Prediction of Oxidation Reduction Potential (ORP) in Sewage Wastewater using Phytoremediation Process and Machine Learning Techniques

The emergence and integration of smart technologies in water and wastewater treatment processes has a play a significant role in preservation of water quality. Wastewater treatment by floating wetlands fits the description of sustainable, cost effective and eco-friendly methods that could protect freshwater resources which are deteriorating due to severe industrial, mining, and agricultural activities The present paper evaluated the performance of machine learning algorithms; Boosted Regression Tree, Hybrid Neuro-Fuzzy, and Wide Neural Network in predicting oxidation reduction potential (ORP) during phytoremediation of wastewater. The prediction accuracy of 18.63%, 8.87%, and 8.76% was obtained for boosted regression tree, hybrid neuro-fuzzy, and wide neural network, respectively. The study suggests that integrating advanced machine learning models not only improves predictive capabilities but also aids in decision-making regarding the suitability of treated wastewater for various applications, thus advancing environmental sustainability efforts. This research envisages that the machine learning algorithms employed can rightly predict the ORP of remediated wastewater to decide its level of portability. Thus, the machine learning models have shown very good prediction and optimization performances demonstrating artificial intelligence models as a powerful tool for achieving great success in the applications of wastewater treatment fields. This study recommend government in collaboration with environmental agencies, and industry stakeholders should embrace advanced smart technologies and encourage the integration of phytoremediation system in sewage treatment plants