A full order, reduced order and machine learning model pipeline for efficient prediction of reactive flows

TL;DR

This paper introduces an integrated pipeline combining full order simulations, reduced order models, and machine learning to efficiently predict chemical conversion rates in reactive flows across different transport regimes.

Contribution

It presents a novel combined approach leveraging simulation data, reduced basis models, and kernel machine learning for fast, reliable reactive flow predictions.

Findings

Effective prediction of chemical conversion rates.

Integration of reduced order models with machine learning.

Applicable across various transport regimes.

Abstract

We present an integrated approach for the use of simulated data from full order discretization as well as projection-based Reduced Basis reduced order models for the training of machine learning approaches, in particular Kernel Methods, in order to achieve fast, reliable predictive models for the chemical conversion rate in reactive flows with varying transport regimes.