Harnessing Avicennia Marina Leaves for Dye Contaminant Removal: An RSM and ANN-Based Study

This study examines the efficacy of Avicennia marina (AM) leaves as an environmentally sustainable biosorbent for the extraction of methylene blue (MB) dye from wastewater. A hybrid approach of Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) was implemented to assess, optimize, and forecast biosorption effectiveness across different operating parameters. The experimental design employed a Central Composite Design (CCD) methodology, focusing on critical parameters including pH, initial dye concentration, temperature, and biosorbent dosage. The ideal biosorption parameters were identified as a temperature of 44.3°C, pH 7.1, a biosorbent dosage of 0.3 grams, and an initial dye concentration of 48.4 mg/L, resulting in a maximum removal efficiency of 84.26%. The ANN model exhibited significant prediction accuracy, so confirming its appropriateness for predicting and enhancing intricate biosorption processes. The findings underscore that AM leaves constitute a cost-efficient, plentiful, and ecologically sustainable resource for wastewater treatment purposes. Furthermore, the amalgamation of RSM and ANN shown significant efficacy in process optimization and forecasting. These findings provide significant insights into the advancement of eco-friendly solutions for the treatment of dye-contaminated water. Subsequent study must prioritize the amplification of the procedure for industrial applications, the execution of ongoing system assessments, and the evaluation of the enduring environmental and economic ramifications of utilizing AM leaves as a biosorbent.