Reduced graph-based representations of detonation-containing flows
Abstract
A graph neural network (GNN)-based autoencoder is leveraged to produce reduced latent graph representations of detonation-containing flows. In a two-dimensional hydrogen-air channel configuration with a uniform fuel-air mixture, it was found that latent graphs with effective resolutions of twice the induction length are capable of reconstructing both the wavefront and the post-shock region of the cellular detonation wave structure. Extrapolation studies using stratified and three-dimensional detonation configurations revealed an intrinsic property of GNN-based reconstruction from reduced latent graphs -- a representational hierarchy, rooted in the local nature of message passing, that tends to prioritize features at the detonation front (i.e., the wavefront profile and triple points) over the downstream deflagrative regions. In particular, it was found that at a fixed ambient condition, the information contained in uniform two-dimensional detonations was sufficient to reconstruct the wavefront structure of both stratified and three-dimensional detonations. Overall, this work demonstrates the utility of GNNs for both reduction and information overlap extraction in detonation-containing flows, opening promising pathways for accelerated simulations of these flows.
Related
- Improving Reduced-Order Rotating Detonation Engine Models with Data Assimilation and Machine Learning
- A domain decomposition non-intrusive reduced order model for turbulent flows
- A reduced order model for turbulent flows in the urban environment using machine learning
- ROSE: Deep Learning exchange-correlation functional from reduced density-matrix representations
- A Comparative Study of Finite-Volume-based Coupled and Segregated Reduced-Order Models for Incompressible Flows in Parametrized Domains
BibTeX
@misc{elilarasan2026reduced,
title = {{Reduced graph-based representations of detonation-containing flows}},
author = {Sinaendhran Pujali Elilarasan and Michael Ullman and Shivam Barwey},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28486},
eprint = {2610.28486},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28486},
}
RIS
TY - UNPB
TI - Reduced graph-based representations of detonation-containing flows
AU - Sinaendhran Pujali Elilarasan
AU - Michael Ullman
AU - Shivam Barwey
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28486
UR - https://arxiv.org/abs/2610.28486
AB - A graph neural network (GNN)-based autoencoder is leveraged to produce reduced latent graph representations of detonation-containing flows. In a two-dimensional hydrogen-air channel configuration with a uniform fuel-air mixture, it was found that latent graphs with effective resolutions of twice the induction length are capable of reconstructing both the wavefront and the post-shock region of the cellular detonation wave structure. Extrapolation studies using stratified and three-dimensional detonation configurations revealed an intrinsic property of GNN-based reconstruction from reduced latent graphs -- a representational hierarchy, rooted in the local nature of message passing, that tends to prioritize features at the detonation front (i.e., the wavefront profile and triple points) over the downstream deflagrative regions. In particular, it was found that at a fixed ambient condition, the information contained in uniform two-dimensional detonations was sufficient to reconstruct the wavefront structure of both stratified and three-dimensional detonations. Overall, this work demonstrates the utility of GNNs for both reduction and information overlap extraction in detonation-containing flows, opening promising pathways for accelerated simulations of these flows.
ER -