Countrywide vegetation height models (VHM) were generated for Armenia based on Copernicus Sentinel-2 imagery within the framework of the FORACCA project. “The Forest Restoration and Climate Change in Armenia” (FORACCA) project is funded by the Swiss Agency for Development and Cooperation (SDC). The project is implemented by the Swiss Federal Institute for Forest, Snow, and Landscape Research (WSL) in collaboration with Zoï Environment Network as well as the Forest Alliance of Armenia. A Convolutional Neural Network (CNN) model was trained in Switzerland to estimate the maximum vegetation height at the spatial resolution of the Sentinel-2 pixel of 10 m. Vegetation heights from the spatially higher-resolved VHM Lidar NFI were used as reference data for the CNN training. Then, the model was spatially transferred and VHMs for Armenia were generated annually based on available Sentinel-2 imagery from May – September of the respective year. Further details on the dataset and model to create the Sentinel-2 VHMs can be found in the paper Jiang et al. (2023, https://doi.org/10.1016/j.srs.2023.100099). Contains modified Copernicus Sentinel data.