Mapping of Monodominant Gilbertiodendron dewevrei Forest Across the Western Congo Basin Using Sentinel-2 Imagery

A novel approach using Sentinel-2 imagery successfully mapped monodominant Gilbertiodendron dewevrei forest within the Sangha Trinational, achieving 83% accuracy. This method distinguished G. dewevrei from spectrally similar mixed forests by leveraging spectral, vegetation, and textural indices, with gray level co-occurrence matrix (GLCM) metrics proving critical due to the species' homogeneous canopy texture. The study demonstrates that freely available Sentinel-2 data can effectively classify distinct tropical forest types when combined with high-quality ground reference datasets, offering a promising tool for conservation monitoring in complex rainforest mosaics.

Heimpel, E., Harris, D. J., Mamboueni, J., Morgan, D., Sanz, C., & Ahrends, A. (2025). Mapping of Monodominant Gilbertiodendron dewevrei Forest Across the Western Congo Basin Using Sentinel-2 Imagery. Remote Sensing, 17(9), 1639. https://doi.org/10.3390/rs17091639