02 Nov 2022
 | 02 Nov 2022

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 Hubert Wagner, Martyn P. Chipperfield, Rocío Barrio Guilló, Chris Wilson, and Hartmut Boesch

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: final response (author comments only)

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
  • RC2: 'Comment on egusphere-2022-924', Luis Guanter, 02 Dec 2022

Peter Joyce et al.


Total article views: 704 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
385 306 13 704 48 9 12
  • HTML: 385
  • PDF: 306
  • XML: 13
  • Total: 704
  • Supplement: 48
  • BibTeX: 9
  • EndNote: 12
Views and downloads (calculated since 02 Nov 2022)
Cumulative views and downloads (calculated since 02 Nov 2022)

Viewed (geographical distribution)

Total article views: 844 (including HTML, PDF, and XML) Thereof 844 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 21 Mar 2023
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.