mlsanityData to 7 Oct 2026

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

arXiv 2603.01080 ↗First posted 1 Mar 2026physics.flu-dyn cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

19 of 39 references.

References · 19

  1. 2017Graph Attention Networkscited by 8,854
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  5. 2016Variational Graph Auto-Encoderscited by 1,373
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  8. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstructioncited by 150
  9. 2025PyG 2.0: Scalable Learning on Real World Graphscited by 49
  10. 2021Graph Neural Networks Accelerated Molecular Dynamicscited by 33
  11. 2022Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Networkcited by 22
  12. 2023Multiscale Graph Neural Network Autoencoders for Interpretable Scientific Machine Learningcited by 18
7 more
  1. 2020AI-assisted super-resolution cosmological simulationscited by 15
  2. 2024Mesh-based Super-Resolution of Fluid Flows with Multiscale Graph Neural Networkscited by 10
  3. 2021NekRS, a GPU-Accelerated Spectral Element Navier-Stokes Solvercited by 8
  4. 2024Single-snapshot machine learning for super-resolution of turbulencecited by 8
  5. 2024CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fieldscited by 8
  6. 2022Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Premixed Combustion and Engine-like Flame Kernel Direct Numerical Simulation Datacited by 5
  7. 2022Applying Physics-Informed Enhanced Super-Resolution Generative Adversarial Networks to Turbulent Non-Premixed Combustion on Non-Uniform Meshes and Demonstration of an Accelerated Simulation Workflowcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Modeling subgrid scale production rates on complex meshes using graph neural networkscited by 0
  2. 2026A graph neural network based chemical mechanism reduction method for combustion applicationscited by 0