Industry News
As the air begins to turn crisp and the leaves change color across North America, many skiers will begin the annual cycle of strengthening their legs, sharpening their stoke, and speculating about when the snow will fly. The gradual turn towards winter brings several reliable markers, such as a new Warren Miller film and seasonal forecasts from the Farmer’s Almanac and the National Oceanic and Atmospheric Administration (NOAA). These seasonal forecasts almost always miss the mark, due to the accumulation of errors in long-term forecasting, but still, they can offer skiers motivation to bust out a few more workouts in the hopes that this season will bring just a couple of extra powder days.
- Related: Fact-Checking the Winter 2025-26 Farmers’ Almanac: What Skiers Should (and Shouldn’t) Bank On
Despite the unreliability of seasonal forecasts, Big Sky Resort, Montana, shared earlier this month that they are leveraging Artificial Intelligence based tools to make a custom seasonal forecast for their resort. Big Sky Resort President and COO Troy Nedved told Explore Big Sky that he has been using Claude, a large language model developed by Anthropic, to develop a custom forecasting tool for Big Sky. “Mother Nature will humble us, and prove to us that we can’t predict stuff at times. There’s no certainty to any of these forecasts. But the increased accuracy is something that may help us anticipate and plan accordingly,” Nedved told Explore Big Sky, referring to previous forecasts for this season and financial forecasts from the last several years.
Modern seasonal forecasts depend heavily on a few different climate oscillations, the most famous of which is the El Niño Southern Oscillation, or El Niño/La Niña. What actually oscillates during an El Niño cycle is the surface temperature of the Pacific Ocean in the tropics, which then influences winds and weather patterns across the rest of the planet. Many skiers are familiar with El Niño and what it could mean for snow in a particular season, but El Niño is not the only such climate oscillation that can play a role in winter weather. Other major cycles include the Madden-Julian Oscillation, the Pacific Decadal Oscillation, the North Atlantic Oscillation, and the Arctic Oscillation. If you think you can get a good idea of where a handful of these oscillations are at and what they’ll mean for snowfall in a couple of months, then you, too, could try your hand at a long-range weather prediction.
A.I. tools like Claude make the process of getting from an idea to a prediction easier. Large language models take ideas from your prompt, comb the internet and other sources for other mentions of those ideas, and string together words to form an answer that sounds believable, and may even be right. The advantage for someone like Nedved, not necessarily an expert in atmospheric physics, but interested in learning about the coupling between the El Niño Southern Oscillation and the Pacific Decadal Oscillation and what that could mean for snow at Big Sky, is that Nedved doesn’t have to sift through the dozens of research papers that have been written about the relationship between those two climate oscillations and its impact on weather around the world.
Though Nedved has reported an increase in accuracy recently, along with a prediction of an above-average year, he remains cautious about using the forecast for any business decisions. “We’re not there yet, and I don’t want to get ahead of ourselves,” Nedved told Explore Big Sky. The move towards season passes in the last two decades and mega-passes more recently, allows ski areas to insulate themselves from the unpredictability of next season’s snow totals. Most of Big Sky’s lift-based revenue has likely already been made for the season, meaning the operating budget can be made with some confidence, without having to worry about selling enough day tickets to make ends meet. At the multi-month scale Nedved said he used, staffing decisions based on when new terrain will be ready to open or when favorable snowmaking conditions will appear are not possible.
A.I. is the fastest adopted technology humans have ever invented, so there’s no surprise the ski industry is getting caught up in trying to find potential benefit. While Big Sky’s forecast for the winter may turn out to be a total dud, it could also be the next big thing. Large language models may not be the best place to go for a hyperlocalized weather forecast, but thinking about how a long-range or mid-range forecast could help optimize ski area operations could lead to new innovations in the ski industry. Whatever the outcome of the ENSO-PDO coupling this season, there is bound to be at least a few good turns up on Big Sky’s Challenger Chair.
