Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale
PNAS Nexus · 03.04.2023 · 2 (4)
DOI: 10.1093/pnasnexus/pgad076 ↗Kurz gefasst
Fachartikel in der Zeitschrift PNAS Nexus, online erschienen am 09.03.2023. Verfasst von Sizhuo Li und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen 1350, Denmark. Die Arbeit wurde bisher 96-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen 1350, Denmark.
- Département Sciences de la terre et de l'univers, espace, Université Paris-Saclay, Gif-sur-Yvette 91190, France.
- Department of Computer Science, University of Copenhagen, Copenhagen 2100, Denmark.
- Department of Information Systems, University of Münster, Münster 48149, Germany.
- Department of Earth Observations, The Danish Agency for Data Supply and Infrastructure, Copenhagen 2400, Denmark.
- Department of Forest Sciences, University of Eastern Finland, Joensuu 80101, Finland.
ORCID-Profile: Sizhuo Li, Christian Igel, Thomas Nord-Larsen, Philippe Ciais
Zitieren
APA
Li, S., Brandt, M., Fensholt, R., Kariryaa, A., Igel, C., Gieseke, F., Nord-Larsen, T., Oehmcke, S., Carlsen, A. H., Junttila, S., Tong, X., d'Aspremont, A., & Ciais, P. (2023). Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale. PNAS Nexus, 2(4). https://doi.org/10.1093/pnasnexus/pgad076
Vancouver
Li S, Brandt M, Fensholt R, Kariryaa A, Igel C, Gieseke F, et al. Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale. PNAS Nexus. 2023;2(4). doi:10.1093/pnasnexus/pgad076
BibTeX
@article{Li2023,
author = {Li, Sizhuo and Brandt, Martin and Fensholt, Rasmus and Kariryaa, Ankit and Igel, Christian and Gieseke, Fabian and Nord-Larsen, Thomas and Oehmcke, Stefan and Carlsen, Ask Holm and Junttila, Samuli and Tong, Xiaoye and d'Aspremont, Alexandre and Ciais, Philippe},
title = {Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale},
journal = {PNAS Nexus},
year = {2023},
volume = {2},
number = {4},
doi = {10.1093/pnasnexus/pgad076}
}
EUVIMED