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

• Main Authors: Joanna A. Kamińska, Fernando Jiménez, Estrella Lucena-Sánchez, Guido Sciavicco, Tomasz Turek
• Format: Article
• Language: English
• Published: MDPI AG 2020-11-01
• Series: Atmosphere
• Subjects: air pollution; nitrogen oxides; random forest; lag variables; multi-objective optimization; traffic flow
• Online Access: https://www.mdpi.com/2073-4433/11/12/1293

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 NO_x 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 NO_x, 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 NO_x. 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 NO_x 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.