Predictive Optimization of Natural Coagulants Using Artificial Neural Networks: A Case Study with Moringa Oleifera Seed Extract

This study explores the application of Artificial Neural Networks (ANNs) for optimizing Moringa oleifera seed extract as a coagulant in wastewater treatment. Moringa oleifera is recognized for its eco-friendly and sustainable properties, with proteins that effectively aggregate and remove colloidal impurities. Traditional optimization techniques, such as Response Surface Methodology (RSM), have been applied to this natural coagulant but fail to model the complex, nonlinear interactions influencing coagulation efficacy. By leveraging the predictive capabilities of ANNs, this study aims to address the limitations of traditional methods, offering a more precise approach to optimizing coagulant dosage. Experimental results reveal that an optimal dosage of 0.02 g/100 mL achieves a turbidity reduction efficiency of 70.59%, with diminishing returns at higher concentrations. The ANN model demonstrates strong predictive performance, achieving a Root Mean Squared Error (RMSE) of 0.384 and Mean Absolute Error (MAE) of 0.312. This highlights the model's capability to capture nonlinear relationships between coagulant dosage and turbidity reduction. The findings underscore the potential of integrating ANNs with natural coagulants to develop scalable, sustainable, and cost-effective solutions for water treatment, particularly in resource-constrained settings.