Prediction of hydroxyl radical exposure during ozonation using different machine learning methods with ozone decay kinetic parameters.

Journal: Water research
PMID:

Abstract

The abatement of micropollutants by ozonation can be accurately calculated by measuring the exposures of molecular ozone (O) and hydroxyl radical (OH) (i.e., ∫[O]dt and ∫[OH]dt). In the actual ozonation process, ∫[O]dt values can be calculated by monitoring the O decay during the process. However, calculating ∫[OH]dt is challenging in the field, which necessitates developing models to predict ∫[OH]dt from measurable parameters. This study demonstrates the development of machine learning models to predict ∫[OH]dt (the output variable) from five basic input variables (pH, dissolved organic carbon concentration, alkalinity, temperature, and O dose) and two optional ones (∫[O]dt and instantaneous ozone demand, IOD). To develop the models, four different machine learning methods (random forest, support vector regression, artificial neural network, and Gaussian process regression) were employed using the input and output variables measured (or determined) in 130 different natural water samples. The results indicated that incorporating ∫[O]dt as an input variable significantly improved the accuracy of prediction models, increasing overall R by 0.01-0.09, depending on the machine learning method. This suggests that ∫[O]dt plays a crucial role as a key variable reflecting the OH-yielding characteristics of dissolved organic matter. Conversely, IOD had a minimal impact on the accuracy of the prediction models. Generally, machine-learning-based prediction models outperformed those based on the response surface methodology developed as a control. Notably, models utilizing the Gaussian process regression algorithm demonstrated the highest coefficients of determination (overall R = 0.91-0.95) among the prediction models.

Authors

  • Dongwon Cha
    School of Chemical and Biological Engineering, Institute of Chemical Process (ICP), and Institute of Engineering Research, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea.
  • Sanghun Park
    School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, UNIST-gil 50, Ulsan 44919, Republic of Korea.
  • Min Sik Kim
    Department of Environmental Engineering, Jeonbuk National University, 567 Baekje-daero, Deokjin-gu, Jeonju-si, Jeonbuk-do 54896, Republic of Korea.
  • Jaesang Lee
    Center for Neuromorphic Engineering, Korea Institute of Science and Technology, Seoul 02792, Korea.
  • Yunho Lee
    School of Earth Sciences and Environmental Engineering, Gwangju Institute of Science and Technology (GIST), 123 Cheomdangwagi-ro, Buk-gu, Gwangju 61005, Republic of Korea.
  • Kyung Hwa Cho
    School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Eonyang-eup, Ulju-gun, Ulsan 689-798, Republic of Korea.
  • Changha Lee
    School of Chemical and Biological Engineering, Institute of Chemical Process (ICP), and Institute of Engineering Research, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea. Electronic address: leechangha@snu.ac.kr.