Neural nets map CMIP6 weather into Greenland melt

Open paper intelligence

ANNs trained on CESM2 translate CMIP6 atmospheres into Greenland surface-melt increases of about 79–264% by 2100 depending on SSP.

Source

First Application of Artificial Neural Networks to Estimate 21st Century Greenland Ice Sheet Surface Melt

Sellevold R, Vizcaino M · Geophysical research letters · 2021

doi.org/10.1029/2021gl092449 Read the full paper ↗1 citationscc by

Study at a glance

Design: Computational / modelling — ANNs trained on CESM2 melt then applied across CMIP6 SSP atmospheres
N: Hundreds of CMIP6 historical/SSP runs; ensemble size not a single primary N in stored text
Population: Greenland Ice Sheet surface melt under CMIP6 21st-century scenarios
Outcome: Projected melt increases (~79–264% by 2100 depending on SSP)

Structured fields used in claim comparison tables when every cited study has a complete layer.

What they did

Authors trained separate ANNs on CESM2 summer T2m, Z500, cloud, radiation, and snowfall to predict annual GrIS melt, then applied T2m and snowfall networks to hundreds of CMIP6 historical and SSP runs and compared a subset with MAR.

What they found

Melt rises 79% (SSP1-2.6) to 264% (SSP5-8.5) versus 1979–1998. Absolute increases are 414±276 to 1,378±555 Gt yr−1. T2m and snowfall ANNs beat cloud/Z500/radiation versus MAR. SSP5-8.5 ensemble mean bias versus MAR is only 1.6%.

The limits

What it doesn't show

Networks are trained on one GCM’s melt physics; CMIP6 climate-sensitivity spread dominates; SSP1-2.6 MAR comparison is much worse (71.9% high); this is surface melt, not full sea-level contribution.

Key terms

GrIS: Greenland Ice Sheet.
CESM2: Community Earth System Model 2, which includes interactive Greenland melt.
MAR: Modèle Atmosphérique Régional, a Greenland-specialized RCM.
SSP5-8.5: High-end Shared Socioeconomic Pathway used for 21st-century forcing.
Surface melt: Snow and ice melted at the ice-sheet surface, a major SMB term.

Flashcards

1 / 11

Research intelligence for this paper

See its role on concept claims, tensions it is part of, placement history, and related discoveries.

Open paper intelligence

Quiz yourself

1 / 7

Full GrIS sea-level potential cited:

Common questions

Training model?

CESM2 explicit Greenland melt.

Best predictor pair vs MAR?

Near-surface temperature and snowfall.

SSP5-8.5 melt increase?

264% or 1,378 ± 555 Gt yr−1.

Why higher than older RCP estimates?

CMIP6 models are hotter than CMIP5.