How we predict snow
Veabird Snow forecasts the surface on every run at hundreds of ski resorts for the next 10 days. Here is what goes into it, how we check it, and what we are doing to make it better.
1. Start from the best weather models
Every forecast blends four global weather models hour by hour: ECMWF (European), GFS (US), ICON (German) and GEM (Canadian). Where a high-resolution regional model covers the resort (HRRR in the US, HRDPS in Canada, AROME in France and the Alps, ICON-D2 in central Europe, MSM in Japan), we add it at double weight, because it sees mountains far better than a global grid does.
How much the global models disagree about the next three days of summit snowfall sets our confidence. That spread gives the low, likely and high storm totals and the chance of a powder day.
2. Bring the weather down to each run
A weather model sees a mountain as a few grid boxes. Skiers ski runs. So we map every run from OpenStreetMap and measure its top, bottom, steepness and the direction it faces. Resorts without mapped runs get 12 virtual slopes: three elevation bands times four directions.
Then, at the top, middle and bottom of each run, hour by hour:
- Temperature follows a lapse rate fitted to the model's freezing level, so the summit can be snowing while the base rains.
- Rain or snow splits between −0.2 °C and 2.2 °C. Snow density follows the Kuchera snow-to-liquid ratio: cold storms give light powder, warm ones give heavy cement.
- More snow higher up: about 4% more precipitation for every 100 m of elevation.
- Wind loads snow onto sheltered slopes and scours exposed ones, more so above treeline.
- Sun: the real sun position on each slope drives melting, overnight crusts and spring corn.
- Groomers and skiers: grooming at 4 a.m. on groomed runs, skier traffic from 9 to 4 depending on difficulty.
The result is classified into a surface you would recognize (deep powder, corduroy, corn, crust, ice) and scored 0 to 100. Runs with too little snow show as predicted closed.
3. Look further ahead with climate
Beyond 10 days, weather forecasts stop being useful. For later dates we use the last 10 seasons of reanalysis (ERA5) to show what is normal for that resort and month, and we compare this season's snowfall so far with the same point in past seasons. Comparing a resort with its own history cancels most of the bias in reanalysis data. These outlooks are climate, not forecasts; see the '26-27 Snow Report.
4. Check ourselves every day
Against weather stations
Each day we save the forecast at the nearest SNOTEL station to each US resort, then score it against the measured snow-depth gain 1 to 5 days ahead: average error, bias, and how often we caught (or falsely called) 5 cm days.
Against resort reports
We also score forecasts against the snowfall resorts report themselves, worldwide, and check those reports against nearby stations so we know which ones to trust.
Let the best model lead
Models that verify better get more weight: per resort once it has 10 scored days, otherwise across all stations once there are 30. The forecast you see is the same blend we score.
How we intend to improve
- Verify outside the US. SNOTEL only covers the western US. Next we are adding Canadian and European station networks, so the skill-weighted blend works as well at Whistler and Zermatt as it does at Snowbird.
- Correct each resort's bias. Some resorts are consistently over- or under-forecast: lake effect, rain shadows, narrow valleys that models smooth out. Once a resort has enough verified seasons, we will correct its snowfall forecast for that known bias.
- Weight models by lead time and storm type. Today skill is measured on days 1 and 2. The model that is best tomorrow is not always best five days out, or in every kind of storm. We plan to weight models by lead day and by storm type.
- Score the surface, not just the snowfall. Snowfall is easy to measure; corduroy and crust are not. We want to check our surface and open/closed predictions against resort grooming and lift reports, and against skier feedback.
- Account for settling. Snow-depth gain undercounts new snow because fresh snow compacts. Modeling that settling will make our station scores fairer and our bias corrections more accurate.
- Test seasonal signals. The month-by-month outlook uses climate only. We will test whether El Niño, La Niña and similar signals add real skill before we use them.
Forecasts are guidance, not guarantees, and never a substitute for avalanche bulletins or ski patrol. Spotted a forecast that missed? Tell us. Misses are how the model gets better.