Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Fix the driver behind crashes, sound loss and screen glitches3Repair Windows errors before they cause bigger problemsiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
NYU Abu Dhabi researchers report that their Random Analogue Predictor (RAP) can forecast Arctic sea-ice extent as far as nine months ahead. The method searches historical records for patterns resembling current sea-ice conditions, then uses what followed those patterns to create an ensemble of possible forecasts. Its reported performance is comparable to established seasonal models, making RAP a proposed benchmark—not a replacement for more sophisticated forecasting systems.
What the algorithm forecasts—and what it does not
RAP targets Arctic sea-ice extent: the area covered by sea ice, rather than Arctic climate as a whole. The researchers report forecasts with lead times of up to nine months. That finding does not mean the algorithm predicts the timing or effects of all climate change, or that every forecast will be accurate.
The result was announced in an October 8, 2026 release from New York University, distributed by EurekAlert. The release identifies the peer-reviewed paper as “Random analog prediction provides a benchmark for seasonal Arctic sea ice extent forecasting,” published in Scientific Reports (DOI: 10.1038/s41598-026-72959-0). Read the NYU research release on EurekAlert.
How RAP turns past patterns into forecasts
It searches the historical record
Unlike physics-based systems that simulate the atmosphere, ocean and sea ice, RAP uses historical Arctic sea-ice-extent records. It looks for past patterns similar to present conditions and examines what happened after those analogues.
#1 Best Overall
It produces a range of possible outcomes
RAP combines those later outcomes into an ensemble of forecasts. The spread among ensemble members serves as an uncertainty estimate: a wider spread indicates that the possible outcomes differ more. The release describes this as a way to estimate uncertainty, but does not provide a numerical measure of calibration or a forecast-specific confidence guarantee.
How its reported performance compares
NYU’s release says RAP achieved forecast skill comparable to models used by the Sea Ice Prediction Network. For September Arctic sea-ice extent, its forecast error was reported as comparable to that of 34 seasonal forecasting models.
Rank #2
This is a reported comparison, not evidence that RAP outperforms those models or is ready to replace them. The release’s news copy does not provide a full table of error metrics, the detailed evaluation period, or enough information to independently assess how performance varies by lead time. Those details matter when comparing forecast systems: the target and region, lead time and target season, error metric and evaluation period, treatment of uncertainty, and model complexity should all be aligned.
Why Arctic sea-ice extent matters
Sea ice reflects some incoming solar energy back into space, while darker ocean water absorbs more. Changes in sea ice can also influence atmospheric and oceanic patterns beyond the Arctic. The NYU release explains these connections but gives no numerical estimate of their magnitude, so the forecast result should not be read as a quantified estimate of climate impacts.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Why researchers propose RAP as a benchmark
A method built from historical patterns can provide a comparatively transparent point of reference for evaluating more complex forecasts. Researchers propose RAP for assessing physics-based and AI-driven methods against a clear benchmark. Senior author Francesco Paparella, inaugural director of Mubadala ACCESS at NYU Abu Dhabi, said: “The value of RAP is not that it replaces more sophisticated models, but that it gives us a clear standard against which they can be tested.”
Quick Recap
Best Value
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
