Modeling spinel oxide based-photocatalytic degradation of organic pollutants from industrial wastewater

Rapid population growth has resulted in rapid growth in industrialization to meet various human needs. As a result of this, huge volume of effluent is being generated from the industrial processes and released into the water bodies. These anthropogenic activities are often detrimental to human and aquatic lives. In this study, a modeling approach to evaluate the photocatalytic degradation of organic pollutants from industrial wastewater using spinel oxide is investigated. Four machine learning algorithms namely, linear regression, decision tree ensemble, medium Gaussian support vector machine, and exponential Gaussian process regression were employed. The parametric analysis of the predictors (particle size of the spinel oxides, the initial dye concentration, the amount of photocatalysts, the band gap, and the irradiation time) and the targeted output of the photocatalytic degradation efficiency shows that a non-linear relationship exists between the predictors and the targeted output. This was further confirmed by the linear regression model with R-2 of 0.220. Besides, the decision tree ensemble and medium Gaussian support vector machine regression offer poor performances in predicting the photocatalytic degradation efficiency as indicated by R-2 of 0.420 and 0.490, respectively. A superior performance in predicting the photocatalytic degradation efficiency was displayed by the exponential Gaussian process regression with R2 of 0.991.