Committed Ice Loss in the European Alps Until 2050 Using a Deep‐Learning‐Aided 3D Ice‐Flow Model With Data Assimilation.

Modeling the short‐term (<50 years) evolution of glaciers is difficult because of issues related to model initialization and data assimilation. However, this timescale is critical, particularly for water resources, natural hazards, and ecology. Using a unique record of satellite remote‐sensing data, combined with a novel optimisation and surface‐forcing‐calculation method within the framework of the deep‐learning‐based Instructed Glacier Model, we are able to ameliorate initialization issues. We thus model the committed evolution of all glaciers in the European Alps up to 2050 using present‐day climate conditions, assuming no future climate change. We find that the resulting committed ice loss exceeds a third of the present‐day ice volume by 2050, with multi‐kilometer frontal retreats for even the largest glaciers. Our results show the importance of modeling ice dynamics to accurately retrieve the ice‐thickness distribution and to predict future mass changes. Thanks to high‐performance GPU processing, we also demonstrate our method's global potential. Plain Language Summary: Modeling glaciers is highly challenging over the next few decades because setting up models correctly is a big issue. This is unfortunate, because we really want to know what is going to happen on that timescale, as it will directly affect our lives, homes and jobs. We present a new modeling approach, taking advantage of new data and machine‐learning methods, that allows us to set our model up much more effectively. We thus work out how much ice will be lost in the European Alps between now and 2050, even if the climate does not change further, and find that a third of the ice will be lost, come what may. Even the largest glacier fronts will retreat by several kilometers. We show that modeling glaciers properly, with a well‐set‐up model, is really important to make accurate predictions. Key Points: We present a novel, fast, accurate deep‐learning method for glacier model initialization and forward simulation at a regional scaleWe calculate glacier climatic surface elevation change without needing calibration across the whole of the European Alps for the first timeWe find committed ice loss in the European Alps to be 34% by 2050, rising to 46% with linear extrapolation of 2000–2020 mass‐balance trends [ABSTRACT FROM AUTHOR]