Today, multi-platform LiDAR provides unprecedented 3D data of forests. However, a major bottleneck remains: how do we effectively scale structural details from individual trees to large-area ecological products? Furthermore, traditional empirical methods often struggle to link 3D geometric structures with complex physiological functions.

This session seeks to address these challenges by highlighting research synergizing LiDAR with AI. We aim to explore how this integration  revolutionizes our understanding of forest structure-function relationships. We welcome both methodological and empirical studies across all spatial scales. Topics include: novel AI-driven algorithms for extracting individual-tree parameters; developing large-scale structural datasets through multi-sensor fusion; and scientific studies using these innovations to answer fundamental ecological questions, such as how forest structure drives carbon dynamics, microclimates, and functional diversity.

• GC - Global Environmental Change
• H - Hydrology
• IN - Informatics