Multi-source remote sensing for large-scale biomass estimation in Mediterranean olive orchards using GEDI LiDAR and machine learning

Abstract

Accurate estimation of Above-Ground Biomass Density (AGBD) is essential for assessing carbon stocks and promoting sustainable agricultural practices. This study integrates multi-source remote sensing data, including GEDI LiDAR, optical, SAR, and topographic variables, to predict AGBD in Mediterranean olive orchards using a Random Forest regression model implemented on Google Earth Engine (GEE). The proposed volumetric approach, based on GEDI L2A canopy height and dendrometric parameters, provides a scalable framework for large-scale biomass estimation using lidar technologies on satellite platforms. The model's predictive performance varied depending on data combinations, with the fully multi-source configuration achieving the most consistent results, although overall accuracy remained moderate due to sensor constraints and the inherent limitations of the proposed exploratory framework. NDBI, slope, HV polarization, and MCARI1 were identified as the most influential predictors. The spatial analysis revealed that Spain exhibited the highest total AGB stock among the studied countries, followed by Italy and Greece, reflecting their dominance in olive production. Despite its limitations in precision at fine spatial scales, this exploratory study demonstrates the potential of integrating LiDAR, optical, and SAR data to evaluate biomass distribution in low-stature vegetation. The proposed framework offers a cost-effective and scalable strategy for large-scale carbon monitoring and supports data-driven agricultural management toward more sustainable Mediterranean production systems.