Introducing machine learning model to response surface methodology for biosorption of methylene blue dye using Triticum aestivum biomass

Abstract

Abstract A major environmental problem on a global scale is the contamination of water by dyes, particularly from industrial effluents. Consequently, wastewater treatment from various industrial wastes is crucial to restoring environmental quality. Dye is an important class of organic pollutants that are considered harmful to both people and aquatic habitats. The textile industry has become more interested in agricultural-based adsorbents, particularly in adsorption. The biosorption of Methylene blue (MB) dye from aqueous solutions by the wheat straw (T. aestivum) biomass was evaluated in this study. The biosorption process parameters were optimized using the response surface methodology (RSM) approach with a face-centred central composite design (FCCCD). Using a 10 mg/L concentration MB dye, 1.5 mg of biomass, an initial pH of 6, and a contact time of 60 min at 25 °C, the maximum MB dye removal percentages (96%) were obtained. Artificial neural network (ANN) modelling techniques are also employed to stimulate and validate the process, and their efficacy and ability to predict the reaction (removal efficiency) were assessed. The existence of functional groups, which are important binding sites involved in the process of MB biosorption, was demonstrated using Fourier Transform Infrared Spectroscopy (FTIR) spectra. Moreover, a scan electron microscope (SEM) revealed that fresh, shiny particles had been absorbed on the surface of the T. aestivum following the biosorption procedure. The bio-removal of MB from wastewater effluents has been demonstrated to be possible using T. aestivum biomass as a biosorbent. It is also a promising biosorbent that is economical, environmentally friendly, biodegradable, and cost-effective.