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

• Published in: The Cryosphere
• Main Authors: Rohmer, Jérémy, Thiéblemont, Rémi, Le Cozannet, Gonéri, Goelzer, Heiko, Durand, Gael
• Other Authors: Bureau de Recherches Géologiques et Minières (BRGM) (BRGM), NORCE - Norwegian Research Centre, Mekjarvik 12, N-4072, Randaberg, Norway., 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
• Language: English
• Published: HAL CCSD 2022
• Subjects: [SDU]Sciences of the Universe [physics]; [SDU.STU]Sciences of the Universe [physics]/Earth Sciences; Greenland; Ice Sheet; The Cryosphere
• Online Access: https://hal-insu.archives-ouvertes.fr/insu-03859251; https://hal-insu.archives-ouvertes.fr/insu-03859251/document; https://hal-insu.archives-ouvertes.fr/insu-03859251/file/tc-16-4637-2022.pdf; https://doi.org/10.5194/tc-16-4637-2022

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.