Articles | Volume 16, issue 11
Research article
 | Highlight paper
04 Nov 2022
Research article | Highlight paper |  | 04 Nov 2022

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

Jeremy Rohmer, Remi Thieblemont, Goneri Le Cozannet, Heiko Goelzer, and Gael Durand


Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2022-435', Anonymous Referee #1, 27 Jul 2022
    • AC1: 'Reply on RC1', Jeremy Rohmer, 12 Sep 2022
  • RC2: 'Comment on egusphere-2022-435', Anonymous Referee #2, 29 Jul 2022
    • AC2: 'Reply on RC2', Jeremy Rohmer, 12 Sep 2022

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
ED: Publish subject to minor revisions (review by editor) (20 Sep 2022) by Ginny Catania
AR by Jeremy Rohmer on behalf of the Authors (28 Sep 2022)  Author's response   Author's tracked changes   Manuscript 
ED: Publish subject to technical corrections (30 Sep 2022) by Ginny Catania
AR by Jeremy Rohmer on behalf of the Authors (07 Oct 2022)  Author's response   Manuscript 

Post-review adjustments

AA: Author's adjustment | EA: Editor approval
AA by Jeremy Rohmer on behalf of the Authors (27 Oct 2022)   Author's adjustment   Manuscript
EA: Adjustments approved (28 Oct 2022) by Ginny Catania
This manuscript addresses an urgent problem: the proper quantification and attribution of uncertainties relating to sea-level rise. The authors show how a machine-learning approach may show the way towards a more rigorous treatment of these uncertainties, and how this might be used for policy making.
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 exPlanations approach to a subset of a multi-model ensemble study for the Greenland ice sheet. This allows us to quantify the influence of particular modelling decisions (related to numerical implementation, initial conditions, or parametrisation of ice-sheet processes) directly in terms of sea-level change contribution.