Articles | Volume 16, issue 10
https://doi.org/10.5194/amt-16-2627-2023
https://doi.org/10.5194/amt-16-2627-2023
Research article
 | 
30 May 2023
Research article |  | 30 May 2023

Using a deep neural network to detect methane point sources and quantify emissions from PRISMA hyperspectral satellite images

Peter Joyce, Cristina Ruiz Villena, Yahui Huang, Alex Webb, Manuel Gloor, Fabien H. Wagner, Martyn P. Chipperfield, Rocío Barrio Guilló, Chris Wilson, and Hartmut Boesch

Related authors

Analysis of Antarctic ozone trends from 1979 to 2023
Haotian He, Martyn P. Chipperfield, Sandip S. Dhomse, Wuhu Feng, Shujie Chang, Yajuan Li, Mark Weber, and Saffron Heddell
EGUsphere, https://doi.org/10.5194/egusphere-2026-560,https://doi.org/10.5194/egusphere-2026-560, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
UV/Vis Stratospheric Air Mass Factors considering photochemistry at two Antarctic stations
Laura Gomez-Martin, Cristina Prados-Roman, Martyn P. Chipperfield, Michel Van Roozendael, Olga Puentedura, Monica Navarro-Comas, Hector Ochoa, and Margarita Yela
EGUsphere, https://doi.org/10.5194/egusphere-2026-17,https://doi.org/10.5194/egusphere-2026-17, 2026
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary
The Anomalously Warm Summer of 2023 Over Greenland as Compared to Previous Record Melt Summers of 2012 and 2019
Alexander Mchedlishvili, Marco Vountas, and Hartmut Bösch
EGUsphere, https://doi.org/10.5194/egusphere-2025-6424,https://doi.org/10.5194/egusphere-2025-6424, 2026
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Application of XBAER aerosol optical depth retrieval algorithm to hyperspectral EnMAP satellite data
Simon Laffoy, Marco Vountas, Linlu Mei, and Hartmut Bösch
Atmos. Meas. Tech., 19, 293–306, https://doi.org/10.5194/amt-19-293-2026,https://doi.org/10.5194/amt-19-293-2026, 2026
Short summary
Indirect climate forcing from ozone depleting substances
William J. Collins, John S. Daniel, Martyn P. Chipperfield, Martin Cussac, Makoto Deushi, Gregory Faluvegi, Paul Griffiths, Øivind Hodnebrog, Larry W. Horowitz, James Keeble, Douglas Kinnison, Vaishali Naik, Fiona M. O'Connor, Drew Shindell, Simone Tilmes, Kostas Tsigaridis, Zihao Wang, and James Weber
EGUsphere, https://doi.org/10.5194/egusphere-2025-6033,https://doi.org/10.5194/egusphere-2025-6033, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary

Cited articles

Allen, D. T., Torres, V. M., Thomas, J., Sullivan, D. W., Harrison, M., Hendler, A., Herndon, S. C., Kolb, C. E., Fraser, M. P., and Hill, A. D.: Measurements of methane emissions at natural gas production sites in the United States, P. Natl. Acad. Sci. USA, 110, 17768–17773, 2013. 
Alvarez, R. A., Zavala-Araiza, D., Lyon, D. R., Allen, D. T., Barkley, Z. R., Brandt, A. R., Davis, K. J., Herndon, S. C., Jacob, D. J., and Karion, A.: Assessment of methane emissions from the US oil and gas supply chain, Science, 361, 186–188, 2018. 
Brandt, A. R., Heath, G. A., and Cooley, D.: Methane leaks from natural gas systems follow extreme distributions, Environ. Sci. Technol., 50, 12512–12520, 2016. 
Chollet, F.: Keras: Deep Learning for humans, Release 2.12.0, GitHub [code], https://github.com/keras-team/keras (last access: 1 May 2023), 2015. 
Cusworth, D. H., Jacob, D. J., Varon, D. J., Chan Miller, C., Liu, X., Chance, K., Thorpe, A. K., Duren, R. M., Miller, C. E., Thompson, D. R., Frankenberg, C., Guanter, L., and Randles, C. A.: Potential of next-generation imaging spectrometers to detect and quantify methane point sources from space, Atmos. Meas. Tech., 12, 5655–5668, https://doi.org/10.5194/amt-12-5655-2019, 2019. 
Download
Short summary
Methane emissions are responsible for a lot of the warming caused by the greenhouse effect, much of which comes from a small number of point sources. We can identify methane point sources by analysing satellite data, but it requires a lot of time invested by experts and is prone to very high errors. Here, we produce a neural network that can automatically identify methane point sources and estimate the mass of methane that is being released per hour and are able to do so with far smaller errors.
Share