Machine learning to predict plasma-based CO 2 conversion in dielectric barrier discharge reactors

Green Chemistry 2026 Open access

Read full text
Authors: Jiayin Li, Xinpei Lu, Pranav Arun, Jing Xu, Fausto Gallucci, Sirui Li, Annemie Bogaerts
DOI: 10.1039/d6gc01077f
Cited by: 1
References: 86

Abstract

conversion estimates. SHapley Additive exPlanations (SHAP) analysis further identified flow rate and power as the dominant input features, collectively accounting for 61%-71% of the model's predictions. This work establishes a robust and interpretable framework while quantifying the generalizability of ML models in heterogeneous data environments, offering a practical tool to accelerate plasma-based gas conversion optimization.

Fields of Study & Subjects

Plasma Applications and Diagnostics Plasma and Flow Control in Aerodynamics Aerosol Filtration and Electrostatic Precipitation

Publication details

Journal / source
Green Chemistry
Publisher
Royal Society of Chemistry (RSC)
Volume
28
Issue
23
Pages
9804–9821
Publication date
1 January 2026
Language
EN