The PM2.5-bound polycyclic aromatic hydrocarbon behavior in indoor and outdoor environments, part II: Explainable prediction of benzo[a]pyrene levels

Andreja Stojić; Gordana Jovanović; Svetlana Stanišić; Snježana Herceg Romanić; Andrej Šoštarić; Vladimir Udovičić; Mirjana Perišić; Tijana Milićević

doi:10.1016/j.chemosphere.2021.133154

The PM_2.5-bound polycyclic aromatic hydrocarbon behavior in indoor and outdoor environments, part II: Explainable prediction of benzo[a]pyrene levels

Chemosphere. 2022 Feb:289:133154. doi: 10.1016/j.chemosphere.2021.133154. Epub 2021 Dec 3.

Authors

Andreja Stojić¹, Gordana Jovanović¹, Svetlana Stanišić², Snježana Herceg Romanić³, Andrej Šoštarić⁴, Vladimir Udovičić⁵, Mirjana Perišić¹, Tijana Milićević⁵

Affiliations

¹ Institute of Physics Belgrade, National Institute of the Republic of Serbia, University of Belgrade, 118 Pregrevica Street, 11000, Belgrade, Serbia; Singidunum University, 32 Danijelova Street, 11000, Belgrade, Serbia.
² Singidunum University, 32 Danijelova Street, 11000, Belgrade, Serbia. Electronic address: sstanisic@singidunum.ac.rs.
³ Institute for Medical Research and Occupational Health, 2 Ksaverska Cesta Street, PO Box 291, 10001, Zagreb, Croatia.
⁴ Institute of Public Health Belgrade, 54 Despota Stefana Street, 11000, Belgrade, Serbia.
⁵ Institute of Physics Belgrade, National Institute of the Republic of Serbia, University of Belgrade, 118 Pregrevica Street, 11000, Belgrade, Serbia.

PMID: 34871609
DOI: 10.1016/j.chemosphere.2021.133154

Abstract

Among the polycyclic aromatic hydrocarbons (PAH), benzo[a]pyrene (B[a]P) has been considered more relevant than other species when estimating the potential exposure-related health effects and has been recognized as a marker of carcinogenic potency of air pollutant mixture. The current understanding of the factors which govern non-linear behavior of B[a]P and associated pollutants and environmental processes is insufficient and further research has to rely on the advanced analytical approach which averts the assumptions and avoids simplifications required by linear modeling methods. For the purpose of this study, we employed eXtreme Gradient Boosting (XGBoost), SHapley Additive exPlanations (SHAP) attribution method, and SHAP value fuzzy clustering to investigate the concentrations of inorganic gaseous pollutants, radon, PM_2.5 and particle constituents including trace metals, ions, 16 US EPA priority PM_2.5-bound PAHs and 31 meteorological variables, as key factors which shape indoor and outdoor PM_2.5-bound B[a]P distribution in a university building located in the urban area of Belgrade (Serbia). According to the results, the indoor and outdoor B[a]P levels were shown to be highly correlated and mostly influenced by the concentrations of Chry, B[b]F, CO, B[a]A, I[cd]P, B[k]F, Flt, D[ah]A, Pyr, B[ghi]P, Cr, As, and PM_2.5 in both indoor and outdoor environments. Besides, high B[a]P concentration events were recorded during the periods of low ambient temperature (<12 °C), unstable weather conditions with precipitation and increased soil humidity.

Keywords: Explainable artificial intelligence; Indoor air pollution; Machine learning; Outdoor air pollution; benzo[a]pyrene.

MeSH terms

Air Pollutants* / analysis
Air Pollution, Indoor* / analysis
Benzo(a)pyrene / analysis
Environmental Monitoring
Humans
Particulate Matter / analysis
Polycyclic Aromatic Hydrocarbons* / analysis

Substances

Air Pollutants
Particulate Matter
Polycyclic Aromatic Hydrocarbons
Benzo(a)pyrene