Gathering accurate data on forest resources is one of the most important steps in sustainable planning for these forests. Remote sensing techniques have been widely used in forest management by predicting various forest parameters such as volume, tree density and basal area. This research was conducted in Kalala Forest in northern Iran, and field data were collected by cluster sampling method. 105 samples were inventoried with an area of 400 square meters per sample. At the level of each sample, diameter at breast height and tree height were measured. The volume, tree density, and basal area per hectare of the studied samples were calculated. The values of vegetation indices at the studied sample sites were extracted through the Sentinel-2 satellite image. The relationship between the studied parameters and vegetation indices was modeled through the use of the Random Forest algorithm. This research aims to investigate the ability of the Sentinel-2 satellite to estimate volume, basal area and tree density in the study area using the Random Forest algorithm. Volume modeling results showed that the coefficient of determination (R2) was equal to 0.88, and the percentage root mean square error (%RMSE) was equal to 21.01%. While the results of basal area modeling showed that the coefficient of determination was 0.88, and the percentage of root mean square error was 20.14%. The results of tree density modeling showed that the coefficient of determination was 0.89, and the percentage of root mean square error was 19.22%.The results also showed that the use of the Sentinel-2 satellite and the Random Forest algorithm in modeling gave positive and acceptable results.