A data-driven wall-shear stress model for LES using gradient boosted decision trees
Document typeConference report
Rights accessOpen Access
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.
CitationRadhakrishnan, S. [et al.]. A data-driven wall-shear stress model for LES using gradient boosted decision trees. A: International Conference on High Performance Computing. "High Performance Computing: ISC High Performance Digital 2021 International Workshops: Frankfurt am Main, Germany, June 24–July 2, 2021: revised selected papers". Springer Nature, 2021, p. 105-121. ISBN 978-3-030-90539-2. DOI 10.1007/978-3-030-90539-2_7.
- Departament de Física - Ponències/Comunicacions de congressos 
- Doctorat en Ciència i Tecnologia Aeroespacials - Ponències/Comunicacions de congressos 
- Computer Applications in Science & Engineering - Ponències/Comunicacions de congressos 
- TUAREG - Turbulence and Aerodynamics in Mechanical and Aerospace Engineering Research Group - Ponències/Comunicacions de congressos 
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder