Tree-based machine learning for predicting Neochloris oleoabundans biomass growth and biological nutrient removal from tertiary municipal wastewater

Abstract

Recently, computational models have been increasingly recognized as valuable tools for addressing key challenges in the operational performance of biological wastewater treatment facilities. In this study, tree-based machine learning approaches, such as decision tree regressor (DTR) and extra tree regressor (ETR), were developed to predict microalgae (Neochloris oleoabundans) biomass growth, culture pH, and nutrient removal efficacy (total nitrogen, TN and total phosphorus, TP) for the first time. The experimental data was obtained through a central composite design (CCD) matrix, and Bayesian optimization was applied to fine-tune the models’ hyperparameters. Model performance was evaluated using indicators such as the coefficient of determination (R²), mean absolute error (MAE), and mean-squared error (MSE). The results showed comparable performance between the DTR and ETR models. For TN removal during testing, the R² values for DTR and ETR were 0.9262 and 0.9789, respectively, with DTR (MSE: 0.00895, MAE: 0.0615) and ETR (MSE: 0.00255, MAE: 0.0352) demonstrating reliable predictions. Overall, the ETR model outperformed DTR in predicting responses. The models' generalization capabilities were also assessed by introducing variations in environmental factors.