Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale

Sustainable tree resource management is the key to mitigating climate warming, fostering a green economy, and protecting valuable habitats. Detailed knowledge about tree resources is a prerequisite for such management but is conventionally based on plot-scale data, which often neglects trees outside forests. Here, we present a deep learning-based framework that provides location, crown area, and height for individual overstory trees from aerial images at country scale. We apply the framework on data covering Denmark and show that large trees (stem diameter >10 cm) can be identified with a low bias (12.5%) and that trees outside forests contribute to 30% of the total tree cover, which is typically unrecognized in national inventories. The bias is high (46.6%) when our results are evaluated against all trees taller than 1.3 m, which involve undetectable small or understory trees. Furthermore, we demonstrate that only marginal effort is needed to transfer our framework to data from Finland, despite markedly dissimilar data sources. Our work lays the foundation for digitalized national databases, where large trees are spatially traceable and manageable.

Automated summary

Sustainable tree resource management is crucial for mitigating climate warming, fostering a green economy, and protecting habitats. In this study, a deep learning-based framework was developed to provide location, crown area, and height information of individual overstory trees from aerial images at the country scale. The results showed a low bias in identifying large trees and highlighted the significant contribution of trees outside forests to total tree cover, which is often overlooked in national inventories. However, the framework had a higher bias when evaluating all taller trees, including small or understory trees that are undetectable. Moreover, the framework was easily transferable to data from Finland, despite different data sources.