The Montado ecosystem is an important agri-forestry system in Portugal, occupying about 8% of the total area of the country. However, this biodiverse ecosystem is threatened due to factors such as shrub encroachment. In this context, the development of tools for characterizing and monitoring Montado areas is crucial for their conservation. In this study, we developed a deep convolutional neural network algorithm based on the U-net architecture to identify regions with trees, shrubs, grass, bare soil, or other areas in Montado areas using high-resolution RGB and near-infrared orthophotos (with a spatial resolution of 25 cm) from seven experimental sites in the Alentejo region of Portugal (six used for training/validation and one for testing). To optimize the model’s performance, we performed hyperparameter tuning, which included adjusting the number of filters, dropout rate, and batch size. The best model achieved an overall classification performance of 0.88 and a mean intersection of the union of 0.81 on the test set, indicating high accuracy and reliability of the model in identifying and delineating land cover classes in the Montado ecosystem. The developed model is a powerful tool for identifying the status of the Montado ecosystem regarding shrub encroachment and facilitating better future management.