Single and competitive dye adsorption onto chitosan-based hybrid hydrogels using artificial neural network modeling

Area of Science:

• Materials Science
• Environmental Science
• Chemical Engineering

Background:

• Wastewater treatment requires efficient methods for dye removal.
• Chitosan-based hydrogels offer potential for adsorbing organic pollutants.
• Modifications to hydrogels can enhance their adsorption capabilities.

Purpose of the Study:

• To synthesize and characterize various chitosan-based hybrid hydrogels.
• To evaluate the adsorption performance of these hydrogels for Acid Blue 9 and Allura Red AC dyes.
• To develop and validate an artificial neural network model for predicting dye adsorption capacity.

Main Methods:

• Synthesis of chitosan hydrogel (CH), CH-AC, SCH, SCH-AC, and SCH-CN.
• Adsorption experiments in single and binary dye systems.
• Characterization of hydrogels (e.g., porosity, functional groups).
• Development and training of an artificial neural network (ANN) using Levenberg-Marquardt back-propagation.

Main Results:

• Competitive adsorption was observed, reducing capacity in binary systems.
• SCH-CN exhibited the highest adsorption capacity for both dyes.
• The ANN model achieved high accuracy (R=0.9987, RMSE=0.0119) in predicting adsorption.
• The optimized ANN topology was 5-10-10-10-2.

Conclusions:

• Chitosan-based hybrid hydrogels, particularly SCH-CN, are effective adsorbents for textile dyes.
• Hydrogel modification enhances active sites and functional groups for improved dye interaction.
• ANN modeling provides a reliable tool for predicting dye adsorption efficiency in complex systems.