Nanostructured functionalised sewage sludge- adsorbent: optimising wastewater remediation using ANN and RSM

Heavy metal pollution in industrial wastewater poses serious environmental challenges. This study investigates the optimization of heavy metal adsorption using Artificial Neural Networks (ANN) combined with Response Surface Methodology (RSM). It focuses on the adsorption capabilities of sewage sludge ash (SSA) for iron (Fe2+), manganese (Mn2+), chromium (Cr3+), and aluminium (Al3+). A Box-Behnken Design (BBD) with 25 experiments was created to evaluate three key parameters: temperature (25 – 45°C), solid load percentage (1 – 10%), and contact time (1 – 10 hours). The showed maximum removal efficiencies of 97% for Fe2+, 89% for Mn2+, 97% for Cr3+, and 92% for Al3+ in mono-metal solutions. The functionalised sewage sludge ash had a notable surface area of 7.79 m²/g before adsorption, thereby classifying it as a mesoporous material, which falls within the category of nanoporous material, thus reflecting on enhanced adsorption potential. The ANN-RSM model exhibited strong predictive capability, with an R² of approximately 0.95 and a root mean squared error (RMSE) of 0.086. Sensitivity analysis revealed temperature as the most significant factor affecting adsorption efficiency, followed by contact time and sorbent loading. This research underscores the effectiveness of combining ANN and RSM to optimize heavy metal remediation strategies in wastewater treatment.