Articles | Volume 15, issue 10
https://doi.org/10.5194/amt-15-3261-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-15-3261-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Machine learning techniques to improve the field performance of low-cost air quality sensors
Tony Bush
Department of Engineering Science, University of Oxford, Parks Road,
Oxford, OX1 3PJ, UK
Apertum Consulting, Harwell, Oxfordshire, UK
Nick Papaioannou
Department of Engineering Science, University of Oxford, Parks Road,
Oxford, OX1 3PJ, UK
Felix Leach
CORRESPONDING AUTHOR
Department of Engineering Science, University of Oxford, Parks Road,
Oxford, OX1 3PJ, UK
Francis D. Pope
School of Geography, Earth and Environmental Sciences, University of
Birmingham, Edgbaston, Birmingham, B15 2TT, UK
Ajit Singh
School of Geography, Earth and Environmental Sciences, University of
Birmingham, Edgbaston, Birmingham, B15 2TT, UK
G. Neil Thomas
Institute of Applied Health Research, University of Birmingham,
Edgbaston, Birmingham, B15 2TT, UK
Brian Stacey
Ricardo Energy & Environment, The Gemini Building, Fermi Avenue,
Harwell, Didcot, OX11 0QR, UK
Suzanne Bartington
Institute of Applied Health Research, University of Birmingham,
Edgbaston, Birmingham, B15 2TT, UK
Related authors
No articles found.
Juncheng Qian, Thomas Wynn, Bowen Liu, Yuli Shan, Suzanne E. Bartington, Francis D. Pope, Yuqing Dai, and Zongbo Shi
EGUsphere, https://doi.org/10.5194/egusphere-2025-3839, https://doi.org/10.5194/egusphere-2025-3839, 2025
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary
Short summary
We developed a multi-stage AutoML calibration framework to improve low-cost indoor PM2.5 sensor accuracy. Using chamber tests with varied emission sources, the method corrected drift, humidity effects, and non-linear responses, raising R2 above 0.9 and halving RMSE. The approach enables reliable, scalable indoor air quality monitoring for research and public health applications.
Sophie A. Mills, Adam Milsom, Christian Pfrang, A. Rob MacKenzie, and Francis D. Pope
Atmos. Meas. Tech., 16, 4885–4898, https://doi.org/10.5194/amt-16-4885-2023, https://doi.org/10.5194/amt-16-4885-2023, 2023
Short summary
Short summary
Pollen grains are important components of the atmosphere and have the potential to impact upon cloud processes via their ability to help in the formation of rain droplets. This study investigates the hygroscopicity of two different pollen species using an acoustic levitator. Pollen grains are levitated, and their response to changes in relative humidity is investigated. A key advantage of this method is that it is possible study pollen shape under varying environmental conditions.
Andrea Mazzeo, Michael Burrow, Andrew Quinn, Eloise A. Marais, Ajit Singh, David Ng'ang'a, Michael J. Gatari, and Francis D. Pope
Atmos. Chem. Phys., 22, 10677–10701, https://doi.org/10.5194/acp-22-10677-2022, https://doi.org/10.5194/acp-22-10677-2022, 2022
Short summary
Short summary
A modelling system for meteorology and chemistry transport processes, WRF–CHIMERE, has been tested and validated for three East African conurbations using the most up-to-date anthropogenic emissions available. Results show that the model is able to reproduce hourly and daily temporal variabilities in aerosol concentrations that are close to observations in both urban and rural environments, encouraging the adoption of numerical modelling as a tool for air quality management in East Africa.
Dimitrios Bousiotis, David C. S. Beddows, Ajit Singh, Molly Haugen, Sebastián Diez, Pete M. Edwards, Adam Boies, Roy M. Harrison, and Francis D. Pope
Atmos. Meas. Tech., 15, 4047–4061, https://doi.org/10.5194/amt-15-4047-2022, https://doi.org/10.5194/amt-15-4047-2022, 2022
Short summary
Short summary
In the last decade, low-cost sensors have revolutionised the field of air quality monitoring. This paper extends the ability of low-cost sensors to not only measure air pollution, but also to understand where the pollution comes from. This "source apportionment" is a critical step in air quality management to allow for the mitigation of air pollution. The techniques developed in this paper have the potential for great impact in both research and industrial applications.
Aileen B. Baird, Edward J. Bannister, A. Robert MacKenzie, and Francis D. Pope
Biogeosciences, 19, 2653–2669, https://doi.org/10.5194/bg-19-2653-2022, https://doi.org/10.5194/bg-19-2653-2022, 2022
Short summary
Short summary
Forest environments contain a wide variety of airborne biological particles (bioaerosols) important for plant and animal health and biosphere–atmosphere interactions. Using low-cost sensors and a free-air carbon dioxide enrichment (FACE) experiment, we monitor the impact of enhanced CO2 on airborne particles. No effect of the enhanced CO2 treatment on total particle concentrations was observed, but a potential suppression of high concentration bioaerosol events was detected under enhanced CO2.
Leigh R. Crilley, Louisa J. Kramer, Francis D. Pope, Chris Reed, James D. Lee, Lucy J. Carpenter, Lloyd D. J. Hollis, Stephen M. Ball, and William J. Bloss
Atmos. Chem. Phys., 21, 18213–18225, https://doi.org/10.5194/acp-21-18213-2021, https://doi.org/10.5194/acp-21-18213-2021, 2021
Short summary
Short summary
Nitrous acid (HONO) is a key source of atmospheric oxidants. We evaluate if the ocean surface is a source of HONO for the marine boundary layer, using measurements from two contrasting coastal locations. We observed no evidence for a night-time ocean surface source, in contrast to previous work. This points to significant geographical variation in the predominant HONO formation mechanisms in marine environments, reflecting possible variability in the sea-surface microlayer composition.
Dimitrios Bousiotis, Francis D. Pope, David C. S. Beddows, Manuel Dall'Osto, Andreas Massling, Jakob Klenø Nøjgaard, Claus Nordstrøm, Jarkko V. Niemi, Harri Portin, Tuukka Petäjä, Noemi Perez, Andrés Alastuey, Xavier Querol, Giorgos Kouvarakis, Nikos Mihalopoulos, Stergios Vratolis, Konstantinos Eleftheriadis, Alfred Wiedensohler, Kay Weinhold, Maik Merkel, Thomas Tuch, and Roy M. Harrison
Atmos. Chem. Phys., 21, 11905–11925, https://doi.org/10.5194/acp-21-11905-2021, https://doi.org/10.5194/acp-21-11905-2021, 2021
Short summary
Short summary
Formation of new particles is a key process in the atmosphere. New particle formation events arising from nucleation of gaseous precursors have been analysed in extensive datasets from 13 sites in five European countries in terms of frequency, nucleation rate, and particle growth rate, with several common features and many differences identified. Although nucleation frequencies are lower at roadside sites, nucleation rates and particle growth rates are typically higher.
Dimitrios Bousiotis, Ajit Singh, Molly Haugen, David C. S. Beddows, Sebastián Diez, Killian L. Murphy, Pete M. Edwards, Adam Boies, Roy M. Harrison, and Francis D. Pope
Atmos. Meas. Tech., 14, 4139–4155, https://doi.org/10.5194/amt-14-4139-2021, https://doi.org/10.5194/amt-14-4139-2021, 2021
Short summary
Short summary
Measurement and source apportionment of atmospheric pollutants are crucial for the assessment of air quality and the implementation of policies for their improvement. This study highlights the current capability of low-cost sensors in source identification and differentiation using clustering approaches. Future directions towards particulate matter source apportionment using low-cost OPCs are highlighted.
Dimitrios Bousiotis, James Brean, Francis D. Pope, Manuel Dall'Osto, Xavier Querol, Andrés Alastuey, Noemi Perez, Tuukka Petäjä, Andreas Massling, Jacob Klenø Nøjgaard, Claus Nordstrøm, Giorgos Kouvarakis, Stergios Vratolis, Konstantinos Eleftheriadis, Jarkko V. Niemi, Harri Portin, Alfred Wiedensohler, Kay Weinhold, Maik Merkel, Thomas Tuch, and Roy M. Harrison
Atmos. Chem. Phys., 21, 3345–3370, https://doi.org/10.5194/acp-21-3345-2021, https://doi.org/10.5194/acp-21-3345-2021, 2021
Short summary
Short summary
New particle formation events from 16 sites over Europe have been studied, and the influence of meteorological and atmospheric composition variables has been investigated. Some variables, like solar radiation intensity and temperature, have a positive effect on the occurrence of these events, while others have a negative effect, affecting different aspects such as the rate at which particles are formed or grow. This effect varies depending on the site type and magnitude of these variables.
Cited articles
Alphasense Ltd.: NO2-A43F Nitrogen Dioxide Sensor 4-Electrode Technical
Specification, https://www.alphasense.com/wp-content/uploads/2019/09/NO2-A43F.pdf (last access: 19 May 2021), 2019a.
Alphasense Ltd.: OPC-N3 Particle Monitor Technical Specification,
https://www.alphasense.com/wp-content/uploads/2019/03/OPC-N3.pdf (last access: 19 May 2021), 2019b.
Berrar, D.: Cross-validation, in Encyclopaedia of Bioinformatics and
Computational Biology: ABC of Bioinformatics, Elsevier, 3, 542–545,
2018.
Bigi, A., Mueller, M., Grange, S. K., Ghermandi, G., and Hueglin, C.: Performance of NO, NO2 low cost sensors and three calibration approaches within a real world application, Atmos. Meas. Tech., 11, 3717–3735, https://doi.org/10.5194/amt-11-3717-2018, 2018.
Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140,
https://doi.org/10.1023/A:1018054314350, 1996.
Breiman, L.: Random forests, Mach. Learn., 45, 5–32,
https://doi.org/10.1023/A:1010933404324, 2001.
Castell, N., Dauge, F. R., Schneider, P., Vogt, M., Lerner, U., Fishbain,
B., Broday, D., and Bartonova, A.: Can commercial low-cost sensor platforms
contribute to air quality monitoring and exposure estimates?, Environ. Int.,
99, 293–302, https://doi.org/10.1016/j.envint.2016.12.007, 2017.
CEDA: CEDA Archive, STFC, UK, CEDA [code, data set], https://www.ceda.ac.uk/services/ceda-archive/, last access: 24 May 2022.
Clements, A. L., Reece, S., Conner, T., and Williams, R.: Observed data
quality concerns involving low-cost air sensors, Atmos. Environ., 3,
100034, https://doi.org/10.1016/j.aeaoa.2019.100034, 2019.
Crilley, L. R., Shaw, M., Pound, R., Kramer, L. J., Price, R., Young, S., Lewis, A. C., and Pope, F. D.: Evaluation of a low-cost optical particle counter (Alphasense OPC-N2) for ambient air monitoring, Atmos. Meas. Tech., 11, 709–720, https://doi.org/10.5194/amt-11-709-2018, 2018.
Crilley, L. R., Singh, A., Kramer, L. J., Shaw, M. D., Alam, M. S., Apte, J. S., Bloss, W. J., Hildebrandt Ruiz, L., Fu, P., Fu, W., Gani, S., Gatari, M., Ilyinskaya, E., Lewis, A. C., Ng'ang'a, D., Sun, Y., Whitty, R. C. W., Yue, S., Young, S., and Pope, F. D.: Effect of aerosol composition on the performance of low-cost optical particle counter correction factors, Atmos. Meas. Tech., 13, 1181–1193, https://doi.org/10.5194/amt-13-1181-2020, 2020.
Cross, E. S., Williams, L. R., Lewis, D. K., Magoon, G. R., Onasch, T. B., Kaminsky, M. L., Worsnop, D. R., and Jayne, J. T.: Use of electrochemical sensors for measurement of air pollution: correcting interference response and validating measurements, Atmos. Meas. Tech., 10, 3575–3588, https://doi.org/10.5194/amt-10-3575-2017, 2017.
Defra: Quality Assurance and Quality Control (QA/QC) Procedures for UK Air
Quality Monitoring under 2008/50/EC and 2004/107/EC, https://uk-air.defra.gov.uk/assets/documents/reports/cat09/1902040953_All_Networks_QAQC_Document_2012__Issue2.pdf (last access: 5 May 2021), 2013.
Defra: Clean Air Strategy 2019, https://www.gov.uk/government/publications/clean-air-strategy-2019 (last access: 24 May 2022), 2019.
Defra: Site Information for Oxford St Ebbes(UKA00518) – Defra, UK, https://uk-air.defra.gov.uk/networks/site-info?uka_id=UKA00518&provider=, last access: 21 April 2021.
Defra: UK Air Information Resource – Defra, UK [data set], https://uk-air.defra.gov.uk/data, last access: 24 May 2022.
Defra and DfT: UK plan for tackling roadside nitrogen dioxide
concentrations: An overview, https://www.gov.uk/government/publications/air-quality-plan-for-nitrogen-dioxide-no2-in-uk-2017 (last access: 24 May 2022),
2017.
EC Working Group: Guide to the demonstration of equivalence of ambient air
monitoring methods Report by an EC Working Group on Guidance for the
Demonstration of Equivalence, https://ec.europa.eu/environment/air/quality/legislation/pdf/equivalence.pdf (last access: 24 May 2022),
2010.
EC Working Group: Equivalence Spreadsheet Tool on the Demonstration of
Equivalence, Version Control, Version 3.1, 02/07/20,
https://ec.europa.eu/environment/air/quality/legislation/pdf/EquivalenceTool%20V3.1%20020720.xlsx (last access: 5 May 2021), 2020.
Esposito, E., De Vito, S., Salvato, M., Bright, V., Jones, R. L., and
Popoola, O.: Dynamic neural network architectures for on field stochastic
calibration of indicative low-cost air quality sensing systems, Sensor.
Actuat. B-Chem., 231, 701–713, https://doi.org/10.1016/j.snb.2016.03.038, 2016.
Hasenfratz, D., Saukh, O., and Thiele, L.: On-the-Fly Calibration of Low-Cost
Gas Sensors, in Wireless Sensor Networks, edited by: Picco, P. G. and Heinzelman, W., Springer Berlin Heidelberg, Berlin, Heidelberg, 228–244,
2012.
Hastie, T., Tibshirani, R., and Friedman, J.: The Elements of Statistical
Learning, https://doi.org/10.1007/978-0-387-84858-7, 2009.
Karagulian, F., Barbiere, M., Kotsev, A., Spinelle, L., Gerboles, M.,
Lagler, F., Redon, N., Crunaire, S., and Borowiak, A.: Review of the
performance of low-cost sensors for air quality monitoring, Atmosphere,
10, 506, https://doi.org/10.3390/atmos10090506, 2019.
Kelly, F. P.: Associations of long-term average concentrations of
nitrogen dioxide with motality, COMEAP Report, https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/734799/COMEAP_NO2_Report.pdf (last access: 24 May 2022), 2018.
Leach, F. C. P., Peckham, M. S., and Hammond, M. J.: Identifying NOx Hotspots
in Transient Urban Driving of Two Diesel Buses and a Diesel Car, Atmosphere, 11, 355, https://doi.org/10.3390/atmos11040355, 2020.
Lim, C. C., Kim, H., Vilcassim, M. J. R., Thurston, G. D., Gordon, T., Chen,
L. C., Lee, K., Heimbinder, M., and Kim, S. Y.: Mapping urban air quality
using mobile sampling with low-cost sensors and machine learning in Seoul,
South Korea, Environ. Int., 131, 105022, https://doi.org/10.1016/J.ENVINT.2019.105022,
2019.
Morawska, L., Thai, P. K., Liu, X., Asumadu-Sakyi, A., Ayoko, G., Bartonova,
A., Bedini, A., Chai, F., Christensen, B., Dunbabin, M., Gao, J., Hagler, G.
S. W., Jayaratne, R., Kumar, P., Lau, A. K. H., Louie, P. K. K., Mazaheri,
M., Ning, Z., Motta, N., Mullins, B., Rahman, M. M., Ristovski, Z., Shafiei,
M., Tjondronegoro, D., Westerdahl, D., and Williams, R.: Applications of
low-cost sensing technologies for air quality monitoring and exposure
assessment: How far have they gone?, Environ. Int., 116, 286–299,
https://doi.org/10.1016/j.envint.2018.04.018, 2018.
National Institute for Health Research: NIHR Funding and Awards Search
Website, https://fundingawards.nihr.ac.uk/award/NIHR130095 (last access: 24 May 2022),
2020.
Oshiro, T. M., Perez, P. S., and Baranauskas, J. A.: How Many Trees in a Random Forest?, in: Machine Learning and Data Mining in Pattern Recognition, edited by: Perner, P., MLDM 2012, Lecture Notes in Computer Science, Vol. 7376, Springer, Berlin, Heidelberg, https://doi.org/10.1007/978-3-642-31537-4_13, 2012.
Probst, P., Wright, M., and Boulesteix, A.-L.: Hyperparameters and Tuning
Strategies for Random Forest, https://wires.onlinelibrary.wiley.com/doi/10.1002/widm.1301 (last access: 24 May 2022), 2019.
Public Health England: Health matters: air pollution – GOV. UK, UK Gov., November, https://www.gov.uk/government/publications/health-matters-air-pollution/health-matters-air-pollution (last access: 24 May 2022),
2018.
Schneider, P., Castell, N., Vogt, M., Dauge, F. R., Lahoz, W. A., and
Bartonova, A.: Mapping urban air quality in near real-time using
observations from low-cost sensors and model information, Environ. Int.,
106, 234–247, https://doi.org/10.1016/j.envint.2017.05.005, 2017.
Spinelle, L., Gerboles, M., and Aleixandre, M.: Performance evaluation of
amperometric sensors for the monitoring of O3 and NO2 in ambient air at ppb
level, Procedia Eng., 120, 480–483, https://doi.org/10.1016/j.proeng.2015.08.676, 2015.
Spinelle, L., Gerboles, M., Villani, M. G., Aleixandre, M., and Bonavitacola,
F.: Field calibration of a cluster of low-cost commercially available
sensors for air quality monitoring. Part B: NO, CO and CO2, Sensor.
Actuat. B-Chem., 238, 706–715, https://doi.org/10.1016/j.snb.2016.07.036, 2017a.
Spinelle, L., Gerboles, M., Kotsev, A., and Signorini, M.: Evaluation of
low-cost sensors for air pollution monitoring: Effect of gaseous interfering
compounds and meteorological conditions, JRC Technical Report, https://op.europa.eu/en/publication-detail/-/publication/23e1a2c7-3c41-11e7-a08e-01aa75ed71a1 (last access: 24 May 2022), 2017b.
De Vito, S., Piga, M., Martinotto, L., and Di Francia, G.: CO, NO2 and NOx
urban pollution monitoring with on-field calibrated electronic nose by
automatic bayesian regularization, ensor.
Actuat. B-Chem., 143,
182–191, https://doi.org/10.1016/j.snb.2009.08.041, 2009.
Wang, S., Ma, Y., Wang, Z., Wang, L., Chi, X., Ding, A., Yao, M., Li, Y., Li, Q., Wu, M., Zhang, L., Xiao, Y., and Zhang, Y.: Mobile monitoring of urban air quality at high spatial resolution by low-cost sensors: impacts of COVID-19 pandemic lockdown, Atmos. Chem. Phys., 21, 7199–7215, https://doi.org/10.5194/acp-21-7199-2021, 2021.
Woodall, G., Hoover, M., Williams, R., Benedict, K., Harper, M., Soo, J.-C.,
Jarabek, A., Stewart, M., Brown, J., Hulla, J., Caudill, M., Clements, A.,
Kaufman, A., Parker, A., Keating, M., Balshaw, D., Garrahan, K., Burton, L.,
Batka, S., Limaye, V., Hakkinen, P., and Thompson, B.: Interpreting Mobile
and Handheld Air Sensor Readings in Relation to Air Quality Standards and
Health Effect Reference Values: Tackling the Challenges, Atmosphere, 8, 182, https://doi.org/10.3390/atmos8100182, 2017.
Yu, H., Lo, H., Hsieh, H., Lou, J., Mckenzie, T. G., Chou, J., Chung, P.,
Ho, C., Chang, C., Weng, J., Yan, E., Chang, C., Kuo, T., Chang, P. T., Po,
C., Wang, C., Huang, Y., Ruan, Y., Lin, Y., Lin, S., Lin, H., and Lin, C.:
Feature engineering and classifier ensemble for KDD Cup 2010, JMLR Work,
Conf. Proc., http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.367.249 (last access: 4 May 2021), 2011.
Zhang, Z. M., Chen, S., and Liang, Y. Z.: Baseline correction using adaptive
iteratively reweighted penalized least squares, Analyst, 135, 1138–1146,
https://doi.org/10.1039/b922045c, 2010.
Zhang, Z. M., Chen, S., and Liang, Y. Z.: Google Code Archive – Long-term
storage for Google Code Project Hosting, https://code.google.com/archive/p/airpls/ (last access: 5 May 2021), 2011.
Zimmerman, N., Presto, A. A., Kumar, S. P. N., Gu, J., Hauryliuk, A., Robinson, E. S., Robinson, A. L., and R. Subramanian: A machine learning calibration model using random forests to improve sensor performance for lower-cost air quality monitoring, Atmos. Meas. Tech., 11, 291–313, https://doi.org/10.5194/amt-11-291-2018, 2018.
Short summary
Poor air quality is a human health risk which demands high-spatiotemporal-resolution monitoring data to manage. Low-cost air quality sensors present a convenient pathway to delivering these needs, compared to traditional methods, but bring methodological challenges which can limit operational ability. In this study within Oxford, UK, we develop machine learning methods to improve the quality of low-cost sensors for NO2, PM10 (particulate matter) and PM2.5 and demonstrate their effectiveness.
Poor air quality is a human health risk which demands high-spatiotemporal-resolution monitoring...