This study employs hybrid tree–Least Absolute Shrinkage and Selection Operator approach to forecast pollutant concentrations (PM2.5, PM10, NO2, and CO) in Skopje, using data from 2018 to 2022, which includes meteorological variables and pollution measurements from three sensor nodes. Models were trained on pre-COVID-19 data and then tested on post-COVID-19 observations to assess the pandemic's impact on air quality. Results show that models consistently overpredicted pollution levels during the pandemic, suggesting a positive effect of COVID-19 restrictions on air quality. Applications and research directions of the models in the context of metallurgy, mining, and mineral processing are discussed.
SametJZegerSDominiciF, et al.The national morbidity, mortality, and air pollution study. Part II: morbidity and mortality from air pollution in the United States. Res Rep Health Eff Inst2000; 94: 5–79.
2.
MeisnerCGjorgjevDTozijaF. Estimating health impacts and economic costs of air pollution in the Republic of Macedonia. South East Eur J Public Health2015; 4.
JacobsonMZ. Effects of meteorology on air pollution. In: Jakobson MZ (ed) Atmospheric pollution: history, science, and regulation. Cambridge: Cambridge University Press, 2002, pp.145–178.
5.
AlbertoARamosNAlmeidaR. Parametric study of double-skin facades performance in mild climate countries. J Build Eng2017; 12: 87–98.
6.
SrbinovskaMAndovaVKrkoleva MateskaA, et al.The effect of small green walls on reduction of particulate matter concentration in open areas. J Cleaner Prod2021; 279: 123306.
7.
JuMJOhJChoiYH. Changes in air pollution levels after COVID-19 outbreak in Korea. Sci Total Environ2021; 750: 141521.
8.
WuCLWangHWCaiWJ, et al.Impact of the COVID-19 lockdown on roadside traffic-related air pollution in Shanghai, China. Build Environ2021; 194: 107718.
9.
DimovskaMGjorgjevD. The effects of COVID-19 lockdown on air quality in Macedonia. Open Access Maced J Med Sci2020; 8: 353–362.
10.
KangYRenMMZhaoJX, et al.Prediction of end-point phosphorus content of molten steel in BOF with machine learning models. J Min Metall Sect B2024; 60: 93–103.
11.
GuanPWDebusschereBJBishopSR, et al.LASSO For CALPHAD model selection enables data-efficient thermodynamic modeling: an application in thermochemical hydrogen production materials. ACS Appl Energy Mater2025; 8: 8589–8597.
12.
SrbinovskaMPechkovaSPechkovA, et al.A comprehensive study on air pollution prediction in North Macedonia: insights from LASSO modeling. IEEE Explore. 2024. https://ieeexplore.ieee.org/document/10645136.
13.
BerkRA. Classification and regression trees (CART). In: Berk RA (ed) Statistical learning from a regression perspective. Cham: Springer Texts in Statistics. Springer, 2016, pp.129–186.
14.
PedregosaFVaroquauxGGramfortA, et al.Scikit-learn: machine learning in python. J Mach Learn Res2011; 12: 2825–2830.
