Articles | Volume 14, issue 8
Research article
18 Aug 2021
Research article |  | 18 Aug 2021

Machine learning calibration of low-cost NO2 and PM10 sensors: non-linear algorithms and their impact on site transferability

Peer Nowack, Lev Konstantinovskiy, Hannah Gardiner, and John Cant

Related authors

Opinion: Why all emergent constraints are wrong but some are useful – a machine learning perspective
Peer Nowack and Duncan Watson-Parris
EGUsphere,,, 2024
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
A systematic evaluation of high-cloud controlling factors
Sarah Wilson Kemsley, Paulo Ceppi, Hendrik Andersen, Jan Cermak, Philip Stier, and Peer Nowack
EGUsphere,,, 2024
Short summary
Sensitivities of cloud radiative effects to large-scale meteorology and aerosols from global observations
Hendrik Andersen, Jan Cermak, Alyson Douglas, Timothy A. Myers, Peer Nowack, Philip Stier, Casey J. Wall, and Sarah Wilson Kemsley
Atmos. Chem. Phys., 23, 10775–10794,,, 2023
Short summary
A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019
Xiang Weng, Grant L. Forster, and Peer Nowack
Atmos. Chem. Phys., 22, 8385–8402,,, 2022
Short summary
An unsupervised learning approach to identifying blocking events: the case of European summer
Carl Thomas, Apostolos Voulgarakis, Gerald Lim, Joanna Haigh, and Peer Nowack
Weather Clim. Dynam., 2, 581–608,,, 2021
Short summary

Related subject area

Subject: Gases | Technique: In Situ Measurement | Topic: Data Processing and Information Retrieval
Detection and long-term quantification of methane emissions from an active landfill
Pramod Kumar, Christopher Caldow, Grégoire Broquet, Adil Shah, Olivier Laurent, Camille Yver-Kwok, Sebastien Ars, Sara Defratyka, Susan Warao Gichuki, Luc Lienhardt, Mathis Lozano, Jean-Daniel Paris, Felix Vogel, Caroline Bouchet, Elisa Allegrini, Robert Kelly, Catherine Juery, and Philippe Ciais
Atmos. Meas. Tech., 17, 1229–1250,,, 2024
Short summary
Research of low-cost air quality monitoring models with different machine learning algorithms
Gang Wang, Chunlai Yu, Kai Guo, Haisong Guo, and Yibo Wang
Atmos. Meas. Tech., 17, 181–196,,, 2024
Short summary
New insights from the Jülich Ozone Sonde Intercomparison Experiment: calibration functions traceable to one ozone reference instrument
Herman G. J. Smit, Deniz Poyraz, Roeland Van Malderen, Anne M. Thompson, David W. Tarasick, Ryan M. Stauffer, Bryan J. Johnson, and Debra E. Kollonige
Atmos. Meas. Tech., 17, 73–112,,, 2024
Short summary
Transferability of ML-based Global Calibration Models for NO2 and NO Low-Cost Sensors
Ayah Abu-Hani, Jia Chen, Vigneshkumar Balamurugan, Adrian Wenzel, and Alessandro Bigi
Atmos. Meas. Tech. Discuss.,,, 2024
Revised manuscript accepted for AMT
Short summary
Identification of spikes in continuous ground-based in situ time series of CO2, CH4 and CO: an extended experiment within the European ICOS Atmosphere network
Paolo Cristofanelli, Cosimo Fratticioli, Lynn Hazan, Mali Chariot, Cedric Couret, Orestis Gazetas, Dagmar Kubistin, Antti Laitinen, Ari Leskinen, Tuomas Laurila, Matthias Lindauer, Giovanni Manca, Michel Ramonet, Pamela Trisolino, and Martin Steinbacher
Atmos. Meas. Tech., 16, 5977–5994,,, 2023
Short summary

Cited articles

Bishop, C. M.: Pattern recognition and machine learning, Springer Science+Business Media, Singapore, 2006. a, b
Breiman, L.: Random forests, Mach. Learn., 45, 5–32,, 2001. a, b
Breiman, L. and Friedman, J. H.: Predicting multivariate responses in multiple linear regression, J. Roy. Stat. Soc.-B, 59, 3–54,, 1997. a
Casey, J. G. and Hannigan, M. P.: Testing the performance of field calibration techniques for low-cost gas sensors in new deployment locations: across a county line and across Colorado, Atmos. Meas. Tech., 11, 6351–6378,, 2018. a, b
Casey, J. G., Collier-Oxandale, A., and Hannigan, M.: Performance of artificial neural networks and linear models to quantify 4 trace gas species in an oil and gas production region with low-cost sensors, Sensor. Actuat. B-Chem., 283, 504–514,, 2019. a
Short summary
Machine learning (ML) calibration techniques could be an effective way to improve the performance of low-cost air pollution sensors. Here we provide novel insights from case studies within the urban area of London, UK, where we compared the performance of three ML techniques to calibrate low-cost measurements of NO2 and PM10. In particular, we highlight the key issue of the method-dependent robustness in maintaining calibration skill after transferring sensors to different measurement sites.