Articles | Volume 15, issue 24
Research article
14 Dec 2022
Research article |  | 14 Dec 2022

Volcanic cloud detection using Sentinel-3 satellite data by means of neural networks: the Raikoke 2019 eruption test case

Ilaria Petracca, Davide De Santis, Matteo Picchiani, Stefano Corradini, Lorenzo Guerrieri, Fred Prata, Luca Merucci, Dario Stelitano, Fabio Del Frate, Giorgia Salvucci, and Giovanni Schiavon


Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2022-173', Anonymous Referee #1, 03 Jul 2022
    • AC2: 'Reply on RC1', Ilaria Petracca, 13 Aug 2022
  • RC2: 'Comment on amt-2022-173', Anonymous Referee #2, 10 Jul 2022
    • AC1: 'Reply on RC2', Ilaria Petracca, 12 Aug 2022
    • AC3: 'Reply on RC2 Final', Ilaria Petracca, 13 Aug 2022
  • RC3: 'Comment on amt-2022-173', Anonymous Referee #3, 16 Jul 2022
    • AC4: 'Reply on RC3', Ilaria Petracca, 13 Aug 2022

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Ilaria Petracca on behalf of the Authors (08 Sep 2022)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (23 Sep 2022) by Claudia Timmreck
RR by Anonymous Referee #3 (05 Oct 2022)
RR by Anonymous Referee #1 (14 Oct 2022)
ED: Publish as is (20 Oct 2022) by Claudia Timmreck
AR by Ilaria Petracca on behalf of the Authors (02 Nov 2022)  Manuscript 
Short summary
The authors propose a near-real-time procedure for the detection of volcanic clouds by means of Sentinel-3 satellite data and neural networks. The algorithm results in an automatic image classification where ashy pixels are distinguished from other surfaces with remarkable accuracy. The model is considerably faster if compared to other approaches which are time consuming, case specific, and not automatic. The algorithm can be significantly helpful for emergency management during eruption events.