Symbolic turbulence model development for complex-geometry flows exploiting language model-based transfer learning
Open Access
- 1 September 2025
- journal article
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (9)
Abstract
Evolutionary symbolic regression methods, such as Genetic Programing or Gene Expression Programing (GEP), enable the exploration of turbulence models for Reynolds-averaged Navier–Stokes (RANS) simulations. However, these models often encounter limitations when addressing phenomena beyond their training distribution. While expanding the number of training cases or extending the exploration time could mitigate these issues, the required increase in computational budget restricts such approaches, especially when considering engineering-relevant scenarios. Conversely, knowledge from prior optimizations might be available, but initial candidate solutions are typically generated randomly and rarely incorporate preliminary assumptions to limit the search space. In contrast, transfer learning, widely used for neural networks, offers a solution by reusing knowledge from pre-trained models, but its application to symbolic regression for turbulence modeling remains unexplored. This study introduces a novel framework leveraging the transfer learning methodology for the GEP to develop turbulence closures for RANS. The framework integrates a language model, parameterized without necessitating significant resources, to discern recurring patterns within equations obtained from previous optimizations. The performance is demonstrated on a three-dimensional, highly bent duct, including various physical phenomena. The language model is pre-trained based on simpler building-block flows exhibiting some phenomena present in the highly bent duct, i.e., a canonical duct flow featuring secondary flows and the case of the periodic hill displaying flow separation and reattachment. It is demonstrated that a more targeted and efficient model exploration can be achieved by augmenting the initial set of candidate solutions using a language model and superimposing model information from distinct prior optimizations.Keywords
This publication has 30 references indexed in Scilit:
- Generalization Limits of Data-Driven Turbulence ModelsFlow, Turbulence and Combustion, 2024
- Uncovering labeler bias in machine learning annotation tasksAI and Ethics, 2024
- A priori tests of eddy viscosity models in square duct flowTheoretical and Computational Fluid Dynamics, 2020
- RANS turbulence model development using CFD-driven machine learningJournal of Computational Physics, 2020
- Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic RegressionFlow, Turbulence and Combustion, 2019
- Transfer learning in constructive induction with Genetic ProgrammingGenetic Programming and Evolvable Machines, 2019
- The development of algebraic stress models using a novel evolutionary algorithmInternational Journal of Heat and Fluid Flow, 2017
- A novel evolutionary algorithm applied to algebraic modifications of the RANS stress–strain relationshipJournal of Computational Physics, 2016
- A paradigm for data-driven predictive modeling using field inversion and machine learningJournal of Computational Physics, 2016
- Flow over periodic hills – Numerical and experimental study in a wide range of Reynolds numbersComputers & Fluids, 2009