A convolutional autoencoder and neural ODE framework for surrogate modeling of transient counterflow flames

2026-03-16

AI Summary

This work proposes a reduced-order modeling framework based on convolutional autoencoders (CAE) and neural ordinary differential equations (Neural ODE) to address the prohibitive computational cost of high-fidelity simulations of high-dimensional, unsteady two-dimensional counterflow flames. The approach extends the CAE-Neural ODE architecture to spatially resolved, non-uniform reactive flows for the first time, automatically capturing spatial correlations in the flow field to construct a physically consistent six-dimensional continuous latent manifold and efficiently model its temporal dynamics. The resulting model achieves over 10⁵-fold data compression while accurately reproducing the entire ignition process, flame propagation, and transition to a non-premixed state, with relative prediction errors for major species consistently below 2%.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

A novel convolutional autoencoder neural ODE (CAE-NODE) framework is proposed for a reduced-order model (ROM) of transient 2D counterflow flames, as an extension of AE-NODE methods in homogeneous reactive systems to spatially resolved flows. The spatial correlations of the multidimensional fields are extracted by the convolutional layers, allowing CAE to autonomously construct a physically consistent 6D continuous latent manifold by compressing high-fidelity 2D snapshots (256x256 grid, 21 variables) by over 100,000 times. The NODE is subsequently trained to describe the continuous-time dynamics on the non-linear manifold, enabling the prediction of the full temporal evolution of the flames by integrating forward in time from an initial condition. The results demonstrate that the network can accurately capture the entire transient process, including ignition, flame propagation, and the gradual transition to a non-premixed condition, with relative errors less than ~2% for major species. This study, for the first time, highlights the potential of CAE-NODE for surrogate modeling of unsteady dynamics of multi-dimensional reacting flows.

Problem

• surrogate modeling
• transient counterflow flames
• multi-dimensional reacting flows
• reduced-order model

Innovation

• convolutional autoencoder
• neural ODE
• reduced-order modeling
• transient reacting flows
• latent manifold