02 Nov 2022
02 Nov 2022
Status: this preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).

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

Peter Joyce1,2,3, Cristina Ruiz Villena4,5, Yahui Huang2,3, Alex Webb4,5, Manuel Gloor1, Fabien Hubert Wagner6,7, Martyn P. Chipperfield2,3, Rocío Barrio Guilló4, Chris Wilson2,3, and Hartmut Boesch4,5 Peter Joyce et al.
  • 1School of Geography, University of Leeds, Leeds, United Kingdom
  • 2National Centre for Earth Observation, University of Leeds, Leeds, United Kingdom
  • 3School of Earth and Environment, University of Leeds, Leeds, United Kingdom
  • 4University of Leicester, Leicester, United Kingdom
  • 5National Centre for Earth Observation, University of Leicester, Leicester, United Kingdom
  • 6Institute of Environment and Sustainability, University of California, Los Angeles, CA, USA
  • 7Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove, Pasadena, CA 91109, USA

Abstract. Anthropogenic emissions of methane (CH4) make up a considerable contribution towards the Earth’s radiative budget since pre-industrial times. This is because large amounts of methane are emitted from human activities and the global warming potential of methane is high. The majority of anthropogenic fossil methane emissions to the atmosphere originate from a large number of small (point) sources. Thus, detection and accurate, rapid quantification of such emissions is vital to enable the reduction of emissions to help mitigate future climate change. There exist a number of instruments on satellites that measure radiation at methane-absorbing wavelengths, which have sufficiently high spatial resolution that can be used for detecting highly spatially localised methane 'point sources' (areas on the order of km2). Searching for methane plumes in methane sensitive satellite images using classical methods, such as thresholding and clustering, can be useful but are time-consuming and often inaccurate. Here, we develop a deep neural network to identify and quantify methane point source emissions from hyperspectral imagery from the PRecursore IperSpettrale della Missione Applicativa (PRISMA) satellite with 30-m spatial resolution. The moderately high spectral and spatial resolution as well as considerable global coverage and free access to data make PRISMA a good candidate for methane plume detection. The neural network was trained with simulated synthetic methane plumes generated with the Large Eddy Simulation extension of the Weather Research and Forecasting model (WRF-LES), which we embedded into PRISMA images. The deep neural network was successful at locating plumes with F1-score, precision and recall of 0.95, 0.96 and 0.92, respectively, and was able to quantify emission rates with a mean error of 24 %. The neural network was furthermore able to locate several plumes in real-world images. We have thus demonstrated that our method can be effective in locating and quantifying methane point source emissions in near real time from 30-m resolution satellite data which can aid us in mitigating future climate change.

Peter Joyce et al.

Status: open (until 07 Dec 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2022-924', Anonymous Referee #1, 23 Nov 2022 reply
  • RC2: 'Comment on egusphere-2022-924', Luis Guanter, 02 Dec 2022 reply

Peter Joyce et al.


Total article views: 316 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
204 104 8 316 25 3 7
  • HTML: 204
  • PDF: 104
  • XML: 8
  • Total: 316
  • Supplement: 25
  • BibTeX: 3
  • EndNote: 7
Views and downloads (calculated since 02 Nov 2022)
Cumulative views and downloads (calculated since 02 Nov 2022)

Viewed (geographical distribution)

Total article views: 452 (including HTML, PDF, and XML) Thereof 452 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 06 Dec 2022
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 are 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 lower errors.