Welcome to the ICEBOOST v2.0 viewer

A machine-learning model to estimate glacier ice thickness

Published in Scientific Data: DOI

Individual Glacier product on Zenodo: DOI

Glacier Complex product on Zenodo: DOI

Funding from the EU commission UNIVE UCI

The SKYNET project is funded by the European Commission, under the Marie Curie Global Fellowship scheme, grant no. 101066651.

RGI 62
RGI 70
DATA
Globe
SAT
Movie

    ICEBOOST v2.0

    ≥800 700 600 500 400 300 200 100 0
    ICE THICKNESS [m]
    ≥1500 1125 750 375 0 -125 -250 -375 ≤-500
    BED ELEV [m a.s.l]

    ICEBOOST is a gradient boosted decision tree model. It averages equally the predictions from XGBoost and CatBoost. Both are trained independently for regression, using a l2 loss, and optimized globally.

    ICEBOOST v2.0 model is presented in Scientific Data: https://www.nature.com/articles/s41597-026-07744-9

    ICEBOOST v1.1 model is presented in Geoscientific Model Development: https://gmd.copernicus.org/articles/18/2545/2025/

    MODEL DOMAIN

    The model runs on all glaciers defined in the Randolph Glacier Inventory [Pfeffer and The Randolph Consortium, 2017]. The model is trained on version v.62, which includes ice bodies with direct connection to the ice sheets. The model can be deployed on v. 62 or the most recent v. 70.

    MODEL INPUTS

    TRAINING DATA