Advancing Reacting Flow Simulations with Data-Driven Models

TL;DR

This paper reviews how data-driven models, especially machine learning, can be integrated with physical models to improve simulations of reacting flows like combustion, emphasizing the importance of physical constraints and prior knowledge.

Contribution

It highlights open opportunities for applying data-driven reduced-order modeling in combustion, including feature extraction, manifold identification, and classification techniques.

Findings

Data-driven models enhance combustion simulations.

Physical constraints improve machine learning effectiveness.

Examples include feature extraction and manifold identification.

Abstract

The use of machine learning algorithms to predict behaviors of complex systems is booming. However, the key to an effective use of machine learning tools in multi-physics problems, including combustion, is to couple them to physical and computer models. The performance of these tools is enhanced if all the prior knowledge and the physical constraints are embodied. In other words, the scientific method must be adapted to bring machine learning into the picture, and make the best use of the massive amount of data we have produced, thanks to the advances in numerical computing. The present chapter reviews some of the open opportunities for the application of data-driven reduced-order modeling of combustion systems. Examples of feature extraction in turbulent combustion data, empirical low-dimensional manifold (ELDM) identification, classification, regression, and reduced-order modeling are provided.