Chang impact analysis of level 3 COVID-19 alert on air pollution indicators using artificial neural network

In this study, mean monthly and diurnal variations in fine particulate matters (PM_2.5), nitrate, sulfate, and gaseous precursors were investigated during the Level 3 COVID-19 alert from May 19 to July 27 in 2021. For comparison, the historical data during the identical period in 2019 and 2020 were also provided to determine the effect of the Level 3 COVID-19 alert on aerosols and gaseous pollutants concentrations in Taichung City. A machine learning model using the artificial neural network technique coupled with a kinetic model was applied to predict NO_x, O₃, nitrate (NO₃ ^-), and sulfate (SO₄ ^2-) to investigate potential emission sources and chemical reaction mechanism. D during the Level 3 COVID-19 alert, a decrease in NO_x concentration due to a decrease in traffic flow under the NO_x-saturated regime was observed to enhance the secondary NO₃ ^- and O₃ formation. The present models were shown to predict 80.1, 77.0, 72.6, and 67.2% concentrations of NO_x, O₃, NO₃ ^-, and SO₄ ^2-, respectively, which could help decision-makers for pollutant emissions reduction policies development and air pollution control strategies. It is recommended that more long-term datasets, including water soluble inorganic salts (WIS), precursors including OH radicals, NH₃, HNO₃, and H₂SO₄, be provided by regulatory air quality monitoring stations to further improve the prediction model accuracy.