New Algorithm Forecasts Arctic Sea Ice Up to Nine Months Ahead

Researchers at the Mubadala Arabian Center for Climate and Environmental Sciences (ACCESS) at NYU Abu Dhabi have developed a new algorithm capable of forecasting Arctic sea ice extent up to nine months in advance. This tool, known as the Random Analog Predictor (RAP), offers a novel method to anticipate Arctic changes that impact the global climate system. The findings of this research were published in the journal Scientific Reports on October 11, 2026.

RAP operates by utilizing historical sea ice data to identify past patterns that resemble current conditions. It then employs these historical analogues to generate an ensemble of possible forecasts, providing an estimate of uncertainty for each prediction. Francesco Paparella, inaugural director of Mubadala ACCESS at NYU Abu Dhabi and senior author of the study, highlighted that forecasting Arctic sea ice months ahead is a challenging yet increasingly vital problem as the Arctic continues to change. He noted that their approach is deliberately simple, yet performs competitively with more complex forecasting models.

Arctic sea ice plays a crucial role in the global climate by reflecting solar energy back into space, while the darker ocean absorbs it. Changes in this ice can influence atmospheric and oceanic patterns far beyond the region, making advance predictions valuable for understanding wider climate impacts. The researchers found that RAP produced forecasts with skill comparable to models used by the Sea Ice Prediction Network, with its September sea ice extent forecast error on par with 34 seasonal models.

Unlike physics-based models that simulate the atmosphere, ocean, and sea ice, RAP relies solely on the historical record of Arctic sea ice extent. This simplicity and interpretability allow RAP to serve as a transparent benchmark for evaluating future forecasting methods, including more sophisticated physics-based and AI-driven models. Paparella added that if a complex model cannot outperform such a simple approach, it reveals important insights about the additional predictive information that complexity provides. The team also sees potential for RAP to support the UAE’s growing polar and Arctic research activities by offering a simple, low-cost tool for seasonal sea ice forecasting, as detailed in the study by Faiq Raees et al.

Editor's note: The draft is comprehensive, accurately reflecting all key facts and quotes from the provided full text.