Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data

A novel approach using Sentinel-2 satellite data demonstrates high accuracy in estimating aboveground biomass (AGB) in dense Hyrcanian forests, particularly for Carpinus betulus (common hornbeam). The study found that band 6, located in the red-edge spectrum, exhibited the strongest correlation with AGB (r = −0.723), outperforming other spectral and derived indices. Among machine learning methods tested—Multiple Regression (MR), Artificial Neural Network (ANN), k-Nearest Neighbor (kNN), and Random Forest (RF)—ANN achieved the best performance, with a %RMSE of 19.9%. This method offers a cost-effective alternative to traditional field measurements, which are often hindered by challenging terrain. The findings suggest that simple vegetation indices derived from Sentinel-2 imagery can reliably estimate AGB in temperate forests, providing a scalable solution for biomass assessment in remote or difficult-to-access areas.

Moradi, F., Darvishsefat, A. A., Pourrahmati, M. R., Deljouei, A., & Borz, S. A. (2022). Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data. Forests, 13(1), 104. https://doi.org/10.3390/f13010104