Congo red, a widely utilized dye in the textile industry, presents a significant threat to living organisms due to its carcinogenic properties and non-biodegradable nature. This study proposes a data-driven machine-learning approach to optimize biochar characteristics and environmental conditions to maximize the adsorption capacity of biochar for the removal of Congo red dye. Therefore, six machine learning models were trained and tested on a dataset containing eleven input parameters (related to biochar properties and environmental conditions) and adsorption capacity. The models were evaluated using performance metrics such as R-squared (R2), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). With the highest R2 (0.9785) and lowest RMSE (0.1357), Random Forest Regression (RF) outperformed other machine learning models. DT and XGB also performed well, achieving slightly lower R2 values of 0.9741 and 0.9577, respectively. The LR model performed the worst, with the lowest R2 (0.4575) and the highest RMSE (0.6821). Moreover, the reliability of these models was validated using a 10-fold cross-validation method. RF once again performed the best with an R2 value of 0.9762. Feature analysis revealed that the initial dye concentration relative to biochar dosage (C0), specific surface area (BET), and pore volume (PV) are the most significant factors affecting the dye adsorption capacity of biochar, while parameters such as carbon content (C), the oxygen and nitrogen to carbon molar ratio [(O + N)/C], and pore diameter (D) had minimal impact. This research demonstrates that machine learning models can accurately predict biochar’s contaminant adsorption capacity, enhancing wastewater treatment and promoting efficient, cost-effective environmental management.Graphical
Read full abstract