Improving interpretation of sea-level projections through a machine-learning-based local explanation approach
International audience 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, imp...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , |
Other Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2022
|
Subjects: | |
Online Access: | https://insu.hal.science/insu-03859251 https://insu.hal.science/insu-03859251/document https://insu.hal.science/insu-03859251/file/tc-16-4637-2022.pdf https://doi.org/10.5194/tc-16-4637-2022 |
id |
ftunigrenoble:oai:HAL:insu-03859251v1 |
---|---|
record_format |
openpolar |
spelling |
ftunigrenoble:oai:HAL:insu-03859251v1 2024-05-19T07:41:15+00:00 Improving interpretation of sea-level projections through a machine-learning-based local explanation approach Rohmer, Jérémy Thiéblemont, Rémi Le Cozannet, Gonéri Goelzer, Heiko Durand, Gael Bureau de Recherches Géologiques et Minières (BRGM) Norwegian Research Center (NORCE) Institut des Géosciences de l’Environnement (IGE) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) Université Grenoble Alpes (UGA) 2022 https://insu.hal.science/insu-03859251 https://insu.hal.science/insu-03859251/document https://insu.hal.science/insu-03859251/file/tc-16-4637-2022.pdf https://doi.org/10.5194/tc-16-4637-2022 en eng HAL CCSD Copernicus info:eu-repo/semantics/altIdentifier/doi/10.5194/tc-16-4637-2022 insu-03859251 https://insu.hal.science/insu-03859251 https://insu.hal.science/insu-03859251/document https://insu.hal.science/insu-03859251/file/tc-16-4637-2022.pdf BIBCODE: 2022TCry.16.4637R doi:10.5194/tc-16-4637-2022 http://creativecommons.org/licenses/by/ info:eu-repo/semantics/OpenAccess ISSN: 1994-0424 EISSN: 1994-0416 The Cryosphere https://insu.hal.science/insu-03859251 The Cryosphere, 2022, 16, pp.4637-4657. ⟨10.5194/tc-16-4637-2022⟩ [SDU]Sciences of the Universe [physics] [SDU.STU]Sciences of the Universe [physics]/Earth Sciences info:eu-repo/semantics/article Journal articles 2022 ftunigrenoble https://doi.org/10.5194/tc-16-4637-2022 2024-05-02T00:25:31Z International audience 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 known as "SHAP" (SHapley Additive exPlanations). 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) numerical implementation, (2) initial conditions, (3) modelling of ice-sheet processes, and (4) environmental forcing. 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. Article in Journal/Newspaper Greenland Ice Sheet The Cryosphere Université Grenoble Alpes: HAL The Cryosphere 16 11 4637 4657 |
institution |
Open Polar |
collection |
Université Grenoble Alpes: HAL |
op_collection_id |
ftunigrenoble |
language |
English |
topic |
[SDU]Sciences of the Universe [physics] [SDU.STU]Sciences of the Universe [physics]/Earth Sciences |
spellingShingle |
[SDU]Sciences of the Universe [physics] [SDU.STU]Sciences of the Universe [physics]/Earth Sciences Rohmer, Jérémy Thiéblemont, Rémi Le Cozannet, Gonéri Goelzer, Heiko Durand, Gael Improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
topic_facet |
[SDU]Sciences of the Universe [physics] [SDU.STU]Sciences of the Universe [physics]/Earth Sciences |
description |
International audience 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 known as "SHAP" (SHapley Additive exPlanations). 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) numerical implementation, (2) initial conditions, (3) modelling of ice-sheet processes, and (4) environmental forcing. 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. |
author2 |
Bureau de Recherches Géologiques et Minières (BRGM) Norwegian Research Center (NORCE) Institut des Géosciences de l’Environnement (IGE) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) Université Grenoble Alpes (UGA) |
format |
Article in Journal/Newspaper |
author |
Rohmer, Jérémy Thiéblemont, Rémi Le Cozannet, Gonéri Goelzer, Heiko Durand, Gael |
author_facet |
Rohmer, Jérémy Thiéblemont, Rémi Le Cozannet, Gonéri Goelzer, Heiko Durand, Gael |
author_sort |
Rohmer, Jérémy |
title |
Improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
title_short |
Improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
title_full |
Improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
title_fullStr |
Improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
title_full_unstemmed |
Improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
title_sort |
improving interpretation of sea-level projections through a machine-learning-based local explanation approach |
publisher |
HAL CCSD |
publishDate |
2022 |
url |
https://insu.hal.science/insu-03859251 https://insu.hal.science/insu-03859251/document https://insu.hal.science/insu-03859251/file/tc-16-4637-2022.pdf https://doi.org/10.5194/tc-16-4637-2022 |
genre |
Greenland Ice Sheet The Cryosphere |
genre_facet |
Greenland Ice Sheet The Cryosphere |
op_source |
ISSN: 1994-0424 EISSN: 1994-0416 The Cryosphere https://insu.hal.science/insu-03859251 The Cryosphere, 2022, 16, pp.4637-4657. ⟨10.5194/tc-16-4637-2022⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.5194/tc-16-4637-2022 insu-03859251 https://insu.hal.science/insu-03859251 https://insu.hal.science/insu-03859251/document https://insu.hal.science/insu-03859251/file/tc-16-4637-2022.pdf BIBCODE: 2022TCry.16.4637R doi:10.5194/tc-16-4637-2022 |
op_rights |
http://creativecommons.org/licenses/by/ info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.5194/tc-16-4637-2022 |
container_title |
The Cryosphere |
container_volume |
16 |
container_issue |
11 |
container_start_page |
4637 |
op_container_end_page |
4657 |
_version_ |
1799480846634188800 |