Articles | Volume 14, issue 2
https://doi.org/10.5194/tc-14-565-2020
https://doi.org/10.5194/tc-14-565-2020
Research article
 | 
13 Feb 2020
Research article |  | 13 Feb 2020

Deep learning applied to glacier evolution modelling

Jordi Bolibar, Antoine Rabatel, Isabelle Gouttevin, Clovis Galiez, Thomas Condom, and Eric Sauquet

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
ED: Publish subject to revisions (further review by editor and referees) (01 Nov 2019) by Valentina Radic
AR by Jordi Bolibar on behalf of the Authors (03 Dec 2019)  Author's response   Manuscript 
ED: Referee Nomination & Report Request started (04 Dec 2019) by Valentina Radic
RR by Fabien Maussion (24 Dec 2019)
ED: Publish subject to minor revisions (review by editor) (14 Jan 2020) by Valentina Radic
AR by Jordi Bolibar on behalf of the Authors (16 Jan 2020)  Author's response   Manuscript 
ED: Publish as is (18 Jan 2020) by Valentina Radic
AR by Jordi Bolibar on behalf of the Authors (20 Jan 2020)
Download
Short summary
We introduce a novel approach for simulating glacier mass balances using a deep artificial neural network (i.e. deep learning) from climate and topographical data. This has been added as a component of a new open-source parameterized glacier evolution model. Deep learning is found to outperform linear machine learning methods, mainly due to its nonlinearity. Potential applications range from regional mass balance reconstructions from observations to simulations for past and future climates.