A machine-learning model to estimate glacier ice thickness
The SKYNET project is funded by the European Commission, under the Marie Curie Global Fellowship scheme, grant no. 101066651.
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