Machine learning analysis to interpret the effect of the photocatalytic reaction rate constant (k) of semiconductor-based photocatalysts on dye removal
Published in Journal of Hazardous Materials, 2023
Recommended citation: Kim, C. M., Jaffari, Z. H., Abbas, A., Chowdhury, M. F., & Cho, K. H. (2023). Machine learning analysis to interpret the effect of the photocatalytic reaction rate constant (k) of semiconductor-based photocatalysts on dye removal. Journal of Hazardous Materials, 132995. https://doi.org/10.1016/j.jhazmat.2023.132995
This paper involves modeling removal of dye from wastewater using photocatalysis. The predictors consisted of 38 parameters ranging from experimental to physical parameters which can affect the reation rate constant which was used as target variable. We compared prediction performance of 34 machine learning algorithms. Prior to that a comprehensive feature selection method (Boruta-SHAP) was applied to filter the predictors. The best machine learning algorithm was interpreted using model-agnostic interpretation method (SHAP). The interaction effect of various predictors onto reaction rate constant was analyzed using SHAP interaction plots.