Correcting confounding canopy structure, biochemistry and soil background effects improves leaf area index estimates across diverse ecosystems from Sentinel-2 imagery

High-resolution leaf area index (LAI) data are essential for sustainable agro-ecosystem management and precise disturbance detection. Previous LAI products were primarily derived from satellite data with limited spatiotemporal or spectral resolutions, which could be overcome with the use of Sentinel-2. While hybrid methods that integrate PROSAIL simulations with machine learning offer advantages in extracting high-resolution LAI from Sentinel-2, they still face challenges due to confounding factors related to canopy structure, leaf biochemistry, and soil background. To reduce impacts of these confounders, we developed an efficient hybrid method for Sentinel-2-based LAI retrieval. Our approach consists of random forest models trained on simulated datasets generated by PROSAIL-5B with two refinements: variable canopy fraction of senescent leaves (FS) and soil bidirectional reflectance fact…