The explainable potential of coupling hybridized metaheuristics, XGBoost, and SHAP in revealing toluene behavior in the atmosphere

Nebojsa Bacanin; Mirjana Perisic; Gordana Jovanovic; Robertas Damaševičius; Svetlana Stanisic; Vladimir Simic; Miodrag Zivkovic; Andreja Stojic

doi:10.1016/j.scitotenv.2024.172195

The explainable potential of coupling hybridized metaheuristics, XGBoost, and SHAP in revealing toluene behavior in the atmosphere

Sci Total Environ. 2024 Apr 15:929:172195. doi: 10.1016/j.scitotenv.2024.172195. Online ahead of print.

Authors

Nebojsa Bacanin¹, Mirjana Perisic², Gordana Jovanovic³, Robertas Damaševičius⁴, Svetlana Stanisic⁵, Vladimir Simic⁶, Miodrag Zivkovic⁷, Andreja Stojic⁸

Affiliations

¹ Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11010, Serbia; Sinergija University, Raje Banjicica, Bjeljina 76300, Bosnia and Herzegovina. Electronic address: nbacanin@singidunum.ac.rs.
² Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11010, Serbia; Institute of Physics Belgrade, University of Belgrade, Pregrevica 118, Belgrade 11010, Serbia. Electronic address: mirjana@ipb.ac.rs.
³ Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11010, Serbia; Institute of Physics Belgrade, University of Belgrade, Pregrevica 118, Belgrade 11010, Serbia. Electronic address: gordana.vukovic@ipb.ac.rs.
⁴ Centre of Real Time Computer Systems, Kaunas University of Technology, Barsausko 59, Kaunas 51423, Lithuania. Electronic address: robertas.damasevicius@ktu.lt.
⁵ Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11010, Serbia. Electronic address: sstanisic@singidunum.ac.rs.
⁶ Faculty of Transport and Traffic Engineering, University of Belgrade, Vojvode Stepe 305, Belgrade 44249, Serbia; Yuan Ze University, College of Engineering, Department of Industrial Engineering and Management, Taoyuan City 320315, Taiwan; Department of Computer Science and Engineering, College of Informatics, Korea University, Seoul 02841, Republic of Korea. Electronic address: vsima@sf.bg.ac.rs.
⁷ Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11010, Serbia. Electronic address: mzivkovic@singidunum.ac.rs.
⁸ Informatics and Computing, Singidunum University, Danijelova 32, Belgrade 11010, Serbia; Sinergija University, Raje Banjicica, Bjeljina 76300, Bosnia and Herzegovina. Electronic address: andreja.stojic@ipb.ac.rs.

PMID: 38631643
DOI: 10.1016/j.scitotenv.2024.172195

Abstract

Toluene is a neurotoxic aromatic hydrocarbon and one of the major representatives of volatile organic compounds, known for its abundance, adverse health effects, and role in the formation of other atmospheric pollutants like ozone. This research introduces the enhanced version of the reptile search metaheuristics algorithm which has been utilized to tune the extreme gradient boosting hyperparameters, to investigate toluene atmospheric behavior patterns and interactions with other polluting species within defined environmental conditions. The study is based on a two-year database encompassing concentrations of inorganic gaseous contaminants every hour (NO, NO₂, NOx, and O₃), particulate matter fractions (PM₁, PM_2.5, and PM₁₀), m,p-xylene, toluene, benzene, total non-methane hydrocarbons, and meteorological data. The experimental outcomes were validated against the results of extreme gradient boosting models optimized by seven other recent powerful metaheuristics algorithms. The best-performing model has been interpreted by employing Shapley additive explanations method. In the study, we have focused on the relationship between toluene and benzene, as its most important predictor, and provided a detailed description of environmental conditions which directed their interactions.

Keywords: Explainable AI; Metaheuristics; Swarm intelligence.