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

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

doi:https://doi.org/10.5194/tc-16-4637-2022

Articles | Volume 16, issue 11

https://doi.org/10.5194/tc-16-4637-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Improving the contribution of the land cryosphere to sea level...

https://doi.org/10.5194/tc-16-4637-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

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

Data sets

Local explanation SHAP approach applied to MIROC5,RCP8.5-forced multi-model ensemble study of GrIS future sea-level contributions Jeremy Rohmer https://doi.org/10.5281/zenodo.7157302

Model code and software

Local explanation SHAP approach applied to MIROC5,RCP8.5-forced multi-model ensemble study of GrIS future sea-level contributions Jeremy Rohmer https://doi.org/10.5281/zenodo.7157302

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.