Advances in tree detection and species classification using remote sensing data: a review

Remote sensing has revolutionized forest inventory by enabling accurate, efficient and scalable assessments. This review focuses on two essential aspects: mapping individual trees through detection and crown delineation, and characterizing species composition. Recent advances in optical imagery, laser scanning-based sensing and multi-sensor data integration have significantly improved tree-level mapping and species discrimination. In addition, machine learning (ML) and deep learning (DL) models have enhanced analytical precision and classification performance. By synthesizing data sources, processing techniques and modelling approaches, this review provides a comprehensive overview of the state-of-the-art in remote sensing for forest inventory.