Journal cover Journal topic
The Cryosphere An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 4.790 IF 4.790
  • IF 5-year value: 5.921 IF 5-year
    5.921
  • CiteScore value: 5.27 CiteScore
    5.27
  • SNIP value: 1.551 SNIP 1.551
  • IPP value: 5.08 IPP 5.08
  • SJR value: 3.016 SJR 3.016
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 63 Scimago H
    index 63
  • h5-index value: 51 h5-index 51
Discussion papers
https://doi.org/10.5194/tc-2019-163
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-2019-163
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 26 Jul 2019

Submitted as: research article | 26 Jul 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal The Cryosphere (TC).

Deep learning applied to glacier evolution modelling

Jordi Bolibar1,2, Antoine Rabatel1, Isabelle Gouttevin3, Clovis Galiez4, Thomas Condom1, and Eric Sauquet2 Jordi Bolibar et al.
  • 1Univ. Grenoble Alpes, CNRS, IRD, G-INP, Institut des Géosciences de l'Environnement (IGE, UMR 5001), Grenoble, France
  • 2Irstea, UR RiverLy, Lyon-Villeurbanne, France
  • 3Univ. Grenoble Alpes, Université de Toulouse, Météo-France, CNRS, CNRM, Centre d'Études de la Neige, Grenoble, France
  • 4Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK, Grenoble, France

Abstract. We present a parameterized glacier evolution model, with a surface mass balance (SMB) component based on a deep artificial neural network (i.e. deep learning). While most glacier models tend to incorporate more and more physical processes, here we take an alternative approach by creating a parameterized model based on data science. Annual glacier-wide SMBs can be simulated using either deep learning or Lasso (regularized multilinear regression), whereas the glacier geometry is updated using a glacier-specific parameterization. We compare and cross-validate our nonlinear deep learning SMB model against other standard linear statistical methods on a dataset of 32 French alpine glaciers. Deep learning is found to outperform linear methods, with improved explained variance (up to +64 % in space and +108 % in time) and accuracy (up to +47 % in space and +58 % in time), resulting in an estimated r2 of 0.77 and RMSE of 0.51 m.w.e. Substantial nonlinear structures are captured by deep learning, with around 35 % of nonlinear behaviour in the temporal dimension. For the glacier geometry evolution, the main uncertainties come from the ice thickness data used to initialize the model. These results should encourage the use of deep learning in glacier modelling as a powerful nonlinear tool, capable of capturing the nonlinearities of the climate and glacier systems, that can serve to reconstruct or simulate SMB time series for individual glaciers at a regional scale for past and future climates.

Jordi Bolibar et al.
Interactive discussion
Status: open (until 20 Sep 2019)
Status: open (until 20 Sep 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Jordi Bolibar et al.
Model code and software

ALPGM v1.0 J. Bolibar https://doi.org/10.5281/zenodo.3269678

Jordi Bolibar et al.
Viewed  
Total article views: 368 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
261 104 3 368 12 1 1
  • HTML: 261
  • PDF: 104
  • XML: 3
  • Total: 368
  • Supplement: 12
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 26 Jul 2019)
Cumulative views and downloads (calculated since 26 Jul 2019)
Viewed (geographical distribution)  
Total article views: 114 (including HTML, PDF, and XML) Thereof 114 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 18 Aug 2019
Publications Copernicus
Download
Short summary
We present a glacier evolution model, whose main novelty is its component to compute the mass balance changes, based on a deep artificial neural network (i.e. deep learning). Glacier mass balances are reconstructed using meteorological and topographical data. Deep learning is found to outperform linear methods, especially due to its nonlinearity. Potential applications range from regional mass balance reconstruction to simulations for past and future climates.
We present a glacier evolution model, whose main novelty is its component to compute the mass...
Citation