Articles | Volume 16, issue 10
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


Interactive discussion

Status: closed

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
    • AC1: 'Reply on RC1', Peter Joyce, 28 Mar 2023
  • RC2: 'Comment on egusphere-2022-924', Luis Guanter, 02 Dec 2022
    • AC2: 'Reply on RC2', Peter Joyce, 28 Mar 2023

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Peter Joyce on behalf of the Authors (28 Mar 2023)  Author's response   Author's tracked changes   Manuscript 
ED: Publish as is (29 Mar 2023) by Alexander Kokhanovsky
AR by Peter Joyce on behalf of the Authors (15 Apr 2023)  Author's response   Manuscript 
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.