Researchers have developed a deep-learning framework that combines multisensor satellite imagery to estimate tree abundance across entire nations, producing a baseline that could transform how governments plan and monitor tree restoration efforts. Applied to Rwanda and Tanzania, the framework counted approximately 5.25 billion trees—about 213 million in Rwanda and 5.04 billion in Tanzania—and found that only 48.8% of those trees fell within the WorldCover "tree cover" class. The remaining 51.2% occurred across shrublands, grasslands, croplands, built-up areas, wetlands, sparse vegetation, and mangroves.
The study, led by the University of Copenhagen, was published (DOI: 10.34133/remotesensing.0970) on August 18, 2026, in the Journal of Remote Sensing. The research addresses a growing need: global tree-planting pledges have increased sharply since the Paris Agreement, creating demand for reliable baselines showing how many trees already exist and where they occur. Field inventories are costly and spatially limited, while repeated acquisition of submeter satellite or UAV imagery is difficult to scale. Object-detection methods also struggle when crowns overlap, occupy fractions of pixels, or lack clear boundaries.
The framework uses PlanetScope, Sentinel-1, and Sentinel-2 imagery, analyzing 96 × 96 meter image patches from a 20-band composite resampled to a common 3-meter grid. A hybrid UNet-ResNet50 architecture predicts one tree-count value per patch, estimating tree numbers from spatial, spectral, and textural patterns rather than detecting every crown individually. In comparisons, UNet-R50 achieved a mean absolute error of 17.32 and an r² of 0.73, outperforming ResNet50, ResNeXt50, SwinT, and ViT. Sensor-ablation tests showed that Sentinel-1 plus Sentinel-2 reached an MAE of 18.42 and r² of 0.77, comparable with the three-sensor composite at 18.8 and 0.77, respectively.
Training used about 12 million tree-crown centers from diverse landscapes, with labels assembled from manual interpretation of submeter imagery and semi-automated extraction from airborne and UAV LiDAR canopy-height models. National predictions were bias-corrected using independent National Forest Inventory measurements with country- and land-cover-specific bootstrap calibration. Final estimates indicated median densities of 37 trees per hectare in Rwanda and 42 in Tanzania.
The researchers emphasized the framework's practical value, noting that it "can guide the planning and optimization of resource allocation for tree restoration efforts at national scales." They argue that repeatable satellite-based baselines could help governments track restoration outcomes, identify appropriate planting areas, and better account for trees growing beyond conventional forest boundaries. The approach also avoids dependence on explicit crown boundaries, allowing tree numbers to be inferred even when individual crowns are not fully resolved at 3-meter pixel resolution.
Future work must improve performance in dense closed-canopy forests, where crown overlap and signal saturation reduce sensitivity, and incorporate understory or smaller woody plants. The authors propose integrating forest inventories and very-high-resolution data while exploring attention-based sensor fusion, domain adaptation, and transfer learning to extend the approach to new regions, ecosystems, and satellite sensors at larger scales. The full study is available at https://spj.science.org/doi/10.34133/remotesensing.0970.
