Articles | Volume 19, issue 5
https://doi.org/10.5194/gmd-19-1893-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-19-1893-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
05 Mar 2026
Development and technical paper |
| 05 Mar 2026
| 05 Mar 2026
Enabling fast greenhouse gas emissions inference from satellites with GATES: a Graph-Neural-Network Atmospheric Transport Emulation System
Elena Fillola
CORRESPONDING AUTHOR
School of Chemistry, University of Bristol, Bristol, UK
School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK
Raul Santos-Rodriguez
School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK
Rachel Tunnicliffe
School of Chemistry, University of Bristol, Bristol, UK
Jeffrey N. Clark
School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK
Nawid Keshtmand
School of Chemistry, University of Bristol, Bristol, UK
Anita Ganesan
School of Geographical Sciences, University of Bristol, Bristol, UK
Matthew Rigby
School of Chemistry, University of Bristol, Bristol, UK
Related authors
Rebecca H. Ward, Luke M. Western, Rachel L. Tunnicliffe, Elena Fillola, Aki Tsuruta, Tuula Aalto, and Anita L. Ganesan
Atmos. Meas. Tech., 19, 813–837, https://doi.org/10.5194/amt-19-813-2026, https://doi.org/10.5194/amt-19-813-2026, 2026
Short summary
Short summary
We studied methane emissions in Arctic Alaska using satellite observations to assess how well they can monitor this important greenhouse gas. We found that emission estimates varied depending on the satellite data product and were strongly affected by assumptions in the model. Our results highlight the need for careful interpretation of emissions from Arctic satellite data and thorough testing of models, with implications for reliable climate monitoring.
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
EGUsphere, https://doi.org/10.5194/egusphere-2025-4137, https://doi.org/10.5194/egusphere-2025-4137, 2025
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary
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.
Elena Fillola, Raul Santos-Rodriguez, Alistair Manning, Simon O'Doherty, and Matt Rigby
Geosci. Model Dev., 16, 1997–2009, https://doi.org/10.5194/gmd-16-1997-2023, https://doi.org/10.5194/gmd-16-1997-2023, 2023
Short summary
Short summary
Lagrangian particle dispersion models are used extensively for the estimation of greenhouse gas (GHG) fluxes using atmospheric observations. However, these models do not scale well as data volumes increase. Here, we develop a proof-of-concept machine learning emulator that can produce outputs similar to those of the dispersion model, but 50 000 times faster, using only meteorological inputs. This works demonstrates the potential of machine learning to accelerate GHG estimations across the globe.
Rebecca H. Ward, Luke M. Western, Rachel L. Tunnicliffe, Elena Fillola, Aki Tsuruta, Tuula Aalto, and Anita L. Ganesan
Atmos. Meas. Tech., 19, 813–837, https://doi.org/10.5194/amt-19-813-2026, https://doi.org/10.5194/amt-19-813-2026, 2026
Short summary
Short summary
We studied methane emissions in Arctic Alaska using satellite observations to assess how well they can monitor this important greenhouse gas. We found that emission estimates varied depending on the satellite data product and were strongly affected by assumptions in the model. Our results highlight the need for careful interpretation of emissions from Arctic satellite data and thorough testing of models, with implications for reliable climate monitoring.
Hélène De Longueville, Daniela B. Melo, Alison Redington, Alice Ramsden, Alexandre Danjou, Peter Andrews, Joseph Pitt, Brendan Murphy, Lionel Constantin, Kieran M. Stanley, Simon O'Doherty, Angelina Wenger, Dickon Young, Andreas Engel, Tanja Schuck, Katharina Meixner, Thomas Wagenhaeuser, Fides Gad, Martin K. Vollmer, Stefan Reimann, Michela Maoine, Jgor Arduini, Chris Lunder, Norbert Schmidtbauer, László Haszpra, Mihály Molnár, Arnoud Frumau, Cedric Couret, Matthew Rigby, Stephan Henne, Alistair Manning, and Anita Ganesan
EGUsphere, https://doi.org/10.5194/egusphere-2026-194, https://doi.org/10.5194/egusphere-2026-194, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
This study estimates emissions of hydrofluorocarbons, important greenhouse gases, in north-western Europe using atmospheric observations and atmospheric modelling. The estimates are compared with nationally reported emissions submitted to the United Nations. Overall, our results are consistent with reported values, although differences are found for some gases and countries. The findings indicate that emissions in north-western Europe are declining, reflecting the effects of climate regulations.
Luke M. Western, Stephen Bourguet, Molly Crotwell, Lei Hu, Paul B. Krummel, Hélène De Longueville, Alistair J. Manning, Jens Mühle, Dominique Rust, Isaac Vimont, Martin K. Vollmer, Minde An, Jgor Arduini, Andreas Engel, Paul J. Fraser, Anita L. Ganesan, Christina M. Harth, Chris Lunder, Michela Maione, Stephen A. Montzka, David Nance, Simon O'Doherty, Sunyoung Park, Stefan Reimann, Peter K. Salameh, Roland Schmidt, Kieran M. Stanley, Thomas Wagenhäuser, Dickon Young, Matt Rigby, Ronald G. Prinn, and Ray F. Weiss
Atmos. Chem. Phys., 25, 17761–17778, https://doi.org/10.5194/acp-25-17761-2025, https://doi.org/10.5194/acp-25-17761-2025, 2025
Short summary
Short summary
We used atmospheric measurements to estimate emissions of two hydrochlorofluorocarbon (HCFC) gases, called HCFC-123 and HCFC-124, that harm the ozone layer. Despite international regulation to stop their production, their emissions have not fallen. This may be linked to how they are used to make other chemicals. Our findings show that some banned substances are still reaching the atmosphere, likely through leaks during chemical production, which could slow the recovery of the ozone layer.
Luke M. Western, Matthew Rigby, Jens Mühle, Paul B. Krummel, Chris R. Lunder, Simon O'Doherty, Stefan Reimann, Martin K. Vollmer, Dickon Young, Ben Adam, Paul J. Fraser, Anita L. Ganesan, Christina M. Harth, Ove Hermansen, Jooil Kim, Ray L. Langenfelds, Zoë M. Loh, Blagoj Mitrevski, Joseph R. Pitt, Peter K. Salameh, Roland Schmidt, Kieran Stanley, Ann R. Stavert, Hsiang-Jui Wang, Ray F. Weiss, and Ronald G. Prinn
Earth Syst. Sci. Data, 17, 6557–6582, https://doi.org/10.5194/essd-17-6557-2025, https://doi.org/10.5194/essd-17-6557-2025, 2025
Short summary
Short summary
We used global measurements and an atmospheric model to estimate how emissions and abundances of 42 chemically and radiatively important trace gases have changed over time. These gases affect the Earth's radiative balance and the ozone layer. Our data sets help track progress in reducing emissions of these gases to the atmosphere. This work supports international efforts to protect the environment by providing clear, long-term, consistent data on how these gases are changing in the atmosphere.
Martin K. Vollmer, Joseph R. Pitt, Dickon Young, Stephan Henne, Blagoj Mitrevski, Jens Mühle, Anita Ganesan, Jgor Arduini, Alistair J. Manning, Thomas Wagenhäuser, Alison L. Redington, Brendan Murphy, Ray Gluckmann, Kieran M. Stanley, Paul B. Krummel, Chris R. Lunder, Jaegeun Yun, Dominique Rust, Angelina Wenger, Myriam Guillevic, Jooil Kim, Ray H. J. Wang, Tae Siek Rhee, Lionel Constantin, Arnoud Frumau, Christina M. Harth, Peter K. Salameh, Ove Hermansen, Andreas Engel, Simon O'Doherty, Sunyoung Park, Michela Maione, Paul J. Fraser, Ronald G. Prinn, Ray F. Weiss, and Stefan Reimann
EGUsphere, https://doi.org/10.5194/egusphere-2025-4824, https://doi.org/10.5194/egusphere-2025-4824, 2025
Short summary
Short summary
We provide atmospheric measurements of halogenated olefins from the Advanced Global Atmospheric Gases Experiments and we calculate NorthWest European Emissions.
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
EGUsphere, https://doi.org/10.5194/egusphere-2025-4137, https://doi.org/10.5194/egusphere-2025-4137, 2025
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary
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.
Piers M. Forster, Chris Smith, Tristram Walsh, William F. Lamb, Robin Lamboll, Christophe Cassou, Mathias Hauser, Zeke Hausfather, June-Yi Lee, Matthew D. Palmer, Karina von Schuckmann, Aimée B. A. Slangen, Sophie Szopa, Blair Trewin, Jeongeun Yun, Nathan P. Gillett, Stuart Jenkins, H. Damon Matthews, Krishnan Raghavan, Aurélien Ribes, Joeri Rogelj, Debbie Rosen, Xuebin Zhang, Myles Allen, Lara Aleluia Reis, Robbie M. Andrew, Richard A. Betts, Alex Borger, Jiddu A. Broersma, Samantha N. Burgess, Lijing Cheng, Pierre Friedlingstein, Catia M. Domingues, Marco Gambarini, Thomas Gasser, Johannes Gütschow, Masayoshi Ishii, Christopher Kadow, John Kennedy, Rachel E. Killick, Paul B. Krummel, Aurélien Liné, Didier P. Monselesan, Colin Morice, Jens Mühle, Vaishali Naik, Glen P. Peters, Anna Pirani, Julia Pongratz, Jan C. Minx, Matthew Rigby, Robert Rohde, Abhishek Savita, Sonia I. Seneviratne, Peter Thorne, Christopher Wells, Luke M. Western, Guido R. van der Werf, Susan E. Wijffels, Valérie Masson-Delmotte, and Panmao Zhai
Earth Syst. Sci. Data, 17, 2641–2680, https://doi.org/10.5194/essd-17-2641-2025, https://doi.org/10.5194/essd-17-2641-2025, 2025
Short summary
Short summary
In a rapidly changing climate, evidence-based decision-making benefits from up-to-date and timely information. Here we compile monitoring datasets to track real-world changes over time. To make our work relevant to policymakers, we follow methods from the Intergovernmental Panel on Climate Change (IPCC). Human activities are increasing the Earth's energy imbalance and driving faster sea-level rise compared to the IPCC assessment.
Hannah Chawner, Eric Saboya, Karina E. Adcock, Tim Arnold, Yuri Artioli, Caroline Dylag, Grant L. Forster, Anita Ganesan, Heather Graven, Gennadi Lessin, Peter Levy, Ingrid T. Luijkx, Alistair Manning, Penelope A. Pickers, Chris Rennick, Christian Rödenbeck, and Matthew Rigby
Atmos. Chem. Phys., 24, 4231–4252, https://doi.org/10.5194/acp-24-4231-2024, https://doi.org/10.5194/acp-24-4231-2024, 2024
Short summary
Short summary
The quantity of atmospheric potential oxygen (APO), derived from coincident measurements of carbon dioxide (CO2) and oxygen (O2), has been proposed as a tracer for fossil fuel CO2 emissions. In this model sensitivity study, we examine the use of APO for this purpose in the UK and compare our model to observations. We find that our model simulations are most sensitive to uncertainties relating to ocean fluxes and boundary conditions.
Tanja J. Schuck, Johannes Degen, Eric Hintsa, Peter Hoor, Markus Jesswein, Timo Keber, Daniel Kunkel, Fred Moore, Florian Obersteiner, Matt Rigby, Thomas Wagenhäuser, Luke M. Western, Andreas Zahn, and Andreas Engel
Atmos. Chem. Phys., 24, 689–705, https://doi.org/10.5194/acp-24-689-2024, https://doi.org/10.5194/acp-24-689-2024, 2024
Short summary
Short summary
We study the interhemispheric gradient of sulfur hexafluoride (SF6), a strong long-lived greenhouse gas. Its emissions are stronger in the Northern Hemisphere; therefore, mixing ratios in the Southern Hemisphere lag behind. Comparing the observations to a box model, the model predicts air in the Southern Hemisphere to be older. For a better agreement, the emissions used as model input need to be increased (and their spatial pattern changed), and we need to modify north–south transport.
Alison L. Redington, Alistair J. Manning, Stephan Henne, Francesco Graziosi, Luke M. Western, Jgor Arduini, Anita L. Ganesan, Christina M. Harth, Michela Maione, Jens Mühle, Simon O'Doherty, Joseph Pitt, Stefan Reimann, Matthew Rigby, Peter K. Salameh, Peter G. Simmonds, T. Gerard Spain, Kieran Stanley, Martin K. Vollmer, Ray F. Weiss, and Dickon Young
Atmos. Chem. Phys., 23, 7383–7398, https://doi.org/10.5194/acp-23-7383-2023, https://doi.org/10.5194/acp-23-7383-2023, 2023
Short summary
Short summary
Chlorofluorocarbons (CFCs) were used in Europe pre-1990, damaging the stratospheric ozone layer. Legislation has controlled production and use, and global emissions have decreased sharply. The global rate of decline in CFC-11 recently slowed and was partly attributed to illegal emission in eastern China. This study concludes that emissions of CFC-11 in western Europe have not contributed to the unexplained part of the global increase in CFC-11 observed in the last decade.
Elena Fillola, Raul Santos-Rodriguez, Alistair Manning, Simon O'Doherty, and Matt Rigby
Geosci. Model Dev., 16, 1997–2009, https://doi.org/10.5194/gmd-16-1997-2023, https://doi.org/10.5194/gmd-16-1997-2023, 2023
Short summary
Short summary
Lagrangian particle dispersion models are used extensively for the estimation of greenhouse gas (GHG) fluxes using atmospheric observations. However, these models do not scale well as data volumes increase. Here, we develop a proof-of-concept machine learning emulator that can produce outputs similar to those of the dispersion model, but 50 000 times faster, using only meteorological inputs. This works demonstrates the potential of machine learning to accelerate GHG estimations across the globe.
Angharad C. Stell, Michael Bertolacci, Andrew Zammit-Mangion, Matthew Rigby, Paul J. Fraser, Christina M. Harth, Paul B. Krummel, Xin Lan, Manfredi Manizza, Jens Mühle, Simon O'Doherty, Ronald G. Prinn, Ray F. Weiss, Dickon Young, and Anita L. Ganesan
Atmos. Chem. Phys., 22, 12945–12960, https://doi.org/10.5194/acp-22-12945-2022, https://doi.org/10.5194/acp-22-12945-2022, 2022
Short summary
Short summary
Nitrous oxide is a potent greenhouse gas and ozone-depleting substance, whose atmospheric abundance has risen throughout the contemporary record. In this work, we carry out the first global hierarchical Bayesian inversion to solve for nitrous oxide emissions. We derive increasing global nitrous oxide emissions over 2011–2020, which are mainly driven by emissions between 0° and 30°N, with the highest emissions recorded in 2020.
Luke M. Western, Alison L. Redington, Alistair J. Manning, Cathy M. Trudinger, Lei Hu, Stephan Henne, Xuekun Fang, Lambert J. M. Kuijpers, Christina Theodoridi, David S. Godwin, Jgor Arduini, Bronwyn Dunse, Andreas Engel, Paul J. Fraser, Christina M. Harth, Paul B. Krummel, Michela Maione, Jens Mühle, Simon O'Doherty, Hyeri Park, Sunyoung Park, Stefan Reimann, Peter K. Salameh, Daniel Say, Roland Schmidt, Tanja Schuck, Carolina Siso, Kieran M. Stanley, Isaac Vimont, Martin K. Vollmer, Dickon Young, Ronald G. Prinn, Ray F. Weiss, Stephen A. Montzka, and Matthew Rigby
Atmos. Chem. Phys., 22, 9601–9616, https://doi.org/10.5194/acp-22-9601-2022, https://doi.org/10.5194/acp-22-9601-2022, 2022
Short summary
Short summary
The production of ozone-destroying gases is being phased out. Even though production of one of the main ozone-depleting gases, called HCFC-141b, has been declining for many years, the amount that is being released to the atmosphere has been increasing since 2017. We do not know for sure why this is. A possible explanation is that HCFC-141b that was used to make insulating foams many years ago is only now escaping to the atmosphere, or a large part of its production is not being reported.
Guus J. M. Velders, John S. Daniel, Stephen A. Montzka, Isaac Vimont, Matthew Rigby, Paul B. Krummel, Jens Muhle, Simon O'Doherty, Ronald G. Prinn, Ray F. Weiss, and Dickon Young
Atmos. Chem. Phys., 22, 6087–6101, https://doi.org/10.5194/acp-22-6087-2022, https://doi.org/10.5194/acp-22-6087-2022, 2022
Short summary
Short summary
The emissions of hydrofluorocarbons (HFCs) have increased significantly in the past as a result of the phasing out of ozone-depleting substances. Observations indicate that HFCs are used much less in certain refrigeration applications than previously projected. Current policies are projected to reduce emissions and the surface temperature contribution of HFCs from 0.28–0.44 °C to 0.14–0.31 °C in 2100. The Kigali Amendment is projected to reduce the contributions further to 0.04 °C in 2100.
Alice E. Ramsden, Anita L. Ganesan, Luke M. Western, Matthew Rigby, Alistair J. Manning, Amy Foulds, James L. France, Patrick Barker, Peter Levy, Daniel Say, Adam Wisher, Tim Arnold, Chris Rennick, Kieran M. Stanley, Dickon Young, and Simon O'Doherty
Atmos. Chem. Phys., 22, 3911–3929, https://doi.org/10.5194/acp-22-3911-2022, https://doi.org/10.5194/acp-22-3911-2022, 2022
Short summary
Short summary
Quantifying methane emissions from different sources is a key focus of current research. We present a method for estimating sectoral methane emissions that uses ethane as a tracer for fossil fuel methane. By incorporating variable ethane : methane emission ratios into this model, we produce emissions estimates with improved uncertainty characterisation. This method will be particularly useful for studying methane emissions in areas with complex distributions of sources.
Jens Mühle, Lambert J. M. Kuijpers, Kieran M. Stanley, Matthew Rigby, Luke M. Western, Jooil Kim, Sunyoung Park, Christina M. Harth, Paul B. Krummel, Paul J. Fraser, Simon O'Doherty, Peter K. Salameh, Roland Schmidt, Dickon Young, Ronald G. Prinn, Ray H. J. Wang, and Ray F. Weiss
Atmos. Chem. Phys., 22, 3371–3378, https://doi.org/10.5194/acp-22-3371-2022, https://doi.org/10.5194/acp-22-3371-2022, 2022
Short summary
Short summary
Emissions of the strong greenhouse gas perfluorocyclobutane (c-C4F8) into the atmosphere have been increasing sharply since the early 2000s. These c-C4F8 emissions are highly correlated with the amount of hydrochlorofluorocarbon-22 produced to synthesize polytetrafluoroethylene (known for its non-stick properties) and related chemicals. From this process, c-C4F8 by-product is vented to the atmosphere. Avoiding these unnecessary c-C4F8 emissions could reduce the climate impact of this industry.
Andrew Zammit-Mangion, Michael Bertolacci, Jenny Fisher, Ann Stavert, Matthew Rigby, Yi Cao, and Noel Cressie
Geosci. Model Dev., 15, 45–73, https://doi.org/10.5194/gmd-15-45-2022, https://doi.org/10.5194/gmd-15-45-2022, 2022
Short summary
Short summary
We present a framework for estimating the sources and sinks (flux) of carbon dioxide from satellite data. The framework is statistical and yields measures of uncertainty alongside all estimates of flux and other parameters in the underlying model. It also allows us to generate other insights, such as the size of errors and biases in the data. The primary aim of this research was to develop a fully statistical flux inversion framework for use by atmospheric scientists.
Jan C. Minx, William F. Lamb, Robbie M. Andrew, Josep G. Canadell, Monica Crippa, Niklas Döbbeling, Piers M. Forster, Diego Guizzardi, Jos Olivier, Glen P. Peters, Julia Pongratz, Andy Reisinger, Matthew Rigby, Marielle Saunois, Steven J. Smith, Efisio Solazzo, and Hanqin Tian
Earth Syst. Sci. Data, 13, 5213–5252, https://doi.org/10.5194/essd-13-5213-2021, https://doi.org/10.5194/essd-13-5213-2021, 2021
Short summary
Short summary
We provide a synthetic dataset on anthropogenic greenhouse gas (GHG) emissions for 1970–2018 with a fast-track extension to 2019. We show that GHG emissions continued to rise across all gases and sectors. Annual average GHG emissions growth slowed, but absolute decadal increases have never been higher in human history. We identify a number of data gaps and data quality issues in global inventories and highlight their importance for monitoring progress towards international climate goals.
Mark F. Lunt, Alistair J. Manning, Grant Allen, Tim Arnold, Stéphane J.-B. Bauguitte, Hartmut Boesch, Anita L. Ganesan, Aoife Grant, Carole Helfter, Eiko Nemitz, Simon J. O'Doherty, Paul I. Palmer, Joseph R. Pitt, Chris Rennick, Daniel Say, Kieran M. Stanley, Ann R. Stavert, Dickon Young, and Matt Rigby
Atmos. Chem. Phys., 21, 16257–16276, https://doi.org/10.5194/acp-21-16257-2021, https://doi.org/10.5194/acp-21-16257-2021, 2021
Short summary
Short summary
We present an evaluation of the UK's methane emissions between 2013 and 2020 using a network of tall tower measurement sites. We find emissions that are consistent in both magnitude and trend with the UK's reported emissions, with a declining trend driven by a decrease in emissions from England. The impact of various components of the modelling set-up on these findings are explored through a number of sensitivity studies.
Cited articles
Alexe, M., Bergamaschi, P., Segers, A., Detmers, R., Butz, A., Hasekamp, O., Guerlet, S., Parker, R., Boesch, H., Frankenberg, C., Scheepmaker, R. A., Dlugokencky, E., Sweeney, C., Wofsy, S. C., and Kort, E. A.: Inverse modelling of CH4 emissions for 2010–2011 using different satellite retrieval products from GOSAT and SCIAMACHY, Atmos. Chem. Phys., 15, 113–133, https://doi.org/10.5194/acp-15-113-2015, 2015.
Ba, J. L., Jamie, R. K., and Hinton, G. E.: Layer Normalization, arXiv [preprint], https://doi.org/10.48550/arXiv.1607.06450, 2016.
Baker, D. F.: TransCom 3 inversion intercomparison: Impact of transport model errors on the interannual variability of regional CO2 fluxes, Global Biogeochemical Cycles, 20, 1988–2003, https://doi.org/10.1029/2004GB002439, 2006a.
Baker, D. F.: Variational data assimilation for atmospheric CO2, Tellus B: Chemical and Physical Meteorology, 58, 359–365, https://doi.org/10.1111/j.1600-0889.2006.00218.x, 2006b.
Battaglia, P. W., Hamrick, J. B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V. F., Malinowski, M., Tacchetti, A., Raposo, D., Santoro, A., Faulkner, R., Gülçehre, Ç., Song, H. F., Ballard, A. J., Gilmer, J., Dahl, G. E., Vaswani, A., Allen, K. R., Nash, C., Langston, V., Dyer, C., Heess, N., Wierstra, D., Kohli, P., Botvinick, M. M., Vinyals, O., Li, Y., and Pascanu, R.: Relational inductive biases, deep learning, and graph networks, CoRR, arXiv, arXiv:1806.01261, 2018.
Bergamaschi, P., Karstens, U., Manning, A. J., Saunois, M., Tsuruta, A., Berchet, A., Vermeulen, A. T., Arnold, T., Janssens-Maenhout, G., Hammer, S., Levin, I., Schmidt, M., Ramonet, M., Lopez, M., Lavric, J., Aalto, T., Chen, H., Feist, D. G., Gerbig, C., Haszpra, L., Hermansen, O., Manca, G., Moncrieff, J., Meinhardt, F., Necki, J., Galkowski, M., O'Doherty, S., Paramonova, N., Scheeren, H. A., Steinbacher, M., and Dlugokencky, E.: Inverse modelling of European CH4 emissions during 2006–2012 using different inverse models and reassessed atmospheric observations, Atmos. Chem. Phys., 18, 901–920, https://doi.org/10.5194/acp-18-901-2018, 2018.
Bousquet, P. P.: Regional Changes in Carbon Dioxide Fluxes of Land and Oceans Since 1980, Science, 290, 1342–1346, https://doi.org/10.1126/science.290.5495.1342, 2000.
Brioude, J., Angevine, W. M., McKeen, S. A., and Hsie, E.-Y.: Numerical uncertainty at mesoscale in a Lagrangian model in complex terrain, Geosci. Model Dev., 5, 1127–1136, https://doi.org/10.5194/gmd-5-1127-2012, 2012.
Cartwright, L., Zammit-Mangion, A., and Deutscher, N. M.: Emulation of greenhouse-gas sensitivities using variational autoencoders, Environmetrics, 34, e2754, https://doi.org/10.1002/env.2754, 2023.
Dadheech, N., He, T.-L., and Turner, A. J.: High-resolution greenhouse gas flux inversions using a machine learning surrogate model for atmospheric transport, Atmos. Chem. Phys., 25, 5159–5174, https://doi.org/10.5194/acp-25-5159-2025, 2025.
Essery, R., Best, M., and Cox, P.: MOSES 2.2 Technical Documentation, Hadley Centre, Met Office, https://jules.jchmr.org/sites/default/files/2023-06/JULES-HCTN-30.pdf (last access: February 2026), 2001.
European Commission and United States of America: Global Methane Pledge, https://www.ccacoalition.org/resources/global-methane-pledge (last access: February 2026), 2021.
Fasoli, B., Lin, J. C., Bowling, D. R., Mitchell, L., and Mendoza, D.: Simulating atmospheric tracer concentrations for spatially distributed receptors: updates to the Stochastic Time-Inverted Lagrangian Transport model's R interface (STILT-R version 2), Geosci. Model Dev., 11, 2813–2824, https://doi.org/10.5194/gmd-11-2813-2018, 2018.
Feng, L., Palmer, P. I., Parker, R. J., Lunt, M. F., and Bösch, H.: Methane emissions are predominantly responsible for record-breaking atmospheric methane growth rates in 2020 and 2021, Atmos. Chem. Phys., 23, 4863–4880, https://doi.org/10.5194/acp-23-4863-2023, 2023.
Fillola, E. and Clark, J.: extract_iris_met, Zenodo [code], https://doi.org/10.5281/ZENODO.16634862, 2025.
Fillola, E. and Tunnicliffe, R.: LPDM footprint dataset – Brazil, Zenodo [data set], https://doi.org/10.5281/zenodo.16748754, 2025.
Fillola, E., Santos-Rodriguez, R., Manning, A., O'Doherty, S., and Rigby, M.: A machine learning emulator for Lagrangian particle dispersion model footprints: a case study using NAME, Geosci. Model Dev., 16, 1997–2009, https://doi.org/10.5194/gmd-16-1997-2023, 2023.
Fillola, E., Clark, J., and Keshtmand, N.: GATES: A Graph-Neural-Network Atmospheric Transport Emulation System, Zenodo [code], https://doi.org/10.5281/ZENODO.16679175, 2025.
Ganesan, A. L., Rigby, M., Zammit-Mangion, A., Manning, A. J., Prinn, R. G., Fraser, P. J., Harth, C. M., Kim, K.-R., Krummel, P. B., Li, S., Mühle, J., O'Doherty, S. J., Park, S., Salameh, P. K., Steele, L. P., and Weiss, R. F.: Characterization of uncertainties in atmospheric trace gas inversions using hierarchical Bayesian methods, Atmos. Chem. Phys., 14, 3855–3864, https://doi.org/10.5194/acp-14-3855-2014, 2014.
Ganesan, A. L., Rigby, M., Lunt, M. F., Parker, R. J., Boesch, H., Goulding, N., Umezawa, T., Zahn, A., Chatterjee, A., Prinn, R. G., Tiwari, Y. K., van der Schoot, M., and Krummel, P. B.: Atmospheric observations show accurate reporting and little growth in India's methane emissions, Nature Communications, 8, 836, https://doi.org/10.1038/s41467-017-00994-7, 2017.
He, T.-L., Dadheech, N., Thompson, T. M., and Turner, A. J.: FootNet v1.0: development of a machine learning emulator of atmospheric transport, Geosci. Model Dev., 18, 1661–1671, https://doi.org/10.5194/gmd-18-1661-2025, 2025.
Inness, A., Ades, M., Agustí-Panareda, A., Barré, J., Benedictow, A., Blechschmidt, A.-M., Dominguez, J. J., Engelen, R., Eskes, H., Flemming, J., Huijnen, V., Jones, L., Kipling, Z., Massart, S., Parrington, M., Peuch, V.-H., Razinger, M., Remy, S., Schulz, M., and Suttie, M.: The CAMS reanalysis of atmospheric composition, Atmos. Chem. Phys., 19, 3515–3556, https://doi.org/10.5194/acp-19-3515-2019, 2019.
Jacob, D. J., Varon, D. J., Cusworth, D. H., Dennison, P. E., Frankenberg, C., Gautam, R., Guanter, L., Kelley, J., McKeever, J., Ott, L. E., Poulter, B., Qu, Z., Thorpe, A. K., Worden, J. R., and Duren, R. M.: Quantifying methane emissions from the global scale down to point sources using satellite observations of atmospheric methane, Atmos. Chem. Phys., 22, 9617–9646, https://doi.org/10.5194/acp-22-9617-2022, 2022.
Janardanan, R., Maksyutov, S., Tsuruta, A., Wang, F., Tiwari, Y. K., Valsala, V., Ito, A., Yoshida, Y., Kaiser, J. W., Janssens-Maenhout, G., Arshinov, M., Sasakawa, M., Tohjima, Y., Worthy, D. E. J., Dlugokencky, E. J., Ramonet, M., Arduini, J., Lavric, J. V., Piacentino, S., Krummel, P. B., Langenfelds, R. L., Mammarella, I., and Matsunaga, T.: Country-Scale Analysis of Methane Emissions with a High-Resolution Inverse Model Using GOSAT and Surface Observations, Remote Sensing, 12, https://doi.org/10.3390/rs12030375, 2020.
Janssens-Maenhout, G., Crippa, M., Guizzardi, D., Muntean, M., Schaaf, E., Dentener, F., Bergamaschi, P., Pagliari, V., Olivier, J. G. J., Peters, J. A. H. W., van Aardenne, J. A., Monni, S., Doering, U., Petrescu, A. M. R., Solazzo, E., and Oreggioni, G. D.: EDGAR v4.3.2 Global Atlas of the three major greenhouse gas emissions for the period 1970–2012, Earth Syst. Sci. Data, 11, 959–1002, https://doi.org/10.5194/essd-11-959-2019, 2019.
Joint CEOS-CGMS Working Group on Climate – Greenhouse Gas Task Team: Roadmap for a Coordinated Implementation of Carbon Dioxide and Methane Monitoring from Space, CEOS-CGMS, https://ceos.org/document_management/Publications/Publications-and-Key-Documents/Atmosphere/CEOS_CGMS_GHG_Roadmap_Issue_2_V1.0_FINAL.pdf (last access: February 2026), 2024.
Jones, A., Thomson, D., Hort, M., and Devenish, B.: The U. K. Met Office's next-generation atmospheric dispersion model, NAME III, in: Air Pollution Modeling and Its Application XVII, 580–589, https://doi.org/10.1007/978-0-387-68854-1_62, 2007.
Kaminski, T., Heimann, M., and Giering, R.: A coarse grid three-dimensional global inverse model of the atmospheric transport: 1. Adjoint model and Jacobian matrix, Journal of Geophysical Research: Atmospheres, 104, 18535–18553, https://doi.org/10.1029/1999jd900147, 1999.
Keisler, R.: Forecasting Global Weather with Graph Neural Networks, arXiv [preprint], https://doi.org/10.48550/arXiv.2202.07575, 2022.
Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., and Battaglia, P.: Learning skillful medium-range global weather forecasting, Science, 382, 1416–1421, https://doi.org/10.1126/science.adi2336, 2023.
Leip, A., Skiba, U., Vermeulen, A., and Thompson, R. L.: A complete rethink is needed on how greenhouse gas emissions are quantified for national reporting, Atmospheric Environment, 174, 237–240, https://doi.org/10.1016/j.atmosenv.2017.12.006, 2018.
Loshchilov, I. and Hutter, F.: Decoupled Weight Decay Regularization, in: International Conference on Learning Representations, arXiv [preprint], https://doi.org/10.48550/arXiv.1711.05101, 2019.
Maasakkers, J. D., Jacob, D. J., Sulprizio, M. P., Scarpelli, T. R., Nesser, H., Sheng, J.-X., Zhang, Y., Hersher, M., Bloom, A. A., Bowman, K. W., Worden, J. R., Janssens-Maenhout, G., and Parker, R. J.: Global distribution of methane emissions, emission trends, and OH concentrations and trends inferred from an inversion of GOSAT satellite data for 2010–2015, Atmos. Chem. Phys., 19, 7859–7881, https://doi.org/10.5194/acp-19-7859-2019, 2019.
Met Office: UKCP18 Guidance: Bias correction, https://www.metoffice.gov.uk/binaries/content/assets/metofficegovuk/pdf/research/ukcp/ukcp18-guidance---how-to-bias-correct.pdf (last access: February 2026), 2018.
Met Office: Global NWP meteorological data for Met Office NAME dispersion model (Mk9: July 2015–2017) (Mk9), CEDA (Centre for Environmental Data Analysis) [data set], https://data.ceda.ac.uk/badc/name_nwp/data/global/UMG_Mk9 (last access: September 2025), 2025a.
Met Office: Global NWP meteorological data for Met Office NAME dispersion model (Mk10: June 2017–May 2022) (Mk10), CEDA (Centre for Environmental Data Analysis) [data set], https://data.ceda.ac.uk/badc/name_nwp/data/global/UMG_Mk10 (last access: September 2025), 2025b.
Nair, V. and Hinton, G. E.: Rectified linear units improve restricted boltzmann machines, in: ICML'10: Proceedings of the 27th International Conference on International Conference on Machine Learning, 807–814, https://dl.acm.org/doi/10.5555/3104322.3104425 (last access: February 2026), 2010.
Parker, R. and Boesch, H.: University of Leicester GOSAT Proxy XCH4 v9.0. Centre for Environmental Data Analysis [data set], https://doi.org/10.5285/18ef8247f52a4cb6a14013f8235cc1eb, 2020.
Parker, R. J., Webb, A., Boesch, H., Somkuti, P., Barrio Guillo, R., Di Noia, A., Kalaitzi, N., Anand, J. S., Bergamaschi, P., Chevallier, F., Palmer, P. I., Feng, L., Deutscher, N. M., Feist, D. G., Griffith, D. W. T., Hase, F., Kivi, R., Morino, I., Notholt, J., Oh, Y.-S., Ohyama, H., Petri, C., Pollard, D. F., Roehl, C., Sha, M. K., Shiomi, K., Strong, K., Sussmann, R., Té, Y., Velazco, V. A., Warneke, T., Wennberg, P. O., and Wunch, D.: A decade of GOSAT Proxy satellite CH4 observations, Earth Syst. Sci. Data, 12, 3383–3412, https://doi.org/10.5194/essd-12-3383-2020, 2020.
Peters, W., Miller, J. B., Whitaker, J., Denning, A. S., Hirsch, A., Krol, M. C., Zupanski, D., Bruhwiler, L., and Tans, P. P.: An ensemble data assimilation system to estimate CO2 surface fluxes from atmospheric trace gas observations, Journal of Geophysical Research, 110, https://doi.org/10.1029/2005jd006157, 2005.
Pfaff, T., Fortunato, M., Sanchez-Gonzalez, A., and Battaglia, P.: Learning Mesh-Based Simulation with Graph Networks, in: International Conference on Learning Representations, https://doi.org/10.48550/arXiv.1607.06450, 2020.
Pisso, I., Sollum, E., Grythe, H., Kristiansen, N. I., Cassiani, M., Eckhardt, S., Arnold, D., Morton, D., Thompson, R. L., Groot Zwaaftink, C. D., Evangeliou, N., Sodemann, H., Haimberger, L., Henne, S., Brunner, D., Burkhart, J. F., Fouilloux, A., Brioude, J., Philipp, A., Seibert, P., and Stohl, A.: The Lagrangian particle dispersion model FLEXPART version 10.4, Geosci. Model Dev., 12, 4955–4997, https://doi.org/10.5194/gmd-12-4955-2019, 2019.
Rigby, M., Tunnicliffe, R., lukewestern, hanchawn, ag12733, aliceramsden, Jones, G., Young, D., Ward, R., Angharad, ANickless-Bristol, and joe-pitt: ACRG-Bristol/acrg: ACRG v0.2.0 (v0.2.0), Zenodo [code], https://doi.org/10.5281/zenodo.6834888, 2022.
Roten, D., Wu, D., Fasoli, B., Oda, T., and Lin, J. C.: An interpolation method to reduce the computational time in the stochastic Lagrangian particle dispersion modeling of spatially dense XCO2 retrievals, Earth and Space Science, 8, https://doi.org/10.1029/2020ea001343, 2021.
Sanchez-Gonzalez, A., Godwin, J., Pfaff, T., Ying, R., Leskovec, J., and Battaglia, P. W.: Learning to simulate complex physics with graph networks, in: Proceedings of the 37th International Conference on Machine Learning, arXiv [preprint], 8459–8468, https://doi.org/10.48550/arXiv.2002.09405, 2020.
Saunois, M., Martinez, A., Poulter, B., Zhang, Z., Raymond, P. A., Regnier, P., Canadell, J. G., Jackson, R. B., Patra, P. K., Bousquet, P., Ciais, P., Dlugokencky, E. J., Lan, X., Allen, G. H., Bastviken, D., Beerling, D. J., Belikov, D. A., Blake, D. R., Castaldi, S., Crippa, M., Deemer, B. R., Dennison, F., Etiope, G., Gedney, N., Höglund-Isaksson, L., Holgerson, M. A., Hopcroft, P. O., Hugelius, G., Ito, A., Jain, A. K., Janardanan, R., Johnson, M. S., Kleinen, T., Krummel, P. B., Lauerwald, R., Li, T., Liu, X., McDonald, K. C., Melton, J. R., Mühle, J., Müller, J., Murguia-Flores, F., Niwa, Y., Noce, S., Pan, S., Parker, R. J., Peng, C., Ramonet, M., Riley, W. J., Rocher-Ros, G., Rosentreter, J. A., Sasakawa, M., Segers, A., Smith, S. J., Stanley, E. H., Thanwerdas, J., Tian, H., Tsuruta, A., Tubiello, F. N., Weber, T. S., van der Werf, G. R., Worthy, D. E. J., Xi, Y., Yoshida, Y., Zhang, W., Zheng, B., Zhu, Q., Zhu, Q., and Zhuang, Q.: Global Methane Budget 2000–2020, Earth Syst. Sci. Data, 17, 1873–1958, https://doi.org/10.5194/essd-17-1873-2025, 2025.
Scarpelli, T. R., Jacob, D. J., Grossman, S., Lu, X., Qu, Z., Sulprizio, M. P., Zhang, Y., Reuland, F., Gordon, D., and Worden, J. R.: Updated Global Fuel Exploitation Inventory (GFEI) for methane emissions from the oil, gas, and coal sectors: evaluation with inversions of atmospheric methane observations, Atmos. Chem. Phys., 22, 3235–3249, https://doi.org/10.5194/acp-22-3235-2022, 2022.
Schmidli, J., Frei, C., and Vidale, P. L.: Downscaling from GCM precipitation: a benchmark for dynamical and statistical downscaling methods, International Journal of Climatology, 26, 679–689, https://doi.org/10.1002/joc.1287, 2006.
Schroeder, R., McDonald, K. C., Chapman, B. D., Jensen, K., Podest, E., Tessler, Z. D., Bohn, T. J., and Zimmermann, R.: Development and Evaluation of a Multi-Year Fractional Surface Water Data Set Derived from Active/Passive Microwave Remote Sensing Data, Remote Sensing, 7, 16688–16732, https://doi.org/10.3390/rs71215843, 2015.
Stein, A. F., Draxler, R. R., Rolph, G. D., Stunder, B. J. B., Cohen, M. D., and Ngan, F.: NOAA's HYSPLIT Atmospheric Transport and Dispersion Modeling System, Bulletin of the American Meteorological Society, 96, 2059–2077, https://doi.org/10.1175/BAMS-D-14-00110.1, 2015.
Thompson, R. L., Krishnankutty, N., Pisso, I., Schneider, P., Stebel, K., Sasakawa, M., Stohl, A., and Platt, S.: Efficient use of a Lagrangian Particle Dispersion Model for atmospheric inversions using satellite observations of column mixing ratios, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2025-147, 2025.
Tunnicliffe, R. L., Ganesan, A. L., Parker, R. J., Boesch, H., Gedney, N., Poulter, B., Zhang, Z., Lavrič, J. V., Walter, D., Rigby, M., Henne, S., Young, D., and O'Doherty, S.: Quantifying sources of Brazil's CH4 emissions between 2010 and 2018 from satellite data, Atmos. Chem. Phys., 20, 13041–13067, https://doi.org/10.5194/acp-20-13041-2020, 2020.
Uber Technologies Inc: H3: Uber's Hexagonal Hierarchical Spatial Index (3.7.7), PyPi, https://pypi.org/project/h3/3.7.7/ (last access: January 2025), 2024.
Veefkind, J. P., Aben, I., McMullan, K., Förster, H., Vries, J. de, Otter, G., Claas, J., Eskes, H. J., Haan, J. F. de, Kleipool, Q., Weele, M. van, Hasekamp, O., Hoogeveen, R., Landgraf, J., Snel, R., Tol, P., Ingmann, P., Voors, R., Kruizinga, B., Vink, R., Visser, H., and Levelt, P. F.: TROPOMI on the ESA Sentinel-5 Precursor: A GMES mission for global observations of the atmospheric composition for climate, air quality and ozone layer applications, Remote Sensing of Environment, 120, 70–83, https://doi.org/10.1016/j.rse.2011.09.027, 2012.
Vojta, M., Plach, A., Thompson, R. L., and Stohl, A.: A comprehensive evaluation of the use of Lagrangian particle dispersion models for inverse modeling of greenhouse gas emissions, Geosci. Model Dev., 15, 8295–8323, https://doi.org/10.5194/gmd-15-8295-2022, 2022.
Ward, R. H., Western, L. M., Tunnicliffe, R. L., Fillola, E., Tsuruta, A., Aalto, T., and Ganesan, A. L.: Uncertainty and retrieval sensitivity in TROPOMI-based methane inversions over the North Slope of Alaska, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2025-4230, 2025.
Western, L. M., Ramsden, A. E., Ganesan, A. L., Boesch, H., Parker, R. J., Scarpelli, T. R., Tunnicliffe, R. L., and Rigby, M.: Estimates of North African Methane Emissions from 2010 to 2017 Using GOSAT Observations, Environ. Sci. Technol. Lett., 8, 626–632, https://doi.org/10.1021/acs.estlett.1c00327, 2021.
Wilson, C., Chipperfield, M. P., Gloor, M., Parker, R. J., Boesch, H., McNorton, J., Gatti, L. V., Miller, J. B., Basso, L. S., and Monks, S. A.: Large and increasing methane emissions from eastern Amazonia derived from satellite data, 2010–2018, Atmos. Chem. Phys., 21, 10643–10669, https://doi.org/10.5194/acp-21-10643-2021, 2021.
Worden, J. R., Pandey, S., Zhang, Y., Cusworth, D. H., Qu, Z., Bloom, A. A., Ma, S., Maasakkers, J. D., Byrne, B., Duren, R., Crisp, D., Gordon, D., and Jacob, D. J.: Verifying Methane Inventories and Trends With Atmospheric Methane Data, AGU Advances, 4, e2023AV000871, https://doi.org/10.1029/2023AV000871, 2023.
Short summary
Satellite-based greenhouse gas measurements can be used in “inverse models” to improve emissions reporting, but one of the key components, the simulations of atmospheric transport, struggle to scale to large datasets. We introduce the model GATES, an AI-driven emulator that outputs transport plumes 1000× faster than traditional models. Applied to Brazil’s methane emissions, GATES produces estimates consistent with physics-based methods, offering a scalable path for timely emissions monitoring.
Satellite-based greenhouse gas measurements can be used in “inverse models” to improve emissions...
