Physics-Informed Latent Neural ODEs for Reduced-Order Modeling of Hydrogen, Ammonia, and Methane Combustion Kinetics
Abstract
Detailed chemical kinetic mechanisms are computationally expensive in reacting-flow simulations because of their high dimensionality and numerical stiffness. We develop an end-to-end physics-informed autoencoder neural ordinary differential equation (PI-AE-NODE) framework in which an encoder compresses the thermochemical state into a low-dimensional latent space, a Neural ODE advances it continuously in time, and a decoder reconstructs the temperature and all species mass fractions. Elemental conservation, mass conservation, and enthalpy consistency are embedded in the training objective. The framework is applied to H2/air, NH3/air, and CH4/air autoignition using detailed mechanisms of increasing size and complexity, which are represented accurately with only a few latent variables. Compared with an otherwise identical data-driven model, the physical constraints improve ignition delay prediction and conservation behaviour. The models reproduce major and intermediate species evolution at both training and unseen conditions, and their latent dynamics permit efficient explicit integration, with the computational advantage over the detailed mechanisms increasing with mechanism size.
Related
- Parameter Recovery and Noise Sensitivity of Physics-Informed Neural Networks for Michaelis–Menten Kinetics: A Benchmark Against Classical Nonlinear Least Squares
- Beyond white- and black-box modeling tools in optical communications and optical computing: physics-informed data-driven modeling
- Temperature-Dependent Multiphysics Modeling of Additive Friction Stir Deposition Using Multi-Task Coupled Physics-Informed Neural Networks
- A Scoping Review of Physics Informed Machine Learning for Wave Propagation Modeling in Seismology
- Physics-Informed Residual Deep Learning for Constitutive Modeling of Hot Deformation and Dynamic Recrystallization in a Mo-Rich α+β Titanium Alloy
BibTeX
@misc{patel2026physicsinformed,
title = {{Physics-Informed Latent Neural ODEs for Reduced-Order Modeling of Hydrogen, Ammonia, and Methane Combustion Kinetics}},
author = {Jay Patel and Shubhangi Bansude},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.42016},
eprint = {2610.42016},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.42016},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Physics-Informed Latent Neural ODEs for Reduced-Order Modeling of Hydrogen, Ammonia, and Methane Combustion Kinetics
AU - Jay Patel
AU - Shubhangi Bansude
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.42016
UR - https://arxiv.org/abs/2610.42016
AB - Detailed chemical kinetic mechanisms are computationally expensive in reacting-flow simulations because of their high dimensionality and numerical stiffness. We develop an end-to-end physics-informed autoencoder neural ordinary differential equation (PI-AE-NODE) framework in which an encoder compresses the thermochemical state into a low-dimensional latent space, a Neural ODE advances it continuously in time, and a decoder reconstructs the temperature and all species mass fractions. Elemental conservation, mass conservation, and enthalpy consistency are embedded in the training objective. The framework is applied to H_2/air, NH_3/air, and CH_4/air autoignition using detailed mechanisms of increasing size and complexity, which are represented accurately with only a few latent variables. Compared with an otherwise identical data-driven model, the physical constraints improve ignition delay prediction and conservation behaviour. The models reproduce major and intermediate species evolution at both training and unseen conditions, and their latent dynamics permit efficient explicit integration, with the computational advantage over the detailed mechanisms increasing with mechanism size.
ER -