Using self-organizing maps to detect northern hemisphere cryo-cover transformation

Northern Hemisphere cryo-cover (here defined as both snow and sea ice covers) is dynamic and has displayed distinct spatial and temporal variability, as well as shifts in stability (predominantly becoming less stable) in recent decades. To better understand these transitions, this manuscript focuses on three transitional months of cryo-cover transformation, March, June and October, and implements Self-Organizing Maps (SOMs) on a MeaSuREs derived (temporal coverage of 1979-2012) cryo-cover concentration dataset. Cryo-cover transformation was analyzed on a regional and hemispheric basis with trends calculated for all areas identified by the SOMs. Results suggest cryo-cover decreases (in area and stability) during March and June as pixels shift from SOM identified stable patterns to more transient patterns. October results suggest increases in transient cryo-cover, a result of declining stability in sea ice but also increasing snow cover predominantly centered around 50 degrees N latitude. All months experience regions of increasing and decreasing cryo-cover trends. Decreasing trends are predominant in March and June, although some areas of increase are apparent even during these months. By contrast, October has significant area experiencing increasing trends in cryo-cover, as well as large decreasing trends in the ice domain. Given accelerated rising temperatures in the Northern Hemisphere high latitudes, transformation of cryo-cover will continue, and monitoring these changes spatially (using methodologies like SOMs) will be necessary to better understand the radiative and environmental impacts.