Advancing forest monitoring with remote sensing and machine learning

Scope and topics

Forest ecosystems provide vital environmental, economic, and social benefits across landscapes worldwide. Strengthening their sustainable use and conservation requires modern, data-driven monitoring systems that can capture rapid forest changes. As climate change intensifies disturbances and stresses, near-real-time forest monitoring has become essential for assessing ecosystem health, biodiversity, and resilience.

Recent advances in active and passive remote sensing technologies, including optical, radar, LiDAR, and drone-based observations, enable consistent, high-resolution assessments of forest structure, composition, and dynamics across spatial and temporal scales. When combined with machine learning and artificial intelligence, these data support automated detection and characterization of forest change, providing frequent updates that enhance early warning capacities, track post-disturbance recovery, and inform adaptive forest management.

This session welcomes innovative methods and applications of remote sensing and artificial intelligence for near-real-time forest monitoring. We invite studies on forest health assessment, disturbance and fire detection, biodiversity and habitat monitoring, and time-series analyses using satellite, airborne, or UAV data. Comparative evaluations of algorithms, data sources, and scalable monitoring approaches are particularly encouraged.

By showcasing advances in automated and near-real-time forest observation, this session aims to promote faster, more accurate, and responsive monitoring systems to better understand and manage forest ecosystems under changing environmental conditions.