On-Field Performance Test and Calibration of Two Commercially Available Low-Cost Sensors Devices for CO2 Monitoring
© 2022 IIETA. This article is published by IIETA and is licensed under the CC BY 4.0 license (http://creativecommons.org/licenses/by/4.0/).
OPEN ACCESS
The use of low-cost devices for air quality monitoring is rapidly growing, and the reason behind the growth might (at least partially) be the real-time monitoring at a lower fixed and operating cost, ease of use and portability. nevertheless, the poor data reliability of low-cost sensors (LCS) remains a considerable challenge, especially when deployed in real-world conditions. This study aimed to evaluate and improve the performance of two commercially available indoor air quality monitoring LCS devices: AirVisual Pro and uRAD Monitor A3 (uRAD), which were used to monitor CO2 via non-dispersive infrared technology. The analysis took place from June to July 2019 in several classrooms of an urban school in Porto city. Machine learning techniques such as multivariate linear, support vector, gradient boosting and XGBoost regression models were used to perform an on-field calibration for improving the data accuracy of the devices. The results showed that although both the devices showed a strong linear correlation (r > 0.9) with the reference device, they might indicate deviated CO2 concentrations if used in their advertised plug and play format. Specifically, uRAD showed a steady offset compared to the reference values, while AirVisual Pro showed lower deviations than uRAD. The on-field calibration models improved the reliability and showed low root mean square error values (around 30 mg/m3) and a high coefficient of determination (0.99).
carbon dioxide, low-cost sensors, machine learning
[1] I nsightPartners, Air Quality Sensor Market Forecast to 2027 – COVID-19 Impact and Global Analysis by Type, Location, and End User, 2020.
[2] E . G. Snyder et al., The changing paradigm of air pollution monitoring. Environmental Science & Technology, 47(20), pp. 11369–11377, 2013. Art no. Journal Article Review, doi: https://doi.org/10.1021/es4022602.
[3] N ., Castell, M., Viana, M. i. C., Minguillón, C., Guerreiro and X., Querol, Real-world application of new sensor technologies for air quality monitoring. in ETC/ACM Technical Paper, vol. 16, 2013.
[4] R . M., White, I., Paprotny, F., Doering, W. E., Cascio, P. A., Solomon and L. A. G., Sensors, Sensors and Apps for Community-Based Atmospheric Monitoring. In: Air and Waste Management Association’s Magazine for Environmental Managers, pp. 36–40, 2012.
[5] P . J. D. Peterson et al., Practical Use of Metal Oxide Semiconductor Gas Sensors for Measuring Nitrogen Dioxide and Ozone in Urban Environments, (in eng). Sensors (Basel, Switzerland), 17(7), 2017. Art no. Journal Article The Zephyr air quality sensor is currently being developed by Earthsense systems Ltd., a company in which Roland Leigh has direct commercial involvement., doi: https://doi.org/10.3390/s17071653.
[6] L . Morawska et al., Applications of low-cost sensing technologies for air quality monitoring and exposure assessment: How far have they gone? Environment International, 116, pp. 286−299, 2018/07/01/ 2018. doi: https://doi.org/10.1016/j.envint.2018.04.018.
[7] L ., Zhang, F.-C., Tian, X.-W., Peng and X., Yin, A rapid discreteness correction scheme for reproducibility enhancement among a batch of MOS gas sensors. Sensors and Actuators A: Physical, 205, pp. 170−176, 2014/01/01/ 2014. doi: https://doi.org/10.1016/j.sna.2013.11.015.
[8] J . M., Cordero, R., Borge and A., Narros, Using statistical methods to carry out in field calibrations of low cost air quality sensors. Sensors and Actuators B: Chemical, 267, pp. 245−254, 2018/08/15/ 2018. doi: https://doi.org/10.1016/j.snb.2018.04.021.
[9] L ., Spinelle, M., Gerboles, M. G., Villani, M., Aleixandre and F., Bonavitacola, Field calibration of a cluster of low-cost available sensors for air quality monitoring. Part A: Ozone and nitrogen dioxide. Sensors and Actuators B: Chemical, 215, pp. 249−257, 2015/08/01/ 2015. doi: https://doi.org/10.1016/j.snb.2015.03.031.
[10] H. Cui et al., A new calibration system for low-cost Sensor Network in air pollution monitoring. Atmospheric Pollution Research, 12(5), p. 101049, 2021/05/01/ 2021. doi: https://doi.org/10.1016/j.apr.2021.03.012.
[11] L ., Liang, Calibrating low-cost sensors for ambient air monitoring: techniques, trends, and challenges. Environmental Research, vol. 197, p. 111163, 2021/06/01/ 2021, doi: https://doi.org/10.1016/j.envres.2021.111163.
[12] I QAir., AirVisual Pro. https://www.iqair.com/air-quality-monitors/airvisual-pro (accessed).
[13] R adu., uRAD Monitor Model A3., https://www.uradmonitor.com/uradmonitor-model-a3/(accessed).
[14] I ., Demanega, I., Mujan, B. C., Singer, A. S., Anđelković, F., Babich and D., Licina, Performance assessment of low-cost environmental monitors and single sensors under variable indoor air quality and thermal conditions. Building and Environment, 187, p. 107415, 2021/01/01/ 2021. doi: https://doi.org/10.1016/j.buildenv.2020.107415.
[15] M . M. Mukaka, “Statistics corner: A guide to appropriate use of correlation coefficient in medical research,” (in English), Malawi Med J, vol. 24, no. 3, pp. 69−71, 2012. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/23638278
[16] J upyter., https://www.python.org/ (accessed 24/03/2021.
[17] F . Pedregosa et al., Scikit-learn: machine learning in Python. Journal of Machine Learning Research, 12(85), pp. 2825–2830, 2011.
[18] S ., Seabold and J., Perktold, Statsmodels: econometric and statistical modeling with python. 2010.
[19] M ., Waskom, Seaborn: statistical data visualization, Journal of Open Source Software. 6(60), p. 3021, 2021. doi: 10.21105/joss.03021 M4 – Citavi.
[20] J . D., Hunter, Matplotlib: A 2D Graphics Environment. Computing in Science & Engineering, 9(3), pp. 90−95, 2007. doi: 10.1109/MCSE.2007.55.
[21] L ., Spinelle, M., Gerboles, M. G., Villani, M., Aleixandre and F., Bonavitacola, Field calibration of a cluster of low-cost commercially available sensors for air quality monitoring. Part B: NO, CO and CO2, Sensors and Actuators B: Chemical. 238, pp. 706−715, 2017/01/01/ 2017. doi: https://doi.org/10.1016/j.snb.2016.07.036.