Machine learning algorithms prediction of methyl orange removal by Fenton oxidation process

Abstract

Fenton oxidation, an advanced oxidation process (AOP), effectively mineralizes azo dyes, mitigating their environmental impact. The Fenton oxidation process (Fe2⁺/H₂O₂) was employed for the degradation of methyl orange (MO) under varying operational conditions, with its efficiency assessed through chemical oxygen demand (COD) analysis. This study aims to develop predictive models for MO degradation efficiency using four machine learning (ML) algorithms: Gaussian process regression (GPR), multilayer perceptron (MLP), decision tree (DT), and support vector regression (SVR). These models were developed and validated using 42 experimental data points obtained under controlled conditions. Experimental findings revealed a 99% COD removal at an initial MO concentration of 125 mg/L, optimized at pH 3.5, [Fe2⁺] = 25 mg/L, reaction time = 90 min, and a molar ratio of [H₂O₂]/[MO] = 42.5. The predictive accuracy of the ML models was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). The GPR model demonstrated the highest predictive performance (R2 = 0.970), followed by DT (R2 = 0.964). The MLP and SVM models exhibited slightly lower predictive capacities, with R2 values of 0.946 and 0.910, respectively. Feature importance analysis indicated that reaction time was the most significant parameter influencing COD removal, underscoring the necessity of its optimization in practical applications. The integration of ML-based predictive modeling with AOPs provides a robust approach for enhancing wastewater treatment efficiency. The outcomes of this study hold particular relevance for water reuse applications in arid and semiarid regions, where effective pollutant removal is critical for sustainable water resource management