Melamine-Derived MgO/AC Nanocomposite for Efficient Dye Removal: Integrating RSM and Machine Learning Modeling

Area of Science:

• Materials Science
• Environmental Chemistry
• Nanotechnology

Background:

• Wastewater contamination by dyes like methylene blue (MB) poses significant environmental challenges.
• Development of efficient and cost-effective adsorbents is crucial for dye removal.
• Activated carbon (AC) is a common adsorbent, but its performance can be enhanced through modification.

Purpose of the Study:

• To synthesize and evaluate a melamine-derived MgO/activated carbon (MgO/AC) nanocomposite for MB removal.
• To investigate the adsorption mechanisms and optimize operating parameters for MB removal.
• To model the adsorption process using machine learning techniques.

Main Methods:

• Synthesis of MgO/AC nanocomposite using melamine as a precursor.
• Characterization of the adsorbent's properties, including BET surface area.
• Experimental determination of MB removal efficiency under various conditions.
• Optimization of parameters using Response Surface Methodology (RSM).
• Application of machine learning models, including Adaptive Neuro-Fuzzy Inference System (ANFIS), for adsorption modeling.

Main Results:

• The MgO/AC nanocomposite demonstrated high MB removal efficiency (94.72%) despite a low BET surface area (15.19 m²/g).
• Chemically active sites from MgO nanoparticles and nitrogen functionalities enhanced dye-adsorbent interactions.
• RSM successfully optimized operating parameters for efficient MB removal.
• ANFIS model showed excellent predictive performance (R² = 0.981) for the adsorption process.

Conclusions:

• Melamine-derived MgO/AC is a highly efficient adsorbent for methylene blue removal from aqueous solutions.
• The integrated experimental and machine learning approach provides a robust framework for adsorbent evaluation.
• This nanocomposite shows significant potential for practical application in dye-contaminated wastewater treatment.