Advancements in Individual Tree Detection and Forest Structural Attributes Estimation From LiDAR Data: MSITD and SAFER Approaches

Abstract

Abstract Currently, the information on the structural attributes of forests, such as the diameter at breast height (DBH) and the aboveground biomass (AGB), is being used widely in various disciplines. In this study, we first proposed a novel tree detection algorithm called multi‐scale individual tree detection (MSITD) algorithm, which combines the strengths of raster‐based and point‐based approaches in order to detect individual trees from LiDAR data accurately. After tree detection, the DBH and AGB attributes were estimated using the ground control data and metrics extracted from LiDAR data, adopting the safe semi‐supervised regression (SAFER) algorithm specifically designed for addressing regression problems with limited sample data. The performances of these algorithms were evaluated within a 10‐fold nested cross‐validation approach, utilizing the LiDAR data available in the NEWFOR project. The evaluation of the obtained results revealed that both the MSITD algorithm and the SAFER algorithm demonstrate substantial superiority compared to the benchmark algorithms in tree detection, especially for the understory trees, and forest structural attributes estimation, respectively. On average, the MSITD algorithm exhibited a 13% better performance in terms of extraction rate and an 11% better performance in terms of matching rate compared to the benchmark individual tree detection algorithms. For forest structural attributes estimation, the SAFER algorithm provided superior predictions compared to the benchmark ML algorithms, with the average RMSE of 3.38 cm, MAE of 2.84 cm, and R2 of 0.59 for DBH and the average RMSE of 75.79 kg, MAE of 70.02 kg, and R2 of 0.56 for AGB.

Keywords

• forest structural attributes
• LiDAR
• individual tree detection
• machine learning algorithms
• semi‐supervised regression