With the global population increasing and water scarcity becoming a pressing issue worldwide, wastewater treatment has emerged as a crucial solution to meet growing water demands. Wastewater treatment plants (WWTPs) play a vital role in this regard, and the integration of new technologies, such as Machine Learning (ML), holds immense potential for their optimization. This study focuses on evaluating and comparing the performance of four ML regressors - Light Gradient Boosting regressor (LGBM), Random Forest regressor (RF), Support Vector Regressor (SVR), and Ridge Regression - in predicting Total Nitrogen (TN) concentration in a WWTP. The results indicate that the Random Forest regressor outperformed the other algorithms, demonstrating superior performance in correlation coefficient (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). These findings highlight the efficacy of the Random Forest regressor as a valuable tool for accurate TN concentration prediction in WWTPs. By leveraging ML techniques, WWTPs can enhance operational efficiency and contribute to sustainable water management, addressing the global challenge of water scarcity.