Scientific research and decision-making face significant challenges due to the lack of precise and efficient methods for measuring forests, particularly sample plots. These plots are essential for studying ecosystems, advancing silviculture, practicing forestry, and supporting national forest inventories, which underpin policy decisions and international reporting. While laser scanning (LS) systems—terrestrial, mobile, and drone-based—have been used to automate sample plot measurements, the time saved in field data collection often comes at the cost of lengthy processing times. We develop a novel approach that combines repetitive LS measurements, deep learning techniques, and automated LS data collection to streamline sample plot monitoring. This solution accelerates data collection and processing, providing an efficient method for long-term forest monitoring to support both scientific research and practical applications.

2026

2030