Evaluation of machine learning models for predicting TiO2 photocatalytic degradation of air contaminants

Abstract

Abstract The escalation of global urbanization and industrial expansion has resulted in an increase in the emission of harmful substances into the atmosphere. Evaluating the effectiveness of titanium dioxide (TiO2) in photocatalytic degradation through traditional methods is resource-intensive and complex due to the detailed photocatalyst structures and the wide range of contaminants. Therefore in this study, recent advancements in machine learning (ML) are used to offer data-driven approach using thirteen machine learning techniques namely XG Boost (XGB), decision tree (DT), lasso Regression (LR2), support vector regression (SVR), adaBoost (AB), voting Regressor (VR), CatBoost (CB), K-Nearest Neighbors (KNN), gradient boost (GB), random Forest (RF), artificial neural network (ANN), ridge regression (RR), linear regression (LR1) to address the problem of estimation of TiO2 photocatalytic degradation rate of air contaminants. The models are developed using literature data and different methodical tools are used to evaluate the developed ML models. XGB, DT and LR2 models have high R2 values of 0.93, 0.926 and 0.926 in training and 0.936, 0.924 and 0.924 in test phase. While ANN, RR and LR models have lowest R2 values of 0.70, 0.56 and 0.40 in training and 0.62, 0.63 and 0.31 in test phase respectively. XGB, DT and LR2 have low MAE and RMSE values of 0.450 min-1/cm2, 0.494 min-1/cm2 and 0.49 min-1/cm2 for RMSE and 0.263 min-1/cm2, 0.285 min-1/cm2 and 0.29 min-1/cm2 for MAE in test stage. XGB, DT, and LR2 have 93% percent errors within 20% error range in training phase. XGB has 92% and DT, and LR2 have 94% errors with 20% range in test phase. XGB, DT, LR2 models remained the highest performing models and XGB is the most robust and effective in predictions. Feature importances reveal the role of input parameters in prediction made by developed ML models. Dosage, humidity, UV light intensity remain important experimental factors. This study will impact positively in providing efficient models to estimate photocatalytic degradation rate of air contaminants using TiO2.

Keywords

• TiO2
• Photocatalytic degradation
• Air contaminants
• Machine learning