Mesh-based Super-resolution of Detonation Flows with Multiscale Graph Transformers

2025-11-15

AI Summary

Accurate super-resolution reconstruction of detonation flow fields on complex geometries and non-uniform/unstructured grids remains challenging due to strong nonlinearities, multiscale physics, and long-range physical dependencies. Method: This paper proposes a Multi-scale Graph Transformer (MSGT), integrating graph neural networks with Transformer architectures. MSGT employs a dual-level graph representation—local element-wise and neighborhood-based—combined with spectral-element discretization and tokenized feature extraction to effectively capture long-range physical interactions while preserving critical reactive-flow features. Contribution/Results: To the best of our knowledge, this is the first application of multi-scale graph transformers to reactive flow field super-resolution. Evaluated on two-dimensional hydrogen–air detonation flows, MSGT achieves high-fidelity reconstructions, significantly outperforming conventional interpolation methods. The method demonstrates strong generalizability across varying grid resolutions and geometries, indicating substantial potential for practical engineering deployment.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Super-resolution flow reconstruction using state-of-the-art data-driven techniques is valuable for a variety of applications, such as subgrid/subfilter closure modeling, accelerating spatiotemporal forecasting, data compression, and serving as an upscaling tool for sparse experimental measurements. In the present work, a first-of-its-kind multiscale graph transformer approach is developed for mesh-based super-resolution (SR-GT) of reacting flows. The novel data-driven modeling paradigm leverages a graph-based flow-field representation compatible with complex geometries and non-uniform/unstructured grids. Further, the transformer backbone captures long-range dependencies between different parts of the low-resolution flow-field, identifies important features, and then generates the super-resolved flow-field that preserves those features at a higher resolution. The performance of SR-GT is demonstrated in the context of spectral-element-discretized meshes for a challenging test problem of 2D detonation propagation within a premixed hydrogen-air mixture exhibiting highly complex multiscale reacting flow behavior. The SR-GT framework utilizes a unique element-local (+ neighborhood) graph representation for the coarse input, which is then tokenized before being processed by the transformer component to produce the fine output. It is demonstrated that SR-GT provides high super-resolution accuracy for reacting flow-field features and superior performance compared to traditional interpolation-based SR schemes.

Problem

• Super-resolving detonation flows using multiscale graph transformers
• Reconstructing reacting flows on unstructured meshes with transformers
• Enhancing resolution of complex flow fields beyond interpolation methods

Innovation

• Multiscale graph transformer for super-resolution
• Graph-based representation for complex geometries
• Transformer captures long-range dependencies in flow