Ocean acidification (OA) is a consequence of the absorption of anthropogenic carbon emissions and it profoundly impacts marine life. Arctic regions are particularly vulnerable to rapid pH changes due to low ocean buffering capacities and high stratification. New research, led by John Krasting (GFDL) with AOS/CIMES and GFDL co-authors, applied unsupervised machine learning methodology to simulations of surface Arctic acidification using two state-of-the-art coupled climate models. The authors identified four sub-regions whose boundaries are influenced by present-day and projected sea ice patterns. The regional boundaries are consistent between the models and across lower and higher carbon emissions scenarios. AOS Associate Research Scholar Maike Sonnewald and former CIMES Intern Maurizia De Palma are among the paper's co-authors.