analiza aiqbench
This research introduces a novel graph transformer architecture designed to super-resolve complex reacting flows, specifically addressing the challenges of detonation propagation in unstructured grids. By leveraging long-range dependencies within flow-field representations, the model achieves high accuracy in reconstructing fine-scale features from coarse inputs, outperforming traditional interpolation methods. This advancement offers significant potential for accelerating spatiotemporal forecasting and improving subgrid closure modeling in computational fluid dynamics.
Mesh-based Super-resolution of Multiscale Detonation Flows with Graph Transformers
arXiv:2511.12041v4 Announce Type: replace-cross 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 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 + 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.
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 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 + 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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2511.12041 [cs.LG]
(or arXiv:2511.12041v4 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2511.12041 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 280 cuvinte
Subiecte conexe
Extreme-Scale Super-Resolution of Homogeneous Turbulence from a Single Realization
arXiv · 15 oct. 2026
High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics
arXiv · 15 oct. 2026
CLIMB-flow: Coupled Linear Inverse posterior sampling via Multiscale-Based flow
arXiv · 30 sept. 2026
Attention-guided super-resolution of 4D flow MRI in carotid arteries
arXiv · 7 sept. 2026