Every autumn, because the Northern Hemisphere moves toward winter, Judah Cohen starts to piece together a posh atmospheric puzzle. Cohen, a research scientist in MIT’s Department of Civil and Environmental Engineering (CEE), has spent many years studying how conditions within the Arctic set the course for winter weather throughout Europe, Asia, and North America. His research dates back to his postdoctoral work with Bacardi and Stockholm Water Foundations Professor Dara Entekhabi that checked out snow cover within the Siberian region and its reference to winter forecasting.
Cohen’s outlook for the 2025–26 winter highlights a season characterised by indicators emerging from the Arctic using a brand new generation of artificial intelligence tools that help develop the total atmospheric picture.
Looking beyond the standard climate drivers
Winter forecasts rely heavily on El Niño–Southern Oscillation (ENSO) diagnostics, that are the tropical Pacific Ocean and atmosphere conditions that influence weather all over the world. Nevertheless, Cohen notes that ENSO is comparatively weak this 12 months.
“When ENSO is weak, that’s when climate indicators from the Arctic becomes especially essential,” Cohen says.
Cohen monitors high-latitude diagnostics in his subseasonal forecasting, equivalent to October snow cover in Siberia, early-season temperature changes, Arctic sea-ice extent, and the steadiness of the polar vortex. “These indicators can tell a surprisingly detailed story in regards to the upcoming winter,” he says.
One in all Cohen’s most consistent data predictors is October’s weather in Siberia. This 12 months, when the Northern Hemisphere experienced an unusually warm October, Siberia was colder than normal with an early blizzard. “Cold temperatures paired with early snow cover are likely to strengthen the formation of cold air masses that may later spill into Europe and North America,” says Cohen — weather patterns which are historically linked to more frequent cold spells later in winter.
Warm ocean temperatures within the Barents–Kara Sea and an “easterly” phase of the quasi-biennial oscillation also suggest a potentially weaker polar vortex in early winter. When this disturbance couples with surface conditions in December, it results in lower-than-normal temperatures across parts of Eurasia and North America earlier within the season.
AI subseasonal forecasting
While AI weather models have made impressive strides showcasing in short-range (one-to–10-day) forecasts, these advances haven’t yet applied to longer periods. The subseasonal prediction covering two to 6 weeks stays considered one of the hardest challenges in the sphere.
That gap is why this 12 months may very well be a turning point for subseasonal weather forecasting. A team of researchers working with Cohen won first place for the autumn season within the 2025 AI WeatherQuest subseasonal forecasting competition, held by the European Centre for Medium-Range Weather Forecasts (ECMWF). The challenge evaluates how well AI models capture temperature patterns over multiple weeks, where forecasting has been historically limited.
The winning model combined machine-learning pattern recognition with the identical Arctic diagnostics Cohen has refined over many years. The system demonstrated significant gains in multi-week forecasting, surpassing leading AI and statistical baselines.
“If this level of performance holds across multiple seasons, it could represent an actual step forward for subseasonal prediction,” Cohen says
The model also detected a possible cold surge in mid-December for the U.S. East Coast much sooner than usual, weeks before such signals typically arise. The forecast was widely publicized within the media in real-time. If validated, Cohen explains, it might show how combining Arctic indicators with AI could extend the lead time for predicting impactful weather.
“Flagging a possible extreme event three to 4 weeks prematurely can be a watershed moment,” he adds. “It will give utilities, transportation systems, and public agencies more time to arrange.”
What this winter may hold
Cohen’s model shows a greater probability of colder-than-normal conditions across parts of Eurasia and central North America later within the winter, with the strongest anomalies likely mid-season.
“We’re still early, and patterns can shift,” Cohen says. “However the ingredients for a colder winter pattern are there.”
As Arctic warming hurries up, its impact on winter behavior is becoming more evident, making it increasingly essential to know these connections for energy planning, transportation, and public safety. Cohen’s work shows that the Arctic holds untapped subseasonal forecasting power, and AI may help unlock it for time frames which have long been difficult for traditional models.
In November, Cohen even appeared as a clue in crossword, a small sign of how widely his research has entered public conversations about winter weather.
“For me, the Arctic has at all times been the place to look at,” he says. “Now AI is giving us latest ways to interpret its signals.”
Cohen will proceed to update his outlook throughout the season on his blog.
