Preprints
https://doi.org/10.5194/egusphere-2022-435
https://doi.org/10.5194/egusphere-2022-435
 
16 Jun 2022
16 Jun 2022
Status: this preprint is open for discussion.

Improving interpretation of sea-level projections through a machine-learning-based local explanation approach

Jeremy Rohmer1, Remi Thieblemont1, Goneri Le Cozannet1, Heiko Goelzer2, and Gael Durand3 Jeremy Rohmer et al.
  • 1BRGM, 3 av. C. Guillemin, 45060, Orléans, France
  • 2NORCE Norwegian Research Centre, Bjerknes Centre for Climate Research, Bergen, Norway
  • 3IGE, University Grenoble Alpes, Grenoble, France

Abstract. Process-based projections of the sea-level contribution from land ice components are often obtained from simulations using a complex chain of numerical models. Because of their importance in supporting the decision-making process for coastal risk assessment and adaptation, improving the interpretability of these projections is of great interest. To this end, we adopt the local attribution approach developed in the machine learning community by combining the game-theoretic approach known as ‘SHAP’ (SHapley Additive exPlanation) with machine-learning regression models. We apply our methodology to a subset of the multi-model ensemble study of the future contribution of the Greenland ice sheet to sea-level, taking into account different modelling choices related to (1) the numerical implementation, (2) the initial conditions, and (3) the modelling of ice-sheet processes. This allows us to quantify the influence of particular modelling decisions, which is directly expressed in terms of sea level change contribution. This type of diagnosis can be performed on any member of the ensemble, and we show in the Greenland case how the aggregation of the local attribution analyses can help guide future model development as well as scientific interpretation, particularly with regard to spatial model resolution and to retreat parametrisation.

Jeremy Rohmer et al.

Status: open (until 11 Aug 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Jeremy Rohmer et al.

Jeremy Rohmer et al.

Viewed

Total article views: 160 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
117 38 5 160 1 1
  • HTML: 117
  • PDF: 38
  • XML: 5
  • Total: 160
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 16 Jun 2022)
Cumulative views and downloads (calculated since 16 Jun 2022)

Viewed (geographical distribution)

Total article views: 92 (including HTML, PDF, and XML) Thereof 92 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 02 Jul 2022
Download
Short summary
To improve the interpretability of process-based projections of the sea-level contribution from land ice components, we apply the machine-learning-based ‘SHapley Additive exPlanation’ approach to a subset of the multi-model ensemble study for Greenland ice sheet. This allows us to quantify the influence of particular modelling decisions (either related to numerical implementation, initial conditions, or parametrisation of ice-sheet processes) directly in terms of sea level change contribution.