Outlier Detection in Urban Air Quality Sensor Networks

Abstract

Low-cost urban air quality sensor networks are increasingly used to study the spatio-temporal variability in air pollutant concentrations. Recently installed low-cost urban sensors, however, are more prone to result in erroneous data than conventional monitors, e.g., leading to outliers. Commonly applied outlier detection methods are unsuitable for air pollutant measurements that have large spatial and temporal variations as occur in urban areas. We present a novel outlier detection method based upon a spatio-temporal classification, focusing on hourly NO2 concentrations. We divide a full year’s observations into 16 spatio-temporal classes, reflecting urban background vs. urban traffic stations, weekdays vs. weekends, and four periods per day. For each spatio-temporal class, we detect outliers using the mean and standard deviation of the normal distribution underlying the truncated normal distribution of the NO2 observations. Applying this method to a low-cost air quality sensor network in the city of Eindhoven, the Netherlands, we found 0.1–0.5% of outliers. Outliers could reflect measurement errors or unusual high air pollution events. Additional evaluation using expert knowledge is needed to decide on treatment of the identified outliers. We conclude that our method is able to detect outliers while maintaining the spatio-temporal variability of air pollutant concentrations in urban areas.Electronic supplementary materialThe online version of this article (10.1007/s11270-018-3756-7) contains supplementary material, which is available to authorized users.

Low-Cost Environmental Sensor Networks: Recent Advances and Future Directions

“…This was unexpected given the historical reliance on passive sampling and expensive laboratory equipment for analysis in air quality studies (Snyder et al, 2013). It appears public awareness of health risks (Ali et al, 2015;van Zoest et al, 2018), and the proliferation of low-cost in situ sensors (Schneider et al, 2017;Munir et al, 2019) are driving this trend. For water systems more studies focused on quantity (n = 17) as opposed to quality (n = 11).…”

An Effective Energy and Robust Routing Methods for Air Pollution Data Monitoring in WSN

“…A wireless sensor network for air quality consists of web servers and web clients along with the access to the internet and the base stations and wireless nodes are linked to the base station with service to end devices. In Eindhoven, [5] the air quality was discovered in the AREAS in 2016. It was the first resolution for the air quality sensor networks in Netherland, which was executed in 2013 and operated gradually.…”

“…The air boxes placed determined the particulate matters, O 3 , NO 2 , temperature and humidity levels as air flew from one direction to another. For the power supply, the air boxes were connected to the lamp posts [5]. The outlier detection relies on the determination to observe a concentration value if falling under the condition or not.…”

“…Qr ….. (v) The same process is followed up to monitor NO 2 (Nitrogen) in city Eindhoven which is part of Netherland [5]. The overall review work is partitioned into several sections.…”

“…Therefore, the need to manage and control the air pollution becomes a chief task to save the environment with the increase in pollution, health issues due to bad pollution are also on the increase [2]. From a survey [4] [5], depicts that around 12 million people have been affected. Under such circumstances, the minimization of pollutants is a big challenge for the developers and researchers to make city smart.…”