Lag Variables in Nitrogen Oxide Concentration Modelling: A Case Study in Wrocław, Poland

Abstract

Due to the unwavering interest of both residents and authorities in the air quality of urban agglomerations, we pose the following question in this paper: What impact do current and past meteorological factors and traffic flow intensity have on air quality? What is the impact of lagged variables on the fit of an explanation model, and how do they affect its ability to predict? We focused on NO2 and NOx concentrations, and conducted this research using hourly data from the city of Wrocław (western Poland) from 2015 to 2017; we used multi-objective optimization to determine the optimal delays. It turned out that for both NO2 and NOx, the past values for traffic flow, wind speed, and sunshine duration are more important than the current ones. We built random forest models on each of the pollutants for both the current and past values and discovered that including a lagged variable increases the resulting R2 from 0.51 to 0.56 for NO2 and from 0.46 to 0.52 for NOx. We also analyzed the feature importance in each model, and found that for NO2, a wind speed delay of more than three hours causes a significant decrease, while the importance of relative humidity increases with a seven-hour delay; likewise, wind speed increases the importance for NOx prediction with a two-hour delay. We concluded that, in pollutant concentration modeling, the possibility of a delayed effect of the independent variables should always be considered, because it can significantly increase the performance of the model and suggest unexpected relationships or dependencies.

Long-term changes in air quality. The case of Pristina (Kosovo)

“…This may indicate that most of the nitrogen oxide comes from traffic emissions and is related to the burning of fuel, something also confirmed in studies conducted in other cities with urban environments (Anttila at al. 2010, Kurtenbach et al 2012, Smith et al 2015, Lorente et al 2019, Kamińska et al 2020. In 2019, only two days of May (May 7 and May 26), and at the beginning of June, concentrations of nitrogen oxides were at the same low level as in 2020.…”

Functional Kriging for Spatiotemporal Modeling of Nitrogen Dioxide in a Middle Eastern Megacity

“…Transportation, power plants, and natural processes have led to humans and ecosystems faced with serious air quality issues [4,5]. Many acute and chronic impacts on human health and even death may be caused by exposure to high levels of air pollutants [6,7]. The World Health Organization (WHO) reported around 4.2 million yearly deaths due to exposure to air pollution worldwide [8].…”

“…In different studies, the concentration of air pollution has been assessed by measuring or predicting at monitoring stations using various modeling methods [5][6][7][8][9][10][11][12]. The accurate prediction of air pollution improves the protection strategy of the affected population and helps manage the air quality control system effectively.…”