Forecasting of future snow depths is useful for many applications like road safety, winter sport activities, avalanche risk assessment and hydrology. Motivated by the lack of statistical forecasts models for snow depth, in this paper we present a set of models to fill this gap. First, we present a model to do short term forecasts when we assume that reliable weather forecasts of air temperature and precipitation are available. The covariates are included nonlinearly into the model following basic physical principles of snowfall, snow aging and melting. Due to the large set of observations with snow depth equal to zero, we use a zero-inflated gamma regression model, which is commonly used to similar applications like precipitation. We also do long term forecasts of snow depth and much further than traditional weather forecasts for temperature and precipitation. The long-term forecasts are based on fitting models to historic time series of precipitation, temperature and snow depth. We fit the models to data from three locations in Norway with different climatic properties. Forecasting five days into the future, the results showed that, given reliable weather forecasts of temperature and precipitation, the forecast errors in absolute value was between 3 and 7 cm for different locations in Norway. Forecasting three weeks into the future, the forecast errors were between 7 and 16 cm.1 age and density of the snow pack. Compared to other factors, precipitation and temperature are the main drivers of changes in snow depth and most snow models are only based on these factors (Brown et al.;Kohler et al.;.Weather forecast services routinely forecast quantities like temperature, precipitation, wind and air pressure, but very rarely snow depth or other snow related quantities. An exception is snow-forecast.com (Snow Forecast; n.d.) which forecast snow depths for skiing resorts around the world, but the methods used are not publicly available.The small number of weather services forecasting snow depth or other snow related quantities are in a big contrast to the amount logged snow depth data available around the world. E.g. in the US and Canada daily snow depth are logged for at least 8000 locations (Brown et al.;. Motivated by the lack of models to forecast future snow depths and the large amount of historic snow depth data available, in this paper we present models to fill this gap. We build both short-term forecasts, where reliable forecasts of temperature and precipitation are available, and forecasts going further into the future. The work in Brown et al. (2003) is related to the work in this paper, except that the authors use a numerical model to relate snow depth to precipitation and temperature, while we present a statistical model such that probabilistic forecasts can be performed.The paper is organized as follows: In Sections 2 and 3 we describe the statistical models for short and long-term forecasts of snow depth. The models are analyzed on real data in Section 4 and the paper ends with some closing remarks in Sect...