Predictive Modeling of MB Adsorption on Activated Olive Stone Through Artificial Neural Networks

Abstract

The primary objective of this study was to evaluate the potential of activated olive stone (AOS), an organic waste material, for adsorbing Methylene Blue (MB) dye from aqueous solutions and to develop a predictive model using Artificial Neural Networks (ANNs). This research aimed to explore AOS as an eco-friendly and cost-effective adsorbent for wastewater treatment, emphasizing its potential for large-scale applications. Additionally, the study sought to enhance the understanding of how various factors-such as pH, contact time, and adsorbent dosage-affect the adsorption process and to optimize the conditions for maximum dye removal efficiency. The material's structure and functional groups were analyzed using Fourier Transform Infrared (FTIR) spectroscopy. Adsorption experiments conducted in a batch system demonstrated a removal efficiency of 93% under optimal conditions, with a maximum adsorption capacity of 446 mg/g for MB. The optimal conditions were identified as pH 7, a contact time of 30 min, 10 g/L of AOS, and an MB concentration of 250 mg/L. To better understand the influence of various parameters on MB adsorption, an ANN model was developed. The model analysis revealed a strong correlation coefficient (R2) of 91%, indicating that the model could reliably predict MB removal. Overall, the study highlights the promising potential of AOS as an adsorbent for wastewater treatment and demonstrates the effectiveness of ANN models for optimizing adsorption processes.