Machine learning methods for prediction of breakthrough curves in reactive porous media

TL;DR

This paper explores machine learning and tensor methods to efficiently predict breakthrough curves in reactive porous media, reducing computational costs in industrial and environmental applications.

Contribution

It demonstrates the effectiveness of Gaussian processes, neural networks, and cross approximation for predicting breakthrough curves in pore-scale reactive flow.

Findings

ML methods accurately predict breakthrough curves

Tensor methods offer computational efficiency

Applicable to catalytic filter simulations

Abstract

Reactive flows in porous media play an important role in our life and are crucial for many industrial, environmental and biomedical applications. Very often the concentration of the species at the inlet is known, and the so-called breakthrough curves, measured at the outlet, are the quantities which could be measured or computed numerically. The measurements and the simulations could be time-consuming and expensive, and machine learning and Big Data approaches can help to predict breakthrough curves at lower costs. Machine learning (ML) methods, such as Gaussian processes and fully-connected neural networks, and a tensor method, cross approximation, are well suited for predicting breakthrough curves. In this paper, we demonstrate their performance in the case of pore scale reactive flow in catalytic filters.