Response Methodology Optimization and Artificial Neural Network Modeling for the Removal of Sulfamethoxazole Using an...

Area of Science:

• Environmental Science
• Water Treatment Technologies
• Chemical Engineering

Background:

• Antibiotic resistance is a growing global threat, necessitating effective water treatment methods.
• Conventional wastewater treatment struggles to remove emerging contaminants like pharmaceuticals.
• Ozone-electrocoagulation (O-EC) offers a synergistic approach for enhanced contaminant removal.

Purpose of the Study:

• To optimize and model the removal of sulfamethoxazole (SMX) using an ozone-electrocoagulation (O-EC) system.
• To identify key operational parameters influencing SMX removal efficiency.
• To evaluate the predictive capabilities of response surface methodology and artificial neural networks for the O-EC process.

Main Methods:

• Central composite design was employed for experimental optimization.
• Response surface methodology (RSM) was used to model and optimize parameters: current density, reaction time, pH, and ozone dose.
• Artificial neural network (ANN) modeling was utilized to predict SMX removal performance.

Main Results:

• Optimal conditions achieved 99.65% SMX removal: 33.2 A/m² current density, 37.8 min, pH 8.4, and 0.7 g/h ozone dose.
• RSM quadric model accurately predicted the removal process.
• ANN model demonstrated good agreement with experimental data; pH was the most influential factor.

Conclusions:

• The O-EC system is highly effective for removing sulfamethoxazole from aqueous solutions.
• Optimized O-EC parameters ensure efficient antibiotic removal, mitigating resistance spread.
• The study validates O-EC as a viable technology for pharmaceutical wastewater treatment.