On the Performance of Machine Learning Methods for Breakthrough Curve Prediction
This work addresses the challenge of monitoring reactive flows in porous media for technical and environmental applications, but it appears incremental as it applies existing methods to a specific domain without novel breakthroughs.
The authors tackled the problem of predicting breakthrough curves (outlet concentration over time) in reactive porous media flows by applying several machine learning methods to parameters like Damköhler and Peclet numbers, achieving results for both one-dimensional and three-dimensional cases without specifying concrete performance numbers.
Reactive flows are important part of numerous technical and environmental processes. Often monitoring the flow and species concentrations within the domain is not possible or is expensive, in contrast, outlet concentration is straightforward to measure. In connection with reactive flows in porous media, the term breakthrough curve is used to denote the time dependency of the outlet concentration with prescribed conditions at the inlet. In this work we apply several machine learning methods to predict breakthrough curves from the given set of parameters. In our case the parameters are the Damköhler and Peclet numbers. We perform a thorough analysis for the one-dimensional case and also provide the results for the three-dimensional case.