Testing the accuracy and transferability of remotely sensed biomass models across heterogeneous grasslands

Grassland aboveground biomass provides key insights into ecological processes such as carbon sequestration, animal movement patterns, and agricultural management practices. Different model types have been developed to estimate grassland biomass from satellite imagery. However, differences in model performance across sites with different management regimes remain largely understudied. In this study, we compared accuracy and transferability of empirical, physically-based, and hybrid models to estimate grassland biomass from multispectral Sentinel-2 data. Based on field data from five study sites in Europe and the United States, we assessed (1) the accuracy of biomass estimation models per site, (2) model transferability between sites, (3) the performance of models trained or optimized with data from multiple study sites, and (4) the relationship between epistemic uncertainty and model transferability. Our results showed that (1) all models exhibited satisfying and comparable performance at the site level, (2) physically-based models showed the highest degree of transferability between sites, (3) no model consistently outperformed all other models when trained or optimized with field data from multiple sites, and (4) epistemic uncertainty was not necessarily a reliable measure of model applicability to unseen data. Our findings demonstrate the challenges of developing models applicable across grasslands subject to varying ecological conditions and management regimes, further highlighting that model transferability should be considered an integral part of performance assessment when building scalable satellite-based grassland monitoring systems. As next steps we suggest investigating the degree to which adding variables such as climate data or multi-sensor approaches would improve model performance across ecosystems.