Functional Data Analysis for the Detection of Outliers and Study of the Effects of the COVID-19 Pandemic on Air Quality: A Case Study in Gijón, Spain

Air pollution, especially at the ground level, poses a high risk for human health as it can have serious negative effects on population of certain areas. The variability this type data, which are affected by weather conditions and activities, makes difficult conventional methods to precisely detect anomalous values or outliers. In paper, classical analysis, statistical process control, functional data analysis compared purpose. results obtained motivate development new outlier detector based concept directional outlyingness. validation algorithm is perfomed real air quality from city Gijón, Spain, aiming proven reduction in NO2 levels during COVID-19 lockdown that city. Three more variables (SO2, PM10, O3) studied with technique. demonstrate outperforms two other methods, proposed well suited accurate detection outliers variability.