Forest Monitoring

Forest monitoring aims to efficiently and accurately assess forest health and change, crucial for conservation and sustainable management. Current research heavily utilizes remote sensing data (satellite, aerial, and LiDAR) analyzed with machine learning techniques, including deep learning architectures like U-Nets and Mask R-CNNs, and algorithms such as SVMs, to automate tasks like tree crown segmentation, deforestation detection, and biomass estimation. This work is driven by the need for large-scale, high-frequency monitoring to address challenges like deforestation and dieback, improving the speed, cost, and accuracy of forest inventories and ultimately informing conservation efforts and resource management. The development of standardized benchmark datasets is also a key focus to facilitate comparison and advance the field.