Forests and plantations are critical for carbon sequestration, but accurately monitoring their growth has traditionally required expensive lidar surveys or labor-intensive fieldwork. A new artificial intelligence model developed by researchers from Beijing Forestry University, Manchester Metropolitan University, and Tsinghua University changes this paradigm by producing high-resolution canopy height maps using only standard RGB imagery. The study, published in the Journal of Remote Sensing on October 20, 2025 (DOI: 10.34133/remotesensing.0880), demonstrates a method that combines large vision foundation models with self-supervised learning to achieve sub-meter accuracy.
Traditional lidar systems provide precise height data but are costly and technically complex, limiting their application to large areas. Optical remote sensing, while cheaper, lacks the structural detail needed for small-scale plantations. Deep learning approaches have improved canopy estimation but require massive labeled datasets and often lose fine spatial details. The new model, called a canopy height estimation network, integrates three components: a feature extractor powered by the DINOv2 large vision foundation model, a self-supervised feature enhancement unit to retain fine details, and a lightweight convolutional height estimator. When tested against airborne lidar measurements, the model achieved a mean absolute error of just 0.09 meters and an R² of 0.78, outperforming traditional CNN and transformer-based methods. It also enabled over 90% accuracy in single-tree detection and strong correlations with measured above-ground biomass.
The model was validated in the Fangshan District of Beijing, a region of fragmented plantations dominated by Populus tomentosa, Pinus tabulaeformis, and Ginkgo biloba. Using one-meter-resolution Google Earth imagery and lidar-derived references, the AI produced canopy height maps that closely matched ground truth data. It significantly outperformed global canopy height model products, capturing subtle variations in tree crown structure that existing models missed. The generated maps supported individual-tree segmentation and plantation-level biomass estimation with R² values exceeding 0.9 for key species. When applied to a geographically distinct forest in Saihanba, the network maintained robust accuracy, confirming its cross-regional adaptability.
“Our model demonstrates that large vision foundation models (LVFMs) can fundamentally transform forestry monitoring,” said Dr. Xin Zhang, corresponding author at Manchester Metropolitan University. “By combining global image pretraining with local self-supervised enhancement, we achieved lidar-level precision using ordinary RGB imagery. This approach drastically reduces costs and expands access to accurate forest data for carbon accounting and environmental management.” The ability to reconstruct annual growth trends from archived satellite imagery provides a scalable solution for long-term carbon sink monitoring and precision forestry management.
The AI-based mapping framework offers a powerful and affordable approach for tracking forest growth, optimizing plantation management, and verifying carbon credits. Its adaptability across ecosystems makes it suitable for global afforestation and reforestation monitoring programs. Future research will extend this method to natural and mixed forests, integrate automated species classification, and support real-time carbon monitoring platforms. As the world advances toward net-zero goals, such intelligent, scalable mapping tools could play a central role in achieving sustainable forestry and climate-change mitigation.
