Articles | Volume 17, issue 13
https://doi.org/10.5194/amt-17-3917-2024
© Author(s) 2024. 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-17-3917-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
03 Jul 2024
Research article |
| 03 Jul 2024
| 03 Jul 2024
Transferability of machine-learning-based global calibration models for NO2 and NO low-cost sensors
Ayah Abu-Hani
Environmental Sensing and Modeling, Technical University of Munich (TUM), Munich, Germany
Environmental Sensing and Modeling, Technical University of Munich (TUM), Munich, Germany
Vigneshkumar Balamurugan
Environmental Sensing and Modeling, Technical University of Munich (TUM), Munich, Germany
Adrian Wenzel
Environmental Sensing and Modeling, Technical University of Munich (TUM), Munich, Germany
Alessandro Bigi
Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, Modena, Italy
Related authors
No articles found.
Myriam Agrò, Manuel Bettineschi, Silvia Melina, Diego Aliaga, Andrea Bergomi, Beatrice Biffi, Alessandro Bigi, Giancarlo Ciarelli, Cristina Colombi, Paola Fermo, Ivan Grigioni, Veli-Matti Kerminen, Markku Kulmala, Janne Lampilahti, Angela Marinoni, Celestine Oliewo, Juha Sulo, Gianluigi Valli, Roberta Vecchi, Tuukka Petäjä, Katrianne Lehtipalo, and Federico Bianchi
EGUsphere, https://doi.org/10.5194/egusphere-2025-2387, https://doi.org/10.5194/egusphere-2025-2387, 2025
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
This study investigates New Particle Formation (NPF) in Milan, the most populated city in the Po Valley (Italy), using one year of particle number size distribution data (1.2–480 nm). NPF is enhanced under cleaner air conditions with lower pollution, reduced condensation sink, stronger ventilation, and stronger northwesterly winds (e.g., Foehn events). In contrast, longer air mass residence time in the Po Valley and higher air mass exposure to anthropogenic emissions suppress it.
Stavros Stagakis, Dominik Brunner, Junwei Li, Leif Backman, Anni Karvonen, Lionel Constantin, Leena Järvi, Minttu Havu, Jia Chen, Sophie Emberger, and Liisa Kulmala
Biogeosciences, 22, 2133–2161, https://doi.org/10.5194/bg-22-2133-2025, https://doi.org/10.5194/bg-22-2133-2025, 2025
Short summary
Short summary
The balance between CO2 uptake and emissions from urban green areas is still not well understood. This study evaluated for the first time the urban park CO2 exchange simulations with four different types of biosphere model by comparing them with observations. Even though some advantages and disadvantages of the different model types were identified, there was no strong evidence that more complex models performed better than simple ones.
Daniel Kühbacher, Jia Chen, Patrick Aigner, Mario Ilic, Ingrid Super, and Hugo Denier van der Gon
EGUsphere, https://doi.org/10.5194/egusphere-2025-753, https://doi.org/10.5194/egusphere-2025-753, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
We present DRIVE v1.0, a data-driven framework to estimate road transport emissions, their temporal profiles, and the associated uncertainties. The method was applied to the city of Munich, where we present bottom-up emission estimates for the years 2019 to 2022. The estimates are compared against official municipal reports as well as national and European downscaled inventories.
Dominik Brunner, Ivo Suter, Leonie Bernet, Lionel Constantin, Stuart K. Grange, Pascal Rubli, Junwei Li, Jia Chen, Alessandro Bigi, and Lukas Emmenegger
EGUsphere, https://doi.org/10.5194/egusphere-2025-640, https://doi.org/10.5194/egusphere-2025-640, 2025
Short summary
Short summary
In order to support the city of Zurich in tracking its path to net-zero greenhouse gas emissions planned to be reached by 2040, a CO2 emission monitoring system was established. The system combines a dense network of CO2 sensors with a high-resolution atmospheric transport model GRAMM/GRAL. This study presents the setup of the model together with its numerous inputs and evaluates its performance in comparison with the observations from the CO2 sensor network.
Neil Humpage, Hartmut Boesch, William Okello, Jia Chen, Florian Dietrich, Mark F. Lunt, Liang Feng, Paul I. Palmer, and Frank Hase
Atmos. Meas. Tech., 17, 5679–5707, https://doi.org/10.5194/amt-17-5679-2024, https://doi.org/10.5194/amt-17-5679-2024, 2024
Short summary
Short summary
We used a Bruker EM27/SUN spectrometer within an automated weatherproof enclosure to measure greenhouse gas column concentrations over a 3-month period in Jinja, Uganda. The portability of the EM27/SUN allows us to evaluate satellite and model data in locations not covered by traditional validation networks. This is of particular value in tropical Africa, where extensive terrestrial ecosystems are a significant store of carbon and play a key role in the atmospheric budgets of CO2 and CH4.
Giorgio Veratti, Alessandro Bigi, Michele Stortini, Sergio Teggi, and Grazia Ghermandi
Atmos. Chem. Phys., 24, 10475–10512, https://doi.org/10.5194/acp-24-10475-2024, https://doi.org/10.5194/acp-24-10475-2024, 2024
Short summary
Short summary
In a study of two consecutive winter seasons, we used measurements and modelling tools to identify the levels and sources of black carbon pollution in a medium-sized urban area of the Po Valley, Italy. Our findings show that biomass burning and traffic-related emissions (especially from Euro 4 diesel cars) significantly contribute to BC concentrations. This research offers crucial insights for policymakers and urban planners aiming to improve air quality in cities.
Giorgio Veratti, Alessandro Bigi, Sergio Teggi, and Grazia Ghermandi
Geosci. Model Dev., 17, 6465–6487, https://doi.org/10.5194/gmd-17-6465-2024, https://doi.org/10.5194/gmd-17-6465-2024, 2024
Short summary
Short summary
In this study, we present VERT (Vehicular Emissions from Road Traffic), an R package designed to estimate transport emissions using traffic estimates and vehicle fleet composition data. Compared to other tools available in the literature, VERT stands out for its user-friendly configuration and flexibility of user input. Case studies demonstrate its accuracy in both urban and regional contexts, making it a valuable tool for air quality management and transport scenario planning.
Benedikt Herkommer, Carlos Alberti, Paolo Castracane, Jia Chen, Angelika Dehn, Florian Dietrich, Nicholas M. Deutscher, Matthias Max Frey, Jochen Groß, Lawson Gillespie, Frank Hase, Isamu Morino, Nasrin Mostafavi Pak, Brittany Walker, and Debra Wunch
Atmos. Meas. Tech., 17, 3467–3494, https://doi.org/10.5194/amt-17-3467-2024, https://doi.org/10.5194/amt-17-3467-2024, 2024
Short summary
Short summary
The Total Carbon Column Observing Network is a network of ground-based Fourier transform infrared (FTIR) spectrometers used mainly for satellite validation. To ensure the highest-quality validation data, the network needs to be highly consistent. This is a major challenge, which so far is solved by site comparisons with airborne in situ measurements. In this work, we describe the use of a portable FTIR spectrometer as a travel standard for evaluating the consistency of TCCON sites.
Tommaso Isolabella, Vera Bernardoni, Alessandro Bigi, Marco Brunoldi, Federico Mazzei, Franco Parodi, Paolo Prati, Virginia Vernocchi, and Dario Massabò
Atmos. Meas. Tech., 17, 1363–1373, https://doi.org/10.5194/amt-17-1363-2024, https://doi.org/10.5194/amt-17-1363-2024, 2024
Short summary
Short summary
We present an innovative software toolkit to differentiate sources of carbonaceous aerosol in the atmosphere. Our toolkit implements an upgraded mathematical model which allows for determination of fundamental optical properties of the aerosol, its sources, and the mass concentration of different carbonaceous species of particulate matter. We have tested the functionality of the software by re-analysing published data, and we obtained a compatible results with additional information.
Alessandro Bigi, Giorgio Veratti, Elisabeth Andrews, Martine Collaud Coen, Lorenzo Guerrieri, Vera Bernardoni, Dario Massabò, Luca Ferrero, Sergio Teggi, and Grazia Ghermandi
Atmos. Chem. Phys., 23, 14841–14869, https://doi.org/10.5194/acp-23-14841-2023, https://doi.org/10.5194/acp-23-14841-2023, 2023
Short summary
Short summary
Atmospheric particles include compounds that play a key role in the greenhouse effect and air toxicity. Concurrent observations of these compounds by multiple instruments are presented, following deployment within an urban environment in the Po Valley, one of Europe's pollution hotspots. The study compares these data, highlighting the impact of ground emissions, mainly vehicular traffic and biomass burning, on the absorption of sun radiation and, ultimately, on climate change and air quality.
Xinxu Zhao, Jia Chen, Julia Marshall, Michal Gałkowski, Stephan Hachinger, Florian Dietrich, Ankit Shekhar, Johannes Gensheimer, Adrian Wenzel, and Christoph Gerbig
Atmos. Chem. Phys., 23, 14325–14347, https://doi.org/10.5194/acp-23-14325-2023, https://doi.org/10.5194/acp-23-14325-2023, 2023
Short summary
Short summary
We develop a modeling framework using the Weather Research and Forecasting model at a high spatial resolution (up to 400 m) to simulate atmospheric transport of greenhouse gases and interpret column observations. Output is validated against weather stations and column measurements in August 2018. The differential column method is applied, aided by air-mass transport tracing with the Stochastic Time-Inverted Lagrangian Transport (STILT) model, also for an exploratory measurement interpretation.
Vigneshkumar Balamurugan, Jia Chen, Adrian Wenzel, and Frank N. Keutsch
Atmos. Chem. Phys., 23, 10267–10285, https://doi.org/10.5194/acp-23-10267-2023, https://doi.org/10.5194/acp-23-10267-2023, 2023
Short summary
Short summary
In this study, machine learning models are employed to model NO2 and O3 concentrations. We employed a wide range of sources of data, including meteorological and column satellite measurements, to model NO2 and O3 concentrations. The spatial and temporal variability, and their drivers, were investigated. Notably, the machine learning model established the relationship between NOx and O3. Despite the fact that metropolitan regions are NO2 hotspots, rural areas have high O3 concentrations.
Andreas Forstmaier, Jia Chen, Florian Dietrich, Juan Bettinelli, Hossein Maazallahi, Carsten Schneider, Dominik Winkler, Xinxu Zhao, Taylor Jones, Carina van der Veen, Norman Wildmann, Moritz Makowski, Aydin Uzun, Friedrich Klappenbach, Hugo Denier van der Gon, Stefan Schwietzke, and Thomas Röckmann
Atmos. Chem. Phys., 23, 6897–6922, https://doi.org/10.5194/acp-23-6897-2023, https://doi.org/10.5194/acp-23-6897-2023, 2023
Short summary
Short summary
Large cities emit greenhouse gases which contribute to global warming. In this study, we measured the release of one important green house gas, methane, in Hamburg. Multiple sources that contribute to methane emissions were located and quantified. Methane sources were found to be mainly caused by human activity (e.g., by release from oil and gas refineries). Moreover, potential natural sources have been located, such as the Elbe River and lakes.
Maximilian Rißmann, Jia Chen, Gregory Osterman, Xinxu Zhao, Florian Dietrich, Moritz Makowski, Frank Hase, and Matthäus Kiel
Atmos. Meas. Tech., 15, 6605–6623, https://doi.org/10.5194/amt-15-6605-2022, https://doi.org/10.5194/amt-15-6605-2022, 2022
Short summary
Short summary
The Orbiting Carbon Observatory 2 (OCO-2) measures atmospheric concentrations of the most potent greenhouse gas, CO2, globally. By comparing its measurements to a ground-based monitoring network in Munich (MUCCnet), we find that the satellite is able to reliably detect urban CO2 concentrations. Furthermore, spatial CO2 differences captured by OCO-2 and MUCCnet are strongly correlated, which indicates that OCO-2 could be helpful in determining urban CO2 emissions from space.
Benjamin Zanger, Jia Chen, Man Sun, and Florian Dietrich
Geosci. Model Dev., 15, 7533–7556, https://doi.org/10.5194/gmd-15-7533-2022, https://doi.org/10.5194/gmd-15-7533-2022, 2022
Short summary
Short summary
Gaussian priors (GPs) used in least squares inversion do not reflect the true distributions of greenhouse gas emissions well. A method that does not rely on GPs is sparse reconstruction (SR). We show that necessary conditions for SR are satisfied for cities and that the application of a wavelet transform can further enhance sparsity. We apply the theory of compressed sensing to SR. Our results show that SR needs fewer measurements and is superior for assessing unknown emitters compared to GPs.
Vigneshkumar Balamurugan, Jia Chen, Zhen Qu, Xiao Bi, and Frank N. Keutsch
Atmos. Chem. Phys., 22, 7105–7129, https://doi.org/10.5194/acp-22-7105-2022, https://doi.org/10.5194/acp-22-7105-2022, 2022
Short summary
Short summary
In this study, we investigated the response of secondary pollutants to changes in precursor emissions, focusing on the formation of secondary PM, during the COVID-19 lockdown period. We show that, due to the decrease in primary NOx emissions, atmospheric oxidizing capacity is increased. The nighttime increase in ozone, caused by less NO titration, results in higher NO3 radicals, which contribute significantly to the formation of PM nitrates. O3 should be limited in order to control PM pollution.
Andreas Luther, Julian Kostinek, Ralph Kleinschek, Sara Defratyka, Mila Stanisavljević, Andreas Forstmaier, Alexandru Dandocsi, Leon Scheidweiler, Darko Dubravica, Norman Wildmann, Frank Hase, Matthias M. Frey, Jia Chen, Florian Dietrich, Jarosław Nȩcki, Justyna Swolkień, Christoph Knote, Sanam N. Vardag, Anke Roiger, and André Butz
Atmos. Chem. Phys., 22, 5859–5876, https://doi.org/10.5194/acp-22-5859-2022, https://doi.org/10.5194/acp-22-5859-2022, 2022
Short summary
Short summary
Coal mining is an extensive source of anthropogenic methane emissions. In order to reduce and mitigate methane emissions, it is important to know how much and where the methane is emitted. We estimated coal mining methane emissions in Poland based on atmospheric methane measurements and particle dispersion modeling. In general, our emission estimates suggest higher emissions than expected by previous annual emission reports.
Carlos Alberti, Frank Hase, Matthias Frey, Darko Dubravica, Thomas Blumenstock, Angelika Dehn, Paolo Castracane, Gregor Surawicz, Roland Harig, Bianca C. Baier, Caroline Bès, Jianrong Bi, Hartmut Boesch, André Butz, Zhaonan Cai, Jia Chen, Sean M. Crowell, Nicholas M. Deutscher, Dragos Ene, Jonathan E. Franklin, Omaira García, David Griffith, Bruno Grouiez, Michel Grutter, Abdelhamid Hamdouni, Sander Houweling, Neil Humpage, Nicole Jacobs, Sujong Jeong, Lilian Joly, Nicholas B. Jones, Denis Jouglet, Rigel Kivi, Ralph Kleinschek, Morgan Lopez, Diogo J. Medeiros, Isamu Morino, Nasrin Mostafavipak, Astrid Müller, Hirofumi Ohyama, Paul I. Palmer, Mahesh Pathakoti, David F. Pollard, Uwe Raffalski, Michel Ramonet, Robbie Ramsay, Mahesh Kumar Sha, Kei Shiomi, William Simpson, Wolfgang Stremme, Youwen Sun, Hiroshi Tanimoto, Yao Té, Gizaw Mengistu Tsidu, Voltaire A. Velazco, Felix Vogel, Masataka Watanabe, Chong Wei, Debra Wunch, Marcia Yamasoe, Lu Zhang, and Johannes Orphal
Atmos. Meas. Tech., 15, 2433–2463, https://doi.org/10.5194/amt-15-2433-2022, https://doi.org/10.5194/amt-15-2433-2022, 2022
Short summary
Short summary
Space-borne greenhouse gas missions require ground-based validation networks capable of providing fiducial reference measurements. Here, considerable refinements of the calibration procedures for the COllaborative Carbon Column Observing Network (COCCON) are presented. Laboratory and solar side-by-side procedures for the characterization of the spectrometers have been refined and extended. Revised calibration factors for XCO2, XCO and XCH4 are provided, incorporating 47 new spectrometers.
Johannes Gensheimer, Alexander J. Turner, Philipp Köhler, Christian Frankenberg, and Jia Chen
Biogeosciences, 19, 1777–1793, https://doi.org/10.5194/bg-19-1777-2022, https://doi.org/10.5194/bg-19-1777-2022, 2022
Short summary
Short summary
We develop a convolutional neural network, named SIFnet, that increases the spatial resolution of SIF from TROPOMI by a factor of 10 to a spatial resolution of 0.005°. SIFnet utilizes coarse SIF observations, together with a broad range of high-resolution auxiliary data. The insights gained from interpretable machine learning techniques allow us to make quantitative claims about the relationships between SIF and other common parameters related to photosynthesis.
Gerrit Kuhlmann, Ka Lok Chan, Sebastian Donner, Ying Zhu, Marc Schwaerzel, Steffen Dörner, Jia Chen, Andreas Hueni, Duc Hai Nguyen, Alexander Damm, Annette Schütt, Florian Dietrich, Dominik Brunner, Cheng Liu, Brigitte Buchmann, Thomas Wagner, and Mark Wenig
Atmos. Meas. Tech., 15, 1609–1629, https://doi.org/10.5194/amt-15-1609-2022, https://doi.org/10.5194/amt-15-1609-2022, 2022
Short summary
Short summary
Nitrogen dioxide (NO2) is an air pollutant whose concentration often exceeds air quality guideline values, especially in urban areas. To map the spatial distribution of NO2 in Munich, we conducted the Munich NO2 Imaging Campaign (MuNIC), where NO2 was measured with stationary, mobile, and airborne in situ and remote sensing instruments. The campaign provides a unique dataset that has been used to compare the different instruments and to study the spatial variability of NO2 and its sources.
Taylor S. Jones, Jonathan E. Franklin, Jia Chen, Florian Dietrich, Kristian D. Hajny, Johannes C. Paetzold, Adrian Wenzel, Conor Gately, Elaine Gottlieb, Harrison Parker, Manvendra Dubey, Frank Hase, Paul B. Shepson, Levi H. Mielke, and Steven C. Wofsy
Atmos. Chem. Phys., 21, 13131–13147, https://doi.org/10.5194/acp-21-13131-2021, https://doi.org/10.5194/acp-21-13131-2021, 2021
Short summary
Short summary
Methane emissions from leaks in natural gas pipes are often a large source in urban areas, but they are difficult to measure on a city-wide scale. Here we use an array of innovative methane sensors distributed around the city of Indianapolis and a new method of combining their data with an atmospheric model to accurately determine the magnitude of these emissions, which are about 70 % larger than predicted. This method can serve as a framework for cities trying to account for their emissions.
Florian Dietrich, Jia Chen, Benno Voggenreiter, Patrick Aigner, Nico Nachtigall, and Björn Reger
Atmos. Meas. Tech., 14, 1111–1126, https://doi.org/10.5194/amt-14-1111-2021, https://doi.org/10.5194/amt-14-1111-2021, 2021
Short summary
Short summary
Climate change is one of the defining issues of our time. However, most of the current emission estimates are based on calculations, not on actual measurements as it is difficult to quantify the emissions of large sources such as cities. This study shows how to use the relatively new approach of column measurements to quantify urban greenhouse gas emissions in an exact way using only a few compact measurement systems. The approach can be used to evaluate the effectiveness of mitigation policies.
Martine Collaud Coen, Elisabeth Andrews, Alessandro Bigi, Giovanni Martucci, Gonzague Romanens, Frédéric P. A. Vogt, and Laurent Vuilleumier
Atmos. Meas. Tech., 13, 6945–6964, https://doi.org/10.5194/amt-13-6945-2020, https://doi.org/10.5194/amt-13-6945-2020, 2020
Short summary
Short summary
The Mann–Kendall trend test requires prewhitening in the presence of serially correlated data. The effects of five prewhitening methods and time granularity, autocorrelation, temporal segmentation and length of the time series on the statistical significance and the slope are studies for seven atmospheric datasets. Finally, a new algorithm using three prewhitening methods is proposed in order to optimize the power of the test, the amount of erroneous false positive trends and the slope estimate.
Ying Zhu, Jia Chen, Xiao Bi, Gerrit Kuhlmann, Ka Lok Chan, Florian Dietrich, Dominik Brunner, Sheng Ye, and Mark Wenig
Atmos. Chem. Phys., 20, 13241–13251, https://doi.org/10.5194/acp-20-13241-2020, https://doi.org/10.5194/acp-20-13241-2020, 2020
Short summary
Short summary
Average NO2 concentration of on-street mobile measurements (MMs) near the monitoring stations (MSs) was found to be considerably higher than the MSs data. The common measurement height (H) and distance (D) of the MSs result in 27 % lower average concentrations in total than the concentration of our MMs. Another 21 % difference remained after correcting the influence of the measuring H and D. This result makes our city-wide measurements for capturing the full range of concentrations necessary.
Qiansi Tu, Frank Hase, Thomas Blumenstock, Rigel Kivi, Pauli Heikkinen, Mahesh Kumar Sha, Uwe Raffalski, Jochen Landgraf, Alba Lorente, Tobias Borsdorff, Huilin Chen, Florian Dietrich, and Jia Chen
Atmos. Meas. Tech., 13, 4751–4771, https://doi.org/10.5194/amt-13-4751-2020, https://doi.org/10.5194/amt-13-4751-2020, 2020
Short summary
Short summary
Two COCCON instruments are used to observe multiyear greenhouse gases in boreal areas and are compared with the CAMS analysis and S5P satellite data. These three datasets predict greenhouse gas gradients with reasonable agreement. The results indicate that the COCCON instrument has the capability of measuring gradients on regional scales, and observations performed with the portable spectrometers can contribute to inferring sources and sinks and to validating spaceborne greenhouse gases.
Cited articles
Baruah, A., Zivan, O., Bigi, A., and Ghermandi, G.: Evaluation of low-cost gas sensors to quantify intra-urban variability of atmospheric pollutants, Environmental Science: Atmospheres, 3, 830–841, https://doi.org/10.1039/D2EA00165A, 2023. a, b
Beckwith, M., Bates, E., Gillah, A., and Carslaw, N.: NO2 hotspots: are we measuring in the right places?, Atmospheric Environment: X, 2, 100025, https://doi.org/10.1016/j.aeaoa.2019.100025, 2019. a
Borrego, C., Costa, A., Ginja, J., Amorim, M., Coutinho, M., Karatzas, K., Sioumis, T., Katsifarakis, N., Konstantinidis, K., De Vito, S., Esposito, E., Smith, P., André, N., Gérard, P., Francis, L. A., Castell, N., Schneider, P., Viana, M., Minguillón, M. C., Reimringer, W., Otjes, R. P., von Sicard, O., Pohle, R., Elen, B., Suriano, D., Pfister, V., Prato, M., Dipinto, S., and Penza, M.: Assessment of air quality microsensors versus reference methods: The EuNetAir joint exercise, Atmos. Environ., 147, 246–263, https://doi.org/10.1016/j.atmosenv.2016.09.050, 2016. a
deSouza, P., Kahn, R., Stockman, T., Obermann, W., Crawford, B., Wang, A., Crooks, J., Li, J., and Kinney, P.: Calibrating networks of low-cost air quality sensors, Atmos. Meas. Tech., 15, 6309–6328, https://doi.org/10.5194/amt-15-6309-2022, 2022. a
Giordano, M. R., Malings, C., Pandis, S. N., Presto, A. A., McNeill, V., Westervelt, D. M., Beekmann, M., and Subramanian, R.: From low-cost sensors to high-quality data: A summary of challenges and best practices for effectively calibrating low-cost particulate matter mass sensors, J. Aerosol Sci., 158, 105833, https://doi.org/10.1016/j.jaerosci.2021.105833, 2021. a, b
Grover, A., Kapoor, A., and Horvitz, E.: A deep hybrid model for weather forecasting, in: KDD '15: The 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Sydney NSW Australia, 10–13 August 2015, Association for Computing Machinery, 379–386, https://doi.org/10.1145/2783258.2783275, 2015. a
Hossain, M., Saffell, J., and Baron, R.: Differentiating NO2 and O3 at low cost air quality amperometric gas sensors, ACS Sensors, 1, 1291–1294, https://doi.org/10.1021/acssensors.6b00603, 2016. a
Jolliff, J. K., Kindle, J. C., Shulman, I., Penta, B., Friedrichs, M. A., Helber, R., and Arnone, R. A.: Summary diagrams for coupled hydrodynamic-ecosystem model skill assessment, J. Marine Syst., 76, 64–82, https://doi.org/10.1016/j.jmarsys.2008.05.014, 2009. a
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. a
Kelly, F. J. and Fussell, J. C.: Air pollution and public health: emerging hazards and improved understanding of risk, Environ. Geochem. Hlth., 37, 631–649, https://doi.org/10.1007/s10653-015-9720-1, 2015. a
Kim, J., Shusterman, A. A., Lieschke, K. J., Newman, C., and Cohen, R. C.: The BErkeley Atmospheric CO2 Observation Network: field calibration and evaluation of low-cost air quality sensors, Atmos. Meas. Tech., 11, 1937–1946, https://doi.org/10.5194/amt-11-1937-2018, 2018. a, b
Kureshi, R. R., Mishra, B. K., Thakker, D., John, R., Walker, A., Simpson, S., Thakkar, N., and Wante, A. K.: Data-driven techniques for low-cost sensor selection and calibration for the use case of air quality monitoring, Sensors, 22, 1093, https://doi.org/10.3390/s22031093, 2022. a
Li, J., Hauryliuk, A., Malings, C., Eilenberg, S. R., Subramanian, R., and Presto, A. A.: Characterizing the aging of Alphasense NO2 sensors in long-term field deployments, ACS Sensors, 6, 2952–2959, https://doi.org/10.1021/acssensors.1c00729, 2021. a, b
Maag, B., Zhou, Z., and Thiele, L.: A survey on sensor calibration in air pollution monitoring deployments, IEEE Internet Things, 5, 4857–4870, https://doi.org/10.1109/JIOT.2018.2853660, 2018. a
Malings, C., Tanzer, R., Hauryliuk, A., Kumar, S. P. N., Zimmerman, N., Kara, L. B., Presto, A. A., and R. Subramanian: Development of a general calibration model and long-term performance evaluation of low-cost sensors for air pollutant gas monitoring, Atmos. Meas. Tech., 12, 903–920, https://doi.org/10.5194/amt-12-903-2019, 2019. a
Masson, N., Piedrahita, R., and Hannigan, M.: Quantification method for electrolytic sensors in long-term monitoring of ambient air quality, Sensors, 15, 27283–27302, https://doi.org/10.3390/s151027283, 2015. a, b
Mead, M., Popoola, O., Stewart, G., Landshoff, P., Calleja, M., Hayes, M., Baldovi, J., McLeod, M., Hodgson, T., Dicks, J., Lewis, A., Cohen, J., Baron, R., Saffell, J. R., and Jones, R. L.: The use of electrochemical sensors for monitoring urban air quality in low-cost, high-density networks, Atmos. Environ., 70, 186–203, https://doi.org/10.1016/j.atmosenv.2012.11.060, 2013. a, b
Mijling, B., Jiang, Q., de Jonge, D., and Bocconi, S.: Field calibration of electrochemical NO2 sensors in a citizen science context, Atmos. Meas. Tech., 11, 1297–1312, https://doi.org/10.5194/amt-11-1297-2018, 2018. a
Mueller, M., Meyer, J., and Hueglin, C.: Design of an ozone and nitrogen dioxide sensor unit and its long-term operation within a sensor network in the city of Zurich, Atmos. Meas. Tech., 10, 3783–3799, https://doi.org/10.5194/amt-10-3783-2017, 2017. a
Munir, S., Mayfield, M., Coca, D., Jubb, S. A., and Osammor, O.: Analysing the performance of low-cost air quality sensors, their drivers, relative benefits and calibration in cities—A case study in Sheffield, Environ. Monit. Assess., 191, 1–22, https://doi.org/10.1007/s10661-019-7231-8, 2019. a
Nowack, P., Konstantinovskiy, L., Gardiner, H., and Cant, J.: Machine learning calibration of low-cost NO2 and PM10 sensors: non-linear algorithms and their impact on site transferability, Atmos. Meas. Tech., 14, 5637–5655, https://doi.org/10.5194/amt-14-5637-2021, 2021. a, b, c
Okorn, K. and Hannigan, M.: Improving Air Pollutant Metal Oxide Sensor Quantification Practices through: An Exploration of Sensor Signal Normalization, Multi-Sensor and Universal Calibration Model Generation, and Physical Factors Such as Co-Location Duration and Sensor Age, Atmosphere, 12, 645, https://doi.org/10.3390/atmos12050645, 2021. a, b
Papaconstantinou, R., Demosthenous, M., Bezantakos, S., Hadjigeorgiou, N., Costi, M., Stylianou, M., Symeou, E., Savvides, C., and Biskos, G.: Field evaluation of low-cost electrochemical air quality gas sensors under extreme temperature and relative humidity conditions, Atmos. Meas. Tech., 16, 3313–3329, https://doi.org/10.5194/amt-16-3313-2023, 2023. a
Rodriguez, J. D., Perez, A., and Lozano, J. A.: Sensitivity analysis of k-fold cross validation in prediction error estimation, IEEE T. Pattern Anal., 32, 569–575, https://doi.org/10.1109/TPAMI.2009.187, 2009. a
Sahu, R., Nagal, A., Dixit, K. K., Unnibhavi, H., Mantravadi, S., Nair, S., Simmhan, Y., Mishra, B., Zele, R., Sutaria, R., Motghare, V. M., Kar, P., and Tripathi, S. N.: Robust statistical calibration and characterization of portable low-cost air quality monitoring sensors to quantify real-time O3 and NO2 concentrations in diverse environments, Atmos. Meas. Tech., 14, 37–52, https://doi.org/10.5194/amt-14-37-2021, 2021. a
Schneider, P., Bartonova, A., Castell, N., Dauge, F. R., Gerboles, M., Hagler, G. S., Huglin, C., Jones, R. L., Khan, S., Lewis, A. C., Mijling, B., Müller, M., Penza, M., Spinelle, L., Stacey, B., Vogt, M., Wesseling, J., and Williams, R. W.: Toward a unified terminology of processing levels for low-cost air-quality sensors, Environ. Sci. Technol., 53, 8485–8487, https://doi.org/10.1021/acs.est.9b03950, 2019. a, b, c
Schultz, M. G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L. H., Mozaffari, A., and Stadtler, S.: Can deep learning beat numerical weather prediction?, Philos. T. Roy. Soc. A, 379, 20200097, https://doi.org/10.1098/rsta.2020.0097, 2021. a, b
Smith, K. R., Edwards, P. M., Ivatt, P. D., Lee, J. D., Squires, F., Dai, C., Peltier, R. E., Evans, M. J., Sun, Y., and Lewis, A. C.: An improved low-power measurement of ambient NO2 and O3 combining electrochemical sensor clusters and machine learning, Atmos. Meas. Tech., 12, 1325–1336, https://doi.org/10.5194/amt-12-1325-2019, 2019. a
Snyder, E. G., Watkins, T. H., Solomon, P. A., Thoma, E. D., Williams, R. W., Hagler, G. S., Shelow, D., Hindin, D. A., Kilaru, V. J., and Preuss, P. W.: The changing paradigm of air pollution monitoring, Environ. Sci. Technol., 47, 11369–11377, https://doi.org/10.1021/es4022602, 2013. a
Spinelle, L., Gerboles, M., Villani, M. G., Aleixandre, M., and Bonavitacola, F.: Field calibration of a cluster of low-cost available sensors for air quality monitoring. Part A: Ozone and nitrogen dioxide, Sensor. Actuat. B-Chem., 215, 249–257, https://doi.org/10.1016/j.snb.2015.03.031, 2015. a, b, c, d, e
Spinelle, L., Kotsev, A., Signorini, M., and Gerboles, M.: Evaluation of low-cost sensors for air pollution monitoring: Effect of gaseous interfering compounds and meteorological conditions, EUR 28601 EN, Publications Office of the European Union, https://doi.org/10.2760/548327, 2017. a, b, c, d
Suriano, D. and Penza, M.: Assessment of the performance of a low-cost air quality monitor in an indoor environment through different calibration models, Atmosphere, 13, 567, https://doi.org/10.3390/atmos13040567, 2022. a, b
Tagle, M., Rojas, F., Reyes, F., Vásquez, Y., Hallgren, F., Lindén, J., Kolev, D., Watne, Å. K., and Oyola, P.: Field performance of a low-cost sensor in the monitoring of particulate matter in Santiago, Chile, Environ. Monit. Assess., 192, 171, https://doi.org/10.1007/s10661-020-8118-4, 2020. a, b
Van Zoest, V., Osei, F. B., Stein, A., and Hoek, G.: Calibration of low-cost NO2 sensors in an urban air quality network, Atmos. Environ., 210, 66–75, https://doi.org/10.1016/j.atmosenv.2019.04.048, 2019. a, b, c
Vikram, S., Collier-Oxandale, A., Ostertag, M. H., Menarini, M., Chermak, C., Dasgupta, S., Rosing, T., Hannigan, M., and Griswold, W. G.: Evaluating and improving the reliability of gas-phase sensor system calibrations across new locations for ambient measurements and personal exposure monitoring, Atmos. Meas. Tech., 12, 4211–4239, https://doi.org/10.5194/amt-12-4211-2019, 2019. a, b, c
Wang, A., Machida, Y., deSouza, P., Mora, S., Duhl, T., Hudda, N., Durant, J. L., Duarte, F., and Ratti, C.: Leveraging machine learning algorithms to advance low-cost air sensor calibration in stationary and mobile settings, Atmos. Environ., 301, 119692, https://doi.org/10.1016/j.atmosenv.2023.119692, 2023. a, b
WHO: Health aspects of air pollution: results from the WHO project “Systematic review of health aspects of air pollution in Europe”, WHO Regional Office for Europe, Report Nr. E83080, p. 30, 2004. a
Zhu, Y., Chen, J., Bi, X., Kuhlmann, G., Chan, K. L., Dietrich, F., Brunner, D., Ye, S., and Wenig, M.: Spatial and temporal representativeness of point measurements for nitrogen dioxide pollution levels in cities, Atmos. Chem. Phys., 20, 13241–13251, https://doi.org/10.5194/acp-20-13241-2020, 2020. a
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. a, b, c, d
Short summary
This study examined the transferability of machine learning calibration models among low-cost sensor units targeting NO2 and NO. The global models were evaluated under similar and different emission conditions. To counter cross-sensitivity, the study proposed integrating O3 measurements from nearby reference stations, in Switzerland. The models show substantial improvement when O3 measurements are incorporated, which is more pronounced when in regions with elevated O3 concentrations.
This study examined the transferability of machine learning calibration models among low-cost...
