A minimal model for reconstructing interannual mass balance variability of glaciers in the European Alps

We present a minimal model of the glacier surface mass balance. The model relies solely on monthly precipitation and air temperatures as forcing. We first train the model individually for 15 glaciers with existing mass balance measurements. Based on a cross validation, we present a thorough assessment of the model's performance outside of the training period. The cross validation indicates that our model is robust, and our model's performance compares favorably to that from a less parsimonious model based on seasonal sensitivity characteristics. Then, the model is extended for application on glaciers without existing mass balance measurements. We cross validated the model again by withholding the mass balance information from each of the 15 glaciers above during the model training, in order to measure its performance on glaciers not included in the model training. This cross validation indicates that the model retains considerable skill even when applied on glaciers without mass balance measurements. As an exemplary application, the model is then used to reconstruct time series of interannual mass balance variability, covering the past two hundred years, for all glaciers in the European Alps contained in the extended format of the world glacier inventory. Based on this reconstruction, we present a spatially detailed attribution of the glaciers' mass balance variability to temperature and precipitation variability.