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

Abstract

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

Impact of COVID-19 restrictions on hourly levels of PM10, PM2.5 and black carbon at an industrial suburban site in northern Spain

“…Given the available data, variation in pollutant levels during the restrictions were calculated by first determining the mean values for the whole sampling period, and secondly comparing these with the corresponding period in 2019. Rigueira et al (2022) studied PM10 variation during COVID-19 restrictions comparing with data collected from 2015 in a station located in the western area of Gijón. They concluded that reductions observed in PM10 concentration during the lockdown were nothing extraordinary.…”

Bayesian Machine Learning and Functional Data Analysis as a Two-Fold Approach for the Study of Acid Mine Drainage Events

“…Therefore, the concept of depth makes it possible to work with observations, defined in a given time interval, in the form of curves, instead of having to summarize the information contained in these curves into a single value, such as the mean [25]. In this case, the Modified Band Depth (MBD) [45] has been selected as it has demonstrated a better performance in the analysis of environmental data with this approach [46]. Functional directional outlyingness is considered to increase the accuracy in the detection of outliers.…”

Air quality investigation using functional data analysis methods

“…The study demonstrated the effectiveness of functional data analysis in detecting patterns and outliers in nitrogen dioxide concentrations, highlighting the limits of traditional approaches as well as the advantages of functional data analysis for comprehensive air pollution control. Rigueira et al [5] studied the application of functional data analysis for detecting outliers and evaluating the impact of the COVID-19 outbreak on air quality in Gijón, Spain in 2022. The study compared the methodology of classical analysis, statistical process control, and functional data analysis, revealing that functional data analysis outperformed the other two methods in spotting outliers in high-variability data.…”

“…Like in Wang et al [8] study, we also used data smoothing technique (and used Fourier basis as it was done by Torres et al [2]) and tested the significance of difference among different regions using ANOVA. We also performed outliers detection as similar outliers' analysis were performed by Torres et al [2] and by Rigueira et al [5].…”