Citation

Zahra, Ayesha and Foo, Yee Loo (2025) AI-Driven Optimization of Advanced Oxidation Processes in Wastewater Treatment Using Synthetic Data Generation. In: 2025 Multimedia University Engineering Conference, MECON 2025, 21 July 2025 - 23 July 2025, Cyberjaya, Malaysia.

Text IEEE Xplore Full-Text PDF_21.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Wastewater treatment plants protect water sources by removing harmful contaminants. Conventional methods like sedimentation, filtration, and activated sludge are effective for suspended solids and biodegradable matter but struggle with persistent pollutants such as pharmaceutical byproducts, pesticides, and industrial chemicals. Advanced Oxidation Processes (AOPs) offer a solution by using highly reactive hydroxyl radicals (OH) or ultraviolet (UV) rays to fully degrade pollutants into harmless substances like water and carbon dioxide. However, optimizing these non-linear chemical reactions is complex. Artificial Intelligence (AI) and Machine Learning (ML) can optimize AOPs by analyzing large datasets and predicting optimal parameters such as oxidant dosage, Ultraviolet (UV) intensity, and reaction time. A key challenge is the lack of reliable data for training. To address this, our research employed ALVI’s synthetic data generator, which uses a Markov chain-based approach to replicate the non-linear dynamics of wastewater treatment more accurately than traditional imputation methods. The integration of synthetic and real data enhanced model performance, achieving an average 8% increase in coefficient of determination (R²) values in Artificial Neural Network (ANN). This significantly improves AOP optimization, highlighting the transformative potential of AI in environmental protection.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine learning, synthetic data
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	17 Mar 2026 06:26
Last Modified:	17 Mar 2026 06:26
URII:	http://shdl.mmu.edu.my/id/eprint/15486

Downloads

Edit (login required)