Unveiling the potential of a novel portable air quality platform for assessment of fine and coarse particulate matter: in-field testing, calibration, and machine learning insights

• Published in: Environmental monitoring and assessment 2024-10, Vol.196 (10), p.888, Article 888
• Main Authors: Topalović, Dušan B., Tasić, Viša M., Petrović, Jelena S. Stanković, Vlahović, Jelena Lj, Radenković, Mirjana B., Smičiklas, Ivana D.
• Format: Article
• Language: English
• Subjects: Air; Air monitoring; Air Pollutants - analysis; Air pollution; Air Pollution - statistics & numerical data; Air quality; Atmospheric Protection/Air Quality Control/Air Pollution; Calibration; Earth and Environmental Science; Ecology; Ecotoxicology; Environment; Environmental Management; Environmental Monitoring - instrumentation; Environmental Monitoring - methods; Heating; Indoor air pollution; Laboratory tests; Low cost; Machine Learning; Machinery condition monitoring; Metallurgy; Meteorological parameters; Monitoring/Environmental Analysis; Parameter sensitivity; Particulate emissions; Particulate matter; Particulate Matter - analysis; Platforms; Pollutants; Regression analysis; Sensitivity analysis; Sensors; Serbia; Statistical analysis; Statistical significance; Suspended particulate matter
• ISSN: 0167-6369; 1573-2959; 1573-2959
• DOI: 10.1007/s10661-024-13069-0

Although low-cost air quality sensors facilitate the implementation of denser air quality monitoring networks, enabling a more realistic assessment of individual exposure to airborne pollutants, their sensitivity to multifaceted field conditions is often overlooked in laboratory testing. This gap was addressed by introducing an in-field calibration and validation of three PAQMON 1.0 mobile sensing low-cost platforms developed at the Mining and Metallurgy Institute in Bor, Republic of Serbia. A configuration tailored for monitoring PM 2.5 and PM 10 mass concentrations along with meteorological parameters was employed for outdoor measurement campaigns in Bor, spanning heating (HS) and non-heating (NHS) seasons. A statistically significant positive linear correlation between raw PM 2.5 and PM 10 measurements during both campaigns ( R  > 0.90, p  ≤ 0.001) was observed. Measurements obtained from the uncalibrated NOVA SDS011 sensors integrated into the PAQMON 1.0 platforms exhibited a substantial and statistically significant correlation with the GRIMM EDM180 monitor ( R  > 0.60, p  ≤ 0.001). The calibration models based on linear and Random Forest (RF) regression were compared. RF models provided more accurate descriptions of air quality, with average adjR 2 values for air quality variables in the range of 0.70 to 0.80 and average NRMSE values between 0.35 and 0.77. RF-calibrated PAQMON 1.0 platforms displayed divergent levels of accuracy across different pollutant concentration ranges, achieving a data quality objective of 50% during both measurement campaigns. For PM 2.5 , uncertainty ( U r ) was below 50% for concentrations between 9.06 and 34.99 μg/m 3 in HS and 5.75 and 17.58 μg/m 3 in NHS, while for PM 10 , it stayed below 50% from 19.11 to 51.13 μg/m 3 in HS and 11.72 to 38.86 μg/m 3 in NHS.