Digital twinning of all forest and non-forest trees at national level via deep learning

Abstract Intelligent forest management is the key to mitigating climate warming, fostering a green economy, and protecting valuable habitats. Detailed knowledge about forests is a prerequisite for such management but is conventionally based on costly plot-scale data, rarely available at resolution of relevance for management strategies. Here, we present a deep learning-based framework that provides location, crown area and height for each individual tree from aerial images at country scale. We quantify and characterize all individual trees in Denmark and show that 26% of the trees grow outside forests, which is typically unrecognized in national inventories. Furthermore, we demonstrate that only marginal effort is needed to transfer our framework to Finland, despite markedly dissimilar landscapes and data sources. Our work lays the foundation for a global database, where every tree has its digital twin and is spatially traceable and manageable.