Articles | Volume 19, issue 16
https://doi.org/10.5194/amt-19-5387-2026
https://doi.org/10.5194/amt-19-5387-2026
Research article
 | 
19 Aug 2026
Research article |  | 19 Aug 2026

A machine learning method for estimating atmospheric trace gas concentration baselines

Kirstin Gerrand, Elena Fillola, Alistair J. Manning, Jgor Arduini, Paul B. Krummel, Chris R. Lunder, Jens Mühle, Simon O'Doherty, Sunyoung Park, Ronald G. Prinn, Stefan Reimann, Dickon Young, and Matthew Rigby

Related authors

GATES-Background 0.2.0: Emulating background greenhouse gas mole fractions for regional atmospheric inverse modelling with graph neural networks
Nawid Keshtmand, Elena Fillola, Jeff Clark, Raul Santos-Rodriguez, and Matthew Rigby
EGUsphere, https://doi.org/10.5194/egusphere-2026-3361,https://doi.org/10.5194/egusphere-2026-3361, 2026
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
What controls tropospheric carbon monoxide in the remote Southern Hemisphere?
Clara M. Nussbaumer, Colette L. Heald, Teresa Campos, Eric A. Kort, Paul B. Krummel, Ray L. Langenfelds, Monica Madronich, Kathryn McKain, Gabrielle Pétron, Ann Stavert, and Steven C. Wofsy
EGUsphere, https://doi.org/10.5194/egusphere-2026-5476,https://doi.org/10.5194/egusphere-2026-5476, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Using high frequency observations of δ13C-CH4 and δ2H-CH4 and uncertain regional isotopic signatures to estimate sources of UK methane emissions
Alice E. Ramsden, Anita L. Ganesan, Matthew Rigby, Chris Rennick, Tim Arnold, Emmal Safi, Edward Chung, Dafina Kikaj, Cameron Yeo, Dave Lowry, Pete Levy, Simon O'Doherty, Kieran M. Stanley, Dickon Young, Joe Pitt, Damien Martin, Morgan Lopez, Michel Ramonet, Grant L. Forster, Arnoud Frumau, and Alistair J. Manning
Atmos. Chem. Phys., 26, 11421–11448, https://doi.org/10.5194/acp-26-11421-2026,https://doi.org/10.5194/acp-26-11421-2026, 2026
Short summary
Confirming the minimal role of in-atmosphere production on the global HFC-23 budget using a 3D chemical and transport model
Ben Adam, Rayne Holland, Daniel Van Hoomissen, James B. Burkholder, M. Anwar H. Khan, Paul Griffiths, Jens Mühle, Dudley Shallcross, and Matt Rigby
Atmos. Chem. Phys., 26, 10979–10996, https://doi.org/10.5194/acp-26-10979-2026,https://doi.org/10.5194/acp-26-10979-2026, 2026
Short summary
Constraining the atmospheric hydrogen oxidation and soil sink seasonal cycles using HFC-152a
Kane Stone, Candice Chen, Susan Solomon, Luke M. Western, Paul B. Krummel, Gabrielle Pétron, Jens Mühle, and Simon O'Doherty
Atmos. Chem. Phys., 26, 10241–10253, https://doi.org/10.5194/acp-26-10241-2026,https://doi.org/10.5194/acp-26-10241-2026, 2026
Short summary

Cited articles

Altmann, A., Toloşi, L., Sander, O., and Lengauer, T.: Permutation importance: a corrected feature importance measure, Bioinformatics, 26, 1340–1347, https://doi.org/10.1093/bioinformatics/btq134, 2010. a
Arnold, T., Manning, A. J., Kim, J., Li, S., Webster, H., Thomson, D., Mühle, J., Weiss, R. F., Park, S., and O'Doherty, S.: Inverse modelling of CF4 and NF3 emissions in East Asia, Atmos. Chem. Phys., 18, 13305–13320, https://doi.org/10.5194/acp-18-13305-2018, 2018. a, b, c
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001. a
Brokamp, C., Jandarov, R., Hossain, M., and Ryan, P.: Predicting daily urban fine particulate matter concentrations using a random forest model, Environ. Sci. Technol., 52, 4173–4179, https://doi.org/10.1021/acs.est.7b05381, 2018. a
Burkholder, J., Hondnebrog, O., McDonald, B., Orkin, V. L., Papadimitriou, V., and Hoomissen, D. V.: Summary of Abundances, Lifetimes, ODPs, REs, GWPs, GTPs, Scientific Assessment of Ozone Depletion 2022, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=936562 (last access: 20 August 2025), 2023. a
Download
Short summary
To analyse long-term trends in atmospheric trace gas concentrations, it is important to identify data points minimally affected by local pollution sources or air masses carried from other latitudes or altitudes. Traditional methods for detecting these “baselines” are computationally expensive or lack a basis in physical principles. This paper introduces a machine-learning method that uses meteorological data and offers significantly lower computational costs compared to physics-based techniques.
Share