Dominant tree species map in Catalonia (NE Spain)

An accurate dominant tree species map was produced through different foundation models and machine learning algorithms, supported by national forest inventory data. Specifically three Earth observation embedding produtcs were tested, such as Tessera, AlphaEarth, and EarthIndex, and including Sentinel-2 were used as input datasets into three machine learning models, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) to predict 15 tree taxa (12 species and 3 genera) in Catalonia (NE Spain).