Piomelli, U.: Wall-layer models for large-eddy simulations. Progr. Aerospace Sci. 44(6), 437–446 (2008). https://doi.org/10.1016/j.paerosci.2008.06.001. www.sciencedirect.com/science/article/pii/S037604210800047X. Large Eddy Simulation-Current Capabilities and Areas of Needed Research

    Article  Google Scholar 

  4. Piomelli, U., Balaras, E.: Wall-layer models for large-eddy simulations. Annual review of fluid mechanics 34(1), 349–374 (2002)

    Article  MathSciNet  Google Scholar 

  5. Larsson, J., Kawai, S., Bodart, J., Bermejo-Moreno, I.: Large eddy simulation with modeled wall-stress: recent progress and future directions. Mech. Eng. Rev. 3(1), 15–00418 (2016). https://doi.org/10.1299/mer.15-00418

    Article  Google Scholar 

  6. Bose, S.T., Park, G.I.: Wall-modeled large-eddy simulation for complex turbulent flows. Ann. Rev. Fluid Mech. 50(1), 535–561 (2018). https://doi.org/10.1146/annurev-fluid-122316-045241

    Article  MathSciNet  MATH  Google Scholar 

  7. Cheng, W., Pullin, D.I., Samtaney, R., Zhang, W., Gao, W.: Large-eddy simulation of flow over a cylinder with \(re_{D}\) from \(3.9\times 10^{3}\) to \(8.5\times 10^{5}\) : a skin-friction perspective. J. Fluid Mech. 820, 121–158 (2017)

    Article  MathSciNet  Google Scholar 

  8. Larsson, J., Laurence, S., Bermejo-Moreno, I., Bodart, J., Karl, S., Vicquelin, R.: Incipient thermal choking and stable shock-train formation in the heat-release region of a scramjet combustor. Part II Combust. Flame 162, 907–920 (2015). Large eddy simulations

    Article  Google Scholar 

  9. Iyer, P.S., Park, G.I., Malik, M.R.: Application of wall-modeled LES to turbulent separated flows. In: APS Division of Fluid Dynamics Meeting Abstracts, APS Meeting Abstracts, p. G33.004, November 2016

    Google Scholar 

  10. Yang, X.I.A., Urzay, J., Bose, S., Moin, P.: Aerodynamic heating in wall-modeled large-eddy simulation of high-speed flows. AIAA J. 56(2), 731–742 (2018)

    Article  Google Scholar 

  11. Yang, X.I.A., Urzay, J., Moin, P.: Heat-transfer rates in equilibrium-wall-modeled les of supersonic turbulent flows. In: Annual Research Briefs, Center for Turbulence Research, pp. 3–15. Stanford University (2016)

    Google Scholar 

  12. Slotnick, J., et al.: CFD vision 2030 study: a path to revolutionary computational aerosciences (2014)

    Google Scholar 

  13. Milano, M., Koumoutsakos, P.: Neural network modeling for near wall turbulent flow. J. Comput. Phys. 182(1), 1–26 (2002)

    Article  Google Scholar 

  14. Tracey, B., Duraisamy, K., Alonso, J.: Application of supervised learning to quantify uncertainties in turbulence and combustion modeling. https://arc.aiaa.org/doi/abs/10.2514/6.2013-259

  15. Tracey, B.D., Duraisamy, K., Alonso, J.J.: A machine learning strategy to assist turbulence model development. In: 53rd AIAA Aerospace Sciences Meeting, p. 1287 (2015)

    Google Scholar 

  16. Duraisamy, K., Zhang, Z.J., Singh, A.P.: New approaches in turbulence and transition modeling using data-driven techniques. In: 53rd AIAA Aerospace Sciences Meeting, p. 1284, (2015)

    Google Scholar 

  17. Ling, J., Kurzawski, A., Templeton, J.: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166 (2016). https://doi.org/10.1017/jfm.2016.615

    Article  MathSciNet  MATH  Google Scholar 

  18. Jin-Long, W., Wang, J.-X., Xiao, H.: A Bayesian calibration-prediction method for reducing model-form uncertainties with application in rans simulations. Flow Turbul. Combust. 97(3), 761–786 (2016)

    Article  Google Scholar 

  19. Wang, J.-X., Jin-Long, W., Xiao, H.: Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data. Phys. Rev. Fluids 2(3), 034603 (2017)

    Article  Google Scholar 

  20. Jin-Long, W., Xiao, H., Paterson, E.: Physics-informed machine learning approach for augmenting turbulence models: a comprehensive framework. Phys. Rev. Fluids 3(7), 074602 (2018)

    Article  Google Scholar 

  21. King, R.N., Hamlington, P.E., Dahm, W.J.A.: Autonomic closure for turbulence simulations. Phys. Rev. E 93(3), 031301 (2016)

    Article  Google Scholar 

  22. Gamahara, M., Hattori, Y.: Searching for turbulence models by artificial neural network. Phys. Rev. Fluids 2(5), 054604 (2017)

    Article  Google Scholar 

  23. Maulik, R., San, O.: A neural network approach for the blind deconvolution of turbulent flows (2017). arXiv preprint: arXiv:1706.00912

  24. Vollant, A., Balarac, G., Corre, C.: Subgrid-scale scalar flux modelling based on optimal estimation theory and machine-learning procedures. J. Turbul. 18(9), 854–878 (2017)

    Article  MathSciNet  Google Scholar 

  25. Zhang, Z.J., Duraisamy, K.: Machine learning methods for data-driven turbulence modeling. In: 22nd AIAA Computational Fluid Dynamics Conference, p. 2460 (2015)

    Google Scholar 

  26. Ma, M., Jiacai, L., Tryggvason, G.: Using statistical learning to close two-fluid multiphase flow equations for a simple bubbly system. Phys. Fluids 27(9), 092101 (2015)

    Article  Google Scholar 

  27. Ma, M., Jiacai, L., Tryggvason, G.: Using statistical learning to close two-fluid multiphase flow equations for bubbly flows in vertical channels. Int. J. Multiphase Flow 85, 336–347 (2016)

    Article  MathSciNet  Google Scholar 

  28. Duraisamy, K., Iaccarino, G., Xiao, H.: Turbulence modeling in the age of data. Ann. Rev. Fluid Mech. 51, 357–377 (2019)

    Article  MathSciNet  Google Scholar 

  29. Brunton, S.L., Noack, B.R., Koumoutsakos, P.: Machine learning for fluid mechanics. Ann. Rev. Fluid Mech. 52(1), 477–508 (2020)

    Article  Google Scholar 

  30. Yang, X.I.A., Zafar, S., Wang, J.-X., Xiao, H.: Predictive large-eddy-simulation wall modeling via physics-informed neural networks. Phys. Rev. Fluids 4, 034602 (2019)

    Article  Google Scholar 

  31. Lozano-Durán, A., Bae, H.J.: Self-critical machine-learning wall-modeled les for external aerodynamics (2020). arXiv preprint arXiv:2012.10005

  32. Chen, T., Guestrin, C.: Xgboost. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2016. https://doi.org/10.1145/2939672.2939785

  33. Owen, H., et al.: Wall-modeled large-eddy simulation in a finite element framework. Int. J. Numer. Methods Fluids. 92, 20–37 (2019). https://doi.org/10.1002/fld.4770

    Article  MathSciNet  Google Scholar 

  34. Friedman, J.H.: Stochastic gradient boosting. Comput. Statist. Data Anal. 38(4), 367–378 (2002)

    Article  MathSciNet  Google Scholar 

  35. Marusic, I., Monty, J.P., Hultmark, M., Smits, A.J.: On the logarithmic region in wall turbulence. J. Fluid Mech. 716, R3 (2013). https://doi.org/10.1017/jfm.2012.511

    Article  MathSciNet  MATH  Google Scholar 

  36. Vazquez, M., et al.: Alya: multiphysics engineering simulation towards exascale. J. Comput. Sci. 14, 15–27 (2016). https://doi.org/10.1016/j.jocs.2015.12.007. ISSN 1877–7503. www.sciencedirect.com/science/article/pii/S1877750315300521. The Route to Exascale: Novel Mathematical Methods, Scalable Algorithms and Computational Science Skills

    Article  MathSciNet  Google Scholar 

  37. Vreman, A.W.: An eddy-viscosity subgrid-scale model for turbulent shear flow: algebraic theory and applications. Phys. Fluids 16(10), 3670–3681 (2004)

    Article  Google Scholar 

  38. Lehmkuhl, O., Piomelli, U., Houzeaux, G.: On the extension of the integral length-scale approximation model to complex geometries. Int. J. Heat Fluid Flow 78, 108422 (2019)

    Article  Google Scholar 

  39. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

  40. Poroseva, S.V., Colmenares, J.D.F., Murman, S.M.: On the accuracy of RANs simulations with DNS data. Phys. Fluids 28(11), 115102 (2016)

    Article  Google Scholar 

  41. Thompson, R.L., Sampaio, L.E.B., de Bragança Alves, F.A.V., Thais, L., Mompean, G.: A methodology to evaluate statistical errors in DNS data of plane channel flows. Comput. Fluids 130, 1–7 (2016)

    Article  MathSciNet  Google Scholar 

  42. Jinlong, W., Xiao, H., Sun, R., Wang, Q.: Reynolds-averaged Navier-stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned. J. Fluid Mech. 869, 553–586 (2019)

    Article  MathSciNet  Google Scholar 

  43. Kawai, S., Larsson, J.: Wall-modeling in large eddy simulation: length scales, grid resolution, and accuracy. Phys. Fluids 24(1), 015105 (2012)

    Article  Google Scholar 

  44. Hoyas, S., Jiménez, J.: Scaling of the velocity fluctuations in turbulent channels up to re \(\tau \)= 2003. Phys. fluids 18(1), 011702 (2006)

    Article  Google Scholar 

  45. Rumsey, C.L., Gatski, T.B., Sellers, W.L., Vasta, V.N., Viken, S.A.: Summary of the 2004 computational fluid dynamics validation workshop on synthetic jets. AIAA J. 44(2), 194–207 (2006)

    Article  Google Scholar 

  46. Park, G.I.: Wall-modeled large-eddy simulation of a separated flow over the NASA wall-mounted hump by (2015)

    Google Scholar 

  47. Naughton, J.W., Viken, S., Greenblatt, D.: Skin friction measurements on the NASA hump model. AIAA J. 44(6), 1255–1265 (2006)

    Article  Google Scholar 

  48. Kempf, A., Klein, M., Janicka, J.: Efficient generation of initial-and inflow-conditions for transient turbulent flows in arbitrary geometries. Flow Turbul. Combust. 74(1), 67–84 (2005)

    Article  Google Scholar 

Download references

Acknowledgment

SR acknowledges the financial support by the Ministerio de Ciencia y Innovación y Universidades, for the grant, Ayudas para contratos predoctorales para la formación de doctores(Ref: BES-2017-081982). OL has been partially supported by a Ramon y Cajal postdoctoral contract (Ref: RYC2018-025949-I). We also acknowledge the Barcelona Supercomputing Center for awarding us access to the MareNostrum IV machine based in Barcelona, Spain.

Author information

Authors and Affiliations

  1. Barcelona Supercomputing Center, Barcelona, Spain

    Sarath Radhakrishnan, Lawrence Adu Gyamfi, Arnau Miró, Bernat Font, Joan Calafell & Oriol Lehmkuhl

Authors
  1. Sarath Radhakrishnan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lawrence Adu Gyamfi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Arnau Miró
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bernat Font
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Joan Calafell
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Oriol Lehmkuhl
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sarath Radhakrishnan .

Editor information

Editors and Affiliations

  1. University of Tennessee at Knoxville, Knowville, TN, USA

    Heike Jagode

  2. Karlsruhe Institute of Technology, Karlsruhe, Baden-Württemberg, Germany

    Hartwig Anzt

  3. King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

    Hatem Ltaief

  4. University of Tennessee System, Knoxville, TN, USA

    Piotr Luszczek

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Radhakrishnan, S., Gyamfi, L.A., Miró, A., Font, B., Calafell, J., Lehmkuhl, O. (2021). A Data-Driven Wall-Shear Stress Model for LES Using Gradient Boosted Decision Trees. In: Jagode, H., Anzt, H., Ltaief, H., Luszczek, P. (eds) High Performance Computing. ISC High Performance 2021. Lecture Notes in Computer Science(), vol 12761. Springer, Cham. https://doi.org/10.1007/978-3-030-90539-2_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-90539-2_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-90538-5

  • Online ISBN: 978-3-030-90539-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation