Articles | Volume 17, issue 9
https://doi.org/10.5194/amt-17-2583-2024
© 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-17-2583-2024
© 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 May 2024
Research article |
| 03 May 2024
| 03 May 2024
CH4Net: a deep learning model for monitoring methane super-emitters with Sentinel-2 imagery
Anna Vaughan
CORRESPONDING AUTHOR
Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, UK
Gonzalo Mateo-García
Trillium Technologies Ltd., London EC2N 2AX, UK
Image Processing Laboratory, University of Valencia, 46980 Valencia, Spain
Luis Gómez-Chova
Image Processing Laboratory, University of Valencia, 46980 Valencia, Spain
Vít Růžička
Department of Computer Science, University of Oxford, Oxford OX1 2JD, UK
Luis Guanter
Research Institute of Water and Environmental Engineering (IIAMA), Universitat Politècnica de València, 46022 Valencia, Spain
Environmental Defense Fund, Reguliersgracht 79, 1017 LN Amsterdam, the Netherlands
Itziar Irakulis-Loitxate
Research Institute of Water and Environmental Engineering (IIAMA), Universitat Politècnica de València, 46022 Valencia, Spain
United Nations Environment Programme, International Methane Emissions Observatory, 1, rue Miollis, Building VII 75015 Paris, France
Related authors
Anna Vaughan, Will Tebbutt, J. Scott Hosking, and Richard E. Turner
Geosci. Model Dev., 15, 251–268, https://doi.org/10.5194/gmd-15-251-2022, https://doi.org/10.5194/gmd-15-251-2022, 2022
Short summary
Short summary
We develop a new method for climate downscaling, i.e. transforming low-resolution climate model output to high-resolution projections, using a deep-learning model known as a convolutional conditional neural process. This model is shown to outperform an ensemble of baseline methods for downscaling daily maximum temperature and precipitation and provides a powerful new downscaling framework for climate impact studies.
Javier Roger, Luis Guanter, and Javier Gorroño
EGUsphere, https://doi.org/10.5194/egusphere-2025-1917, https://doi.org/10.5194/egusphere-2025-1917, 2025
Short summary
Short summary
Detection of methane point source emissions with satellite-based imaging spectrometres is assessed. We select EMIT and EnMAP instruments for this task. We extract the probabiliy of detection for both instruments using WRF-LES simulations. We compare our results with real plumes, which shows the consistency of the models. Detection and monitoring efforts can be optimized by filtering data based on these results, reducing unnecessary searches and increasing the action taken on these emissions.
Russell Doughty, Yujie Wang, Jennifer Johnson, Nicholas Parazoo, Troy Magney, Zoe Pierrat, Xiangming Xiao, Luis Guanter, Philipp Köhler, Christian Frankenberg, Peter Somkuti, Shuang Ma, Yuanwei Qin, Sean Crowell, and Berrien Moore III
EGUsphere, https://doi.org/10.22541/essoar.168167172.20799710/v1, https://doi.org/10.22541/essoar.168167172.20799710/v1, 2024
Preprint archived
Short summary
Short summary
Here we present a novel model of global photosynthesis, ChloFluo, which uses spaceborne chlorophyll fluorescence to estimate the amount of photosynthetically active radiation absorbed by chlorophyll. Potential uses of our model are to advance our understanding of the timing and magnitude of photosynthesis, its effect on atmospheric carbon dioxide fluxes, and vegetation response to climate events and change.
Javier Roger, Luis Guanter, Javier Gorroño, and Itziar Irakulis-Loitxate
Atmos. Meas. Tech., 17, 1333–1346, https://doi.org/10.5194/amt-17-1333-2024, https://doi.org/10.5194/amt-17-1333-2024, 2024
Short summary
Short summary
Methane emissions can be identified using remote sensing, but surface-related structures disturb detection. In this work, a variation of the matched filter method that exploits a large fraction of the near-infrared range (1000–2500 nm) is applied. In comparison to the raw matched filter, it reduces background noise and strongly attenuates the surface-related artifacts, which leads to a greater detection capability. We propose this variation as a standard methodology for methane detection.
Berend J. Schuit, Joannes D. Maasakkers, Pieter Bijl, Gourav Mahapatra, Anne-Wil van den Berg, Sudhanshu Pandey, Alba Lorente, Tobias Borsdorff, Sander Houweling, Daniel J. Varon, Jason McKeever, Dylan Jervis, Marianne Girard, Itziar Irakulis-Loitxate, Javier Gorroño, Luis Guanter, Daniel H. Cusworth, and Ilse Aben
Atmos. Chem. Phys., 23, 9071–9098, https://doi.org/10.5194/acp-23-9071-2023, https://doi.org/10.5194/acp-23-9071-2023, 2023
Short summary
Short summary
Using two machine learning models, which were trained on TROPOMI methane satellite data, we detect 2974 methane plumes, so-called super-emitters, in 2021. We detect methane emissions globally related to urban areas or landfills, coal mining, and oil and gas production. Using our monitoring system, we identify 94 regions with frequent emissions. For 12 locations, we target high-resolution satellite instruments to enlarge and identify the exact infrastructure responsible for the emissions.
Javier Gorroño, Daniel J. Varon, Itziar Irakulis-Loitxate, and Luis Guanter
Atmos. Meas. Tech., 16, 89–107, https://doi.org/10.5194/amt-16-89-2023, https://doi.org/10.5194/amt-16-89-2023, 2023
Short summary
Short summary
We present a methane flux rate retrieval methodology using the Sentinel-2 mission, validating the algorithm for different scenes and plumes. The detection limit is 1000–2000 kg h−1 for homogeneous scenes and temporally invariant surfaces and above 5000 kg h−1 for heterogeneous ones. Dominant quantification errors are wind-related or plume mask-related. For heterogeneous scenes, the surface structure underlying the methane plume can become a dominant source of uncertainty.
Daniel J. Jacob, Daniel J. Varon, Daniel H. Cusworth, Philip E. Dennison, Christian Frankenberg, Ritesh Gautam, Luis Guanter, John Kelley, Jason McKeever, Lesley E. Ott, Benjamin Poulter, Zhen Qu, Andrew K. Thorpe, John R. Worden, and Riley M. Duren
Atmos. Chem. Phys., 22, 9617–9646, https://doi.org/10.5194/acp-22-9617-2022, https://doi.org/10.5194/acp-22-9617-2022, 2022
Short summary
Short summary
We review the capability of satellite observations of atmospheric methane to quantify methane emissions on all scales. We cover retrieval methods, precision requirements, inverse methods for inferring emissions, source detection thresholds, and observations of system completeness. We show that current instruments already enable quantification of regional and national emissions including contributions from large point sources. Coverage and resolution will increase significantly in coming years.
Elena Sánchez-García, Javier Gorroño, Itziar Irakulis-Loitxate, Daniel J. Varon, and Luis Guanter
Atmos. Meas. Tech., 15, 1657–1674, https://doi.org/10.5194/amt-15-1657-2022, https://doi.org/10.5194/amt-15-1657-2022, 2022
Short summary
Short summary
This study seeks to present the as-yet-unknown potential use of WorldView-3 for the mapping of methane point source emissions. The proposed retrieval methodology is based on the idea that the spectral channels not affected by methane can be used to predict the methane-affected band through regression analysis. The results show the precise location of 26 independent point emissions over different methane hotspot regions worldwide, which prove the game-changing potential that this mission entails.
Anna Vaughan, Will Tebbutt, J. Scott Hosking, and Richard E. Turner
Geosci. Model Dev., 15, 251–268, https://doi.org/10.5194/gmd-15-251-2022, https://doi.org/10.5194/gmd-15-251-2022, 2022
Short summary
Short summary
We develop a new method for climate downscaling, i.e. transforming low-resolution climate model output to high-resolution projections, using a deep-learning model known as a convolutional conditional neural process. This model is shown to outperform an ensemble of baseline methods for downscaling daily maximum temperature and precipitation and provides a powerful new downscaling framework for climate impact studies.
Luis Guanter, Cédric Bacour, Andreas Schneider, Ilse Aben, Tim A. van Kempen, Fabienne Maignan, Christian Retscher, Philipp Köhler, Christian Frankenberg, Joanna Joiner, and Yongguang Zhang
Earth Syst. Sci. Data, 13, 5423–5440, https://doi.org/10.5194/essd-13-5423-2021, https://doi.org/10.5194/essd-13-5423-2021, 2021
Short summary
Short summary
Sun-induced chlorophyll fluorescence (SIF) is an electromagnetic signal emitted by plants in the red and far-red parts of the spectrum. It has a functional link to photosynthesis and can be measured by satellite instruments, which makes it an important variable for the remote monitoring of the photosynthetic activity of vegetation ecosystems around the world. In this contribution we present a SIF dataset derived from the new Sentinel-5P TROPOMI missions.
Cited articles
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., Karion, A., Kort, E. A., Lamb, B. K., Lauvaux, T., Maasakkers, J. D., Marchese, A. J., Omara, M., Pacala, S. W., Peischl, J., Robinson, A. L., Shepson, P. B., Sweeney, C., Townsend-Small, A., Wofsy, S. C., and Hamburg, S. P.: Assessment of methane emissions from the US oil and gas supply chain, Science, 361, 186–188, 2018. a
Aybar, C., Ysuhuaylas, L., Loja, J., Gonzales, K., Herrera, F., Bautista, L., Yali, R., Flores, A., Diaz, L., Cuenca, N., Espinoza, W., Prudencio, F., Llactayo, V., Montero, D., Sudmanns, M., Tiede, D., Mateo-García, G., and Gómez-Chova, L.: CloudSEN12, a global dataset for semantic understanding of cloud and cloud shadow in Sentinel-2, Scientific Data, 9, 782, https://doi.org/10.1038/s41597-022-01878-2, 2022. a
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale, arXiv [preprint], https://doi.org/10.48550/arXiv.2010.11929, 3 June 2020. a
Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez, V., Gascon, F., Hoersch, B., Isola, C., Laberinti, P., Martimort, P., Meygret, A., Spoto, F., Sy, O., Marchese, F., and Bargellini, P.: Sentinel-2: ESA's optical high-resolution mission for GMES operational services, Remote Sens. Environ., 120, 25–36, 2012. a
Gorroño, J., Varon, D. J., Irakulis-Loitxate, I., and Guanter, L.: Understanding the potential of Sentinel-2 for monitoring methane point emissions, Atmos. Meas. Tech., 16, 89–107, https://doi.org/10.5194/amt-16-89-2023, 2023. a
Groshenry, A., Giron, C., Lauvaux, T., d'Aspremont, A., and Ehret, T.: Detecting Methane Plumes using PRISMA: Deep Learning Model and Data Augmentation, arXiv [preprint], https://doi.org/10.48550/arXiv.2211.15429, 17 November 2022. a
Guanter, L., Irakulis-Loitxate, I., Gorroño, J., Sánchez-García, E., Cusworth, D. H., Varon, D. J., Cogliati, S., and Colombo, R.: Mapping methane point emissions with the PRISMA spaceborne imaging spectrometer, Remote Sens. Environ., 265, 112671, https://doi.org/10.1016/j.rse.2021.112671, 2021. a
Irakulis-Loitxate, I., Guanter, L., Liu, Y.-N., Varon, D. J., Maasakkers, J. D., Zhang, Y., Chulakadabba, A., Wofsy, S. C., Thorpe, A. K., Duren, R. M., Frankenberg, C., Lyon, D. R., Hmiel, B., Cusworth, D. H., Zhang, Y., Segl, K., Gorroño, J., Sánchez-García, E., Sulprizio, M. P., Cao, K., Zhu, H., Liang, J., Li, X., Aben, I., and Jacob, D. J.: Satellite-based survey of extreme methane emissions in the Permian basin, Science Advances, 7, eabf4507, https://doi.org/10.1126/sciadv.abf4507, 2021. a
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. a, b
Jeppesen, J. H., Jacobsen, R. H., Inceoglu, F., and Toftegaard, T. S.: A cloud detection algorithm for satellite imagery based on deep learning, Remote Sens. Environ., 229, 247–259, 2019. a
Jongaramrungruang, S., Thorpe, A. K., Matheou, G., and Frankenberg, C.: MethaNet – An AI-driven approach to quantifying methane point-source emission from high-resolution 2-D plume imagery, Remote Sens. Environ., 269, 112809, https://doi.org/10.1016/j.rse.2021.112809, 2022. a
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 22 December 2014. a
López-Puigdollers, D., Mateo-García, G., and Gómez-Chova, L.: Benchmarking Deep Learning Models for Cloud Detection in Landsat-8 and Sentinel-2 Images, Remote Sens.-Basel, 13, 992, https://doi.org/10.3390/rs13050992, 2021. a
Maasakkers, J. D., Varon, D. J., Elfarsdóttir, A., McKeever, J., Jervis, D., Mahapatra, G., Pandey, S., Lorente, A., Borsdorff, T., Foorthuis, L. R., Schuit, B. J., Tol, P., van Kempen, T. A., van Hees, R., and Aben, I.: Using satellites to uncover large methane emissions from landfills, Science Advances, 8, eabn9683, https://doi.org/10.1126/sciadv.abn96832022. a, b
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 5–9 October 2015, Proceedings, Part III 18, Springer, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a
Roy, D. P., Wulder, M. A., Loveland, T. R., Woodcock, C. E., Allen, R. G., Anderson, M. C., Helder, D., Irons, J. R., Johnson, D. M., Kennedy, R., Scambos, T. A., Schaaf, C. B., Schott, J. R., Sheng, Y., Vermote, E. F., Belward, A. S., Bindschadler, R., Cohen, W. B., Gao, F., Hipple, J. D., Hostert, P., Huntington, J., Justice, C. O., Kilic, A., Kovalskyy, V., Lee, Z. P., Lymburner, L., Masek, J. G., McCorkel, J., Shuai, Y., Trezza, R., Vogelmann, J., Wynne, R. H., and Zhu, Z.: Landsat-8: Science and product vision for terrestrial global change research, Remote Sens. Environ., 145, 154–172, 2014. a
Saunois, M., Stavert, A. R., Poulter, B., Bousquet, P., Canadell, J. G., Jackson, R. B., Raymond, P. A., Dlugokencky, E. J., Houweling, S., Patra, P. K., Ciais, P., Arora, V. K., Bastviken, D., Bergamaschi, P., Blake, D. R., Brailsford, G., Bruhwiler, L., Carlson, K. M., Carrol, M., Castaldi, S., Chandra, N., Crevoisier, C., Crill, P. M., Covey, K., Curry, C. L., Etiope, G., Frankenberg, C., Gedney, N., Hegglin, M. I., Höglund-Isaksson, L., Hugelius, G., Ishizawa, M., Ito, A., Janssens-Maenhout, G., Jensen, K. M., Joos, F., Kleinen, T., Krummel, P. B., Langenfelds, R. L., Laruelle, G. G., Liu, L., Machida, T., Maksyutov, S., McDonald, K. C., McNorton, J., Miller, P. A., Melton, J. R., Morino, I., Müller, J., Murguia-Flores, F., Naik, V., Niwa, Y., Noce, S., O'Doherty, S., Parker, R. J., Peng, C., Peng, S., Peters, G. P., Prigent, C., Prinn, R., Ramonet, M., Regnier, P., Riley, W. J., Rosentreter, J. A., Segers, A., Simpson, I. J., Shi, H., Smith, S. J., Steele, L. P., Thornton, B. F., Tian, H., Tohjima, Y., Tubiello, F. N., Tsuruta, A., Viovy, N., Voulgarakis, A., Weber, T. S., van Weele, M., van der Werf, G. R., Weiss, R. F., Worthy, D., Wunch, D., Yin, Y., Yoshida, Y., Zhang, W., Zhang, Z., Zhao, Y., Zheng, B., Zhu, Q., Zhu, Q., and Zhuang, Q.: The Global Methane Budget 2000–2017, Earth Syst. Sci. Data, 12, 1561–1623, https://doi.org/10.5194/essd-12-1561-2020, 2020. a
Schuit, B. J., Maasakkers, J. D., Bijl, P., Mahapatra, G., van den Berg, A.-W., Pandey, S., Lorente, A., Borsdorff, T., Houweling, S., Varon, D. J., McKeever, J., Jervis, D., Girard, M., Irakulis-Loitxate, I., Gorroño, J., Guanter, L., Cusworth, D. H., and Aben, I.: Automated detection and monitoring of methane super-emitters using satellite data, Atmos. Chem. Phys., 23, 9071–9098, https://doi.org/10.5194/acp-23-9071-2023, 2023. a
Sentinel Hub: Sentinel-2 L1C, https://www.sentinel-hub.com/, last access: 25 April 2024. a
Sherwin, E. D., Rutherford, J. S., Chen, Y., Aminfard, S., Kort, E. A., Jackson, R. B., and Brandt, A. R.: Single-blind validation of space-based point-source detection and quantification of onshore methane emissions, Sci. Rep.-UK, 13, 3836, https://doi.org/10.1038/s41598-023-30761-2, 2023. a
Sinergise Ltd., S. L.: Sentinel Hub, https://www.sentinel-hub.com (last access: 10 August 2023), 2023. a
Stocker, T.: Climate change 2013: the physical science basis: Working Group I contribution to the Fifth assessment report of the Intergovernmental Panel on Climate Change, Cambridge University Press, ISBN 978-1-107-05799-1 hardback, ISBN 978-1-107-66182-0 paperback, 2014. a
Tollefson, J.: Scientists raise alarm over `dangerously fast' growth in atmospheric methane, Nature, https://doi.org/10.1038/d41586-022-00312-2, 8 February 2022. a
Vaughan, A.: ch4net (Revision 568db19), Hugging Face [data set], https://doi.org/10.57967/hf/2117, 2024. a
Zavala-Araiza, D., Alvarez, R. A., Lyon, D. R., Allen, D. T., Marchese, A. J., Zimmerle, D. J., and Hamburg, S. P.: Super-emitters in natural gas infrastructure are caused by abnormal process conditions, Nat. Commun., 8, 1–10, 2017. a
Short summary
Methane is a potent greenhouse gas that has been responsible for around 25 % of global warming since the industrial revolution. Consequently identifying and mitigating methane emissions comprise an important step in combating the climate crisis. We develop a new deep learning model to automatically detect methane plumes from satellite images and demonstrate that this can be applied to monitor large methane emissions resulting from the oil and gas industry.
Methane is a potent greenhouse gas that has been responsible for around 25 % of global warming...
