Even if global warming stops completely, the amount of ice in the European Alps is predicted to decrease by 34% by 2050. According to a recent international study by scientists from the University of Lausanne (UNIL, Switzerland), if the pattern observed over the last two decades continues, ice loss could approach almost half of the current volume.

By 2050, 26 years from now, we will lose at least 34% of the ice volume in the European Alps, even if global warming stops completely and immediately. This is the prediction of a new computer model developed by scientists from the Faculty of Earth and Environmental Sciences (UNIL) of the University of Lausanne, in collaboration with the University of Grenoble, ETHZ and the University of Zurich.

In this scenario, developed using machine learning algorithms and climate data, warming will stop in 2022, but glaciers will continue to suffer losses due to inertia in the climate-glacier system. But these most optimistic predictions are far from a realistic future scenario, as greenhouse gas emissions continue to rise worldwide.

In fact, most of the ice volume will disappear

Another, more realistic prediction of the study shows that without radical changes or measures, if the melting trend of the last 20 years continues, almost half (46%) of the ice volume in the Alps will virtually disappear by 2050. In fact, if you only extrapolate data from the last decade, this figure can go up to 65%.

2050: near future

Unlike traditional models that predict end-of-century forecasts, a new study published in Geophysical Research Letters looks at a shorter time frame that makes it easier to see the relevance in our lives and therefore encourages action. How old will our children be in 2050? Will there still be snow in 2038, when Switzerland could host the Olympics? These predictions are even more important because the loss of miles of ice will have visible consequences on population, infrastructure and water resources.

“The data used to create the scenarios stopped in 2022, followed by an extremely hot summer. Therefore, the situation is likely to be even worse than what we currently present,” says Samuel Cook, a researcher at UNIL and first author of the study.

Developing artificial intelligence models

Modeling was carried out using artificial intelligence algorithms. Scientists used deep learning techniques to teach their models to understand physical concepts and feed it with real climate and glaciological data. “Machine learning is revolutionizing the integration of complex data into our models. This important step, previously known to be very difficult and computationally expensive, is now more precise and efficient,” explains Guillaume Jouvet, professor at FGSE and co-author of the study.