Enhancing municipal solid waste leachate treatment efficiency: AI-based prediction of electrocoagulation/flocculation recovery using iron electrodes

• Published in: Environmental technology 2024-12, Vol.45 (28), p.6184-6199
• Main Authors: Igwegbe, Chinenye Adaobi, Onyechi, Chinonso Chukwudi, Białowiec, Andrzej, Onukwuli, Okechukwu Dominic
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial Intelligence; Artificial neural networks; Electrocoagulation; Electrocoagulation - methods; electrocoagulation flocculation; Electrodes; Electrolysis; Energy conservation; Energy costs; environmental engineering; Error analysis; Flocculation; Impact analysis; Iron; Iron - chemistry; Leachates; Modelling; Multilayer perceptrons; Multilayers; Municipal leachate; Municipal solid waste; Municipal waste management; Neural networks; Neural Networks, Computer; Parameter identification; Pollutants; Predictions; Process parameters; Reduction (electrolytic); Solid Waste - analysis; Solid wastes; Statistical analysis; Statistical models; Temperature requirements; Turbidity; Waste Disposal, Fluid - methods; Wastewater - chemistry; Water Pollutants, Chemical - chemistry; Water Purification - methods; Water quality
• ISSN: 0959-3330; 1479-487X; 1479-487X
• DOI: 10.1080/09593330.2024.2328659

This study addresses a gap in municipal leachate (MUPL) treatment by introducing a pioneering application of artificial intelligence (AI) in the electrocoagulation/electroflocculation (EC/EF) process utilizing iron electrodes. The overarching aim is to demonstrate the efficacy of AI, particularly a multi-layer perceptron (MLP)-based feed-forward artificial neural network (ANN) incorporating the Levenberg-Marquardt (LMb) algorithm, in predicting and optimizing EC/EF outcomes for turbidity (TDY) removal. The research methodology involved experimentation and robust ANN data modeling. The significance of this work emerges from the successful integration of AI, showcasing its potential in advancing wastewater, demonstrated through a strong positive correlation (0.994) between the ANN model predictions and experimental outcomes. The study achieves a remarkable 99.4% TDY removal at an electrolysis time of 10 min and contributes valuable insights into the critical parameters influencing the EC/EF process. Results from the ANN modeling exhibit high predictive accuracy, supported by elevated R-squared values and minimal mean square error. Statistical analyses underscore the significance of key process parameters, highlighting the influential roles of current intensity and settling time. The study emphasized the favourable impact of maintaining an acidic pH range, as it reduced electrostatic repulsion between particles, facilitating pollutant agglomeration, and identified electrolysis time as a key factor in enhancing treatment efficiency, supported by a strong positive correlation between electrolysis time and TDY reduction. Energy cost savings were realized by not requiring temperature elevation. Achieving a 99.4% TDY removal translates to substantial reductions in other pollutants present in the MUPL, thereby elevating water quality and ensuring compliance.