Dewi Indira, Fitri Muzayyanah, Rifky Fauzi, Wasinton Simanjuntak, Yandri Yandri, Fakhrony Sholahudin Rohman, Sudibyo Sudibyo, Benadict Rakesh, Anis Tatik Maryani, Yudha Gusti Wibowo
Hospital wastewater contains a complex mixture of pollutants, including biological, chemical, and pharmaceutical contaminants, which necessitates effective treatment strategies. This study investigates the efficiency of electrocoagulation for treating hospital wastewater while employing predictive modeling techniques, including feedforward neural networks (FFNN), neural Wiener (NW), neural Hammerstein (NH), and neural Hammerstein–Wiener (NHW) models. The electrocoagulation process was conducted using aluminum and carbon electrodes, with varying voltage levels (5 V, 10 V, and 15 V) and treatment durations (30, 60, 90, and 120 min). Key water quality parameters, including turbidity, biochemical oxygen demand (BOD), chemical oxygen demand (COD), Escherichia coli, and coliform bacteria, were analyzed before and after treatment. Results demonstrated that increasing voltage and contact time significantly enhanced pollutant removal, with the highest removal efficiencies observed at 15 V and 120 min. Electrocoagulation effectively reduced turbidity, BOD, and COD levels while achieving substantial microbial inactivation. The predictive models successfully captured electrocoagulation dynamics, with the neural Hammerstein–Wiener model exhibiting the highest accuracy (root mean square error [RMSE]: 0.0399, weighted mean absolute percentage error [WMAPE]: 0.0665). These findings suggest that electrocoagulation, coupled with advanced modeling techniques, provides a sustainable and efficient hospital wastewater treatment approach. Future research should focus on optimizing operational parameters, integrating hybrid treatment methods, and developing real-time monitoring systems to enhance treatment efficiency and cost-effectiveness. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
Doctoral Program of Environmental Science, Department of Postgraduate Program, Universitas Lampung, Lampung, Indonesia; Department of Mathematics, Faculty of Science, Institut Teknologi Sumatera, Lampung Selatan, Indonesia; Department of Chemistry, Universitas Lampung, Lampung, Indonesia; Process Systems Engineering Centre (PROSPECT), Research Institute of Sustainable Environment (RISE), Universiti Teknologi Malaysia, UTM Johor Bahru, Johor, 81310, Malaysia; Research Center for Mining Technology, National Research and Innovation Agency (BRIN), South Lampung, 35352, Indonesia; Council of Scientific and Industrial Research, Institute of Minerals and Materials Technology, Govt.of India, Bhubaneswar, India; Postgraduate Program of Environmental Science, Universitas Jambi, Jambi, Indonesia; Department of Mining Engineering, Faculty of Technologi Industry, Institut Teknologi Sumatera, Jl. Terusan Ryacudu, Lampung, Way Hui, 35365, Indonesia; Center for Green and Sustainable Materials, Institut Teknologi Sumatera, Lampung, Indonesia