Sea ice is notoriously difficult to forecast because of its complex relationship with the atmosphere above and ocean below. It’s sensitivity to increasing temperatures have caused the summer Arctic sea ice area to shrink by 50% over the past four decades, equivalent to the loss of an area around 2.34 million square miles. These accelerating changes have dramatic consequences for our climate, for Arctic ecosystems, and Indigenous and local communities whose livelihoods are tied to the seasonal sea ice cycle.
A new tool is set to enable scientists to more accurately forecast Arctic sea ice conditions months into the future using AI (artificial intelligence). The improved predictions could operate as an early warning system for risks associated with rapid sea ice loss and can help better protect Arctic wildlife and coastal communities from the impacts of sea ice loss.
IceNet, the AI predictive tool, is almost 95% accurate in predicting whether sea ice will be present two months ahead, better than the leading physics-based model.