Super-resolution of turbulent reacting flows on complex meshes using graph neural networks

TL;DR

This paper introduces a graph neural network-based method for super-resolution of turbulent reacting flows on complex, unstructured meshes, enabling accurate reconstruction of small-scale features from coarse data.

Contribution

The study develops a GNN-based approach specifically designed for unstructured meshes, extending super-resolution techniques to complex geometries in turbulent flow simulations.

Findings

Effective reconstruction of small-scale turbulent structures.

Demonstrated accuracy on structured non-uniform and unstructured meshes.

Potential to improve coarse-grained simulation fidelity.

Abstract

State-of-the-art deep learning models have been extensively utilized to reconstruct small-scale structures from coarse-grained data in turbulent flows. However, their application has predominantly been restricted to structured uniform meshes, limiting their applicability to data associated with complex geometries that are typically simulated on structured non-uniform or unstructured meshes. Machine learning (ML) models based on graph neural networks (GNNs), known for their ability to process unstructured data, offer a promising alternative. In this study, we leverage the inherent flexibility of GNNs featuring message passing layers to develop a methodology for reconstructing unresolved small-scale structures from low-resolution data on complex meshes. The accuracy of the proposed approach is demonstrated using two cases: a reacting channel flow on a structured non-uniform mesh, and a reacting hydrogen fueled internal combustion (IC) engine featuring an unstructured mesh. Evaluation of results based on visual agreement, statistical metrics, and cumulative error reduction indicates the effectiveness of the method in accurately reconstructing fine-scale features. Overall, this study provides a pathway for integrating data-driven small-scale reconstruction and subgrid-scale modeling to enhance the accuracy of coarse-grained simulations on complex meshes.