Towards a machine-learning-based large eddy simulation of offshore wind farms

This study introduces a Scale-Adaptive Machine-Learning Subgrid-Scale model developed to predict subgrid-scale turbulence within the framework of large eddy simulations for offshore wind farms. Unlike traditional subgrid-scale models that rely on blending of isotropy and scale similarity, the propos...

Full description

Saved in:
Bibliographic Details
Published in:Computers & fluids Vol. 302; p. 106823
Main Authors: Marefat, H. Ali, Alam, Jahrul, Pope, Kevin
Format: Journal Article
Language:English
Published: Elsevier Ltd 15.11.2025
Subjects:
Encoder–decoder models
LES
Machine learning
Offshore wind farms
Subgrid-scale model
LES
Encoder–decoder models
Subgrid-scale model
Machine learning
Offshore wind farms
ISSN:0045-7930
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study introduces a Scale-Adaptive Machine-Learning Subgrid-Scale model developed to predict subgrid-scale turbulence within the framework of large eddy simulations for offshore wind farms. Unlike traditional subgrid-scale models that rely on blending of isotropy and scale similarity, the proposed approach leverages a supervised learning framework based on physically informed flow observables derived from mixed modelling theory and Leonard decomposition. The model employs a novel encoder–decoder neural network architecture designed to capture coherent enstrophy dynamics and multi-scale turbulence interactions. Skip connections and latent representations serve as implicit filters, enabling the model to represent both structural and functional aspects of turbulence. Trained using data from a scale-adaptive LES method, outcome of the presented model has been validated for its ability to learn and reproduce key turbulence characteristics, such as intermittency and energy transfer, across resolutions and flow scenarios. A-priori tests confirm its capacity to capture statistical turbulence features, while a-posteriori tests demonstrate that the model dynamically predicts eddy viscosity and produces flow fields comparable to high-resolution LES with traditional SGS models. When applied on coarser meshes, the model maintains accuracy, as evidenced by agreement in the ratio of subgrid to total kinetic energy. These findings support the potential of this machine-learning-based model as a physics-aware, scalable modelling approach for complex turbulent flows. [Display omitted] •ML–LES integration using scale-adaptive and mixed modelling: Introduces SAM-SGS, a model that learns enstrophy dynamics and energy cascade.•Encoder–decoder architecture improves LES performance: Uses skip connections to boost interpretability, gradient flow, and spatial detail.•Scalable and generalizable AI for offshore LES: SAM-SGS adapts to flow variations, enabling robust LES in wind farm applications.
ISSN:0045-7930
DOI:10.1016/j.compfluid.2025.106823