Predicting adsorptive removal of chlorophenol from aqueous solution using artificial intelligence based modeling...

Area of Science:

• Environmental Science
• Chemical Engineering
• Data Science

Background:

• 2-chlorophenol (CP) is a common pollutant in aqueous solutions.
• Coconut shell carbon (CSC) is a potential adsorbent for CP removal.
• Predictive modeling is crucial for optimizing adsorption processes.

Purpose of the Study:

• Develop and evaluate AI-based models for predicting CP adsorption by CSC.
• Investigate the influence of operational variables (pH, concentration, temperature, time) on adsorption.
• Compare the performance of different nonlinear models.

Main Methods:

• Factorial design with 640 batch experiments.
• Application of five nonlinear models: Radial Basis Function Network (RBFN), Multilayer Perceptron Network (MLPN), Generalized Regression Neural Network, Support Vector Machines, and Gene Expression Programming.
• Brock-Dechert-Scheimkman (BDS) statistics for nonlinearity assessment.

Main Results:

• Experimental data exhibited strong nonlinearity.
• All constructed models demonstrated satisfactory performance.
• RBFN and MLPN models outperformed other models in predicting CP adsorption.
• Sensitivity analysis indicated contact time and solution pH as the most influential factors.

Conclusions:

• AI models, particularly RBFN and MLPN, can effectively capture the nonlinearity in CP adsorption data.
• These models offer robust predictive capabilities for optimizing CP removal using CSC.
• The findings support the use of AI for designing efficient water treatment processes.