An Open and Transferable Deep Learning Framework for Mapping Urban Tree Canopy Using NAIP Imagery
Remote Sensing · 09.06.2026 · 18 (12) · 1899
DOI: 10.3390/rs18121899 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 09.06.2026. Verfasst von Jooyoung Yoo und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Emory University, Atlanta, GA 30322, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NIEHS NIH HHS, Climate-related Exposures, Adaptation, and Health Equity (CLIMA) Center funded by the National Heart, Lung, and Blood Institute.
Abstract (Originalsprache)
The urban tree canopy is an important resource that spans public and private property and whose form and quantity change over short distances. Although remote sensing and deep learning approaches have been used to map urban tree canopy, the high cost of commercial imagery and the technical complexity of model development have limited their adoption by urban forestry practitioners. We developed a structured and reproducible deep learning workflow optimized for freely available USDA National Agriculture Imagery Program (NAIP) imagery. The workflow incorporates a reproducible U-Net segmentation model for canopy delineation and a YOLOv9e object detection model for individual tree identification, enabling complementary estimation of the canopy extent and individual tree locations. Across two neighborhoods in Los Angeles, the optimized U-Net achieved a Dice coefficient of 0.824 for canopy segmentation, while YOLOv9e reached an F1-score of 0.687 for individual tree detection on a held-out test set with 17,466 annotated trees. A data sufficiency experiment showed that model performance stabilizes when approximately 130 trees are annotated per 320 × 320 pixel (px) tile, corresponding to about 25,379 training and 2641 validation labels, providing a practical target for annotation effort. Additional experiments demonstrate a structured workflow for spatial sampling, training data requirements, and the use of model inferences to estimate tree canopy extent and individual tree locations. The workflow also shows encouraging evidence of transferability to previously unseen urban areas without retraining. By relying solely on NAIP-optimized approaches, this new workflow bridges the gap between complex deep learning techniques and the practical needs of urban foresters; empowers local stakeholders to create accurate, affordable, and timely urban tree inventories; and fosters data-driven decision-making for the sustainable management of urban green infrastructure.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, Emory University, Atlanta, GA 30322, USA.
- Spatial Sciences Institute, University of Southern California, Los Angeles, CA 90089, USA.
ORCID-Profile: Jooyoung Yoo, Yi Qi, Beau MacDonald, John P Wilson
Förderung
- NHLBI NIH HHS
- NIEHS NIH HHS
- Climate-related Exposures, Adaptation, and Health Equity (CLIMA) Center funded by the National Heart, Lung, and Blood Institute
- Southern California Environmental Health Science Center (SCEHSC) funded by the National Institute of Environmental Health Sciences
- Bezos Earth Fund
Zitieren
APA
Yoo, J., Qi, Y., Ashe-McNalley, I., MacDonald, B., & Wilson, J. P. (2026). An Open and Transferable Deep Learning Framework for Mapping Urban Tree Canopy Using NAIP Imagery. Remote Sensing, 18(12), 1899. https://doi.org/10.3390/rs18121899
Vancouver
Yoo J, Qi Y, Ashe-McNalley I, MacDonald B, Wilson JP. An Open and Transferable Deep Learning Framework for Mapping Urban Tree Canopy Using NAIP Imagery. Remote Sensing. 2026;18(12):1899. doi:10.3390/rs18121899
BibTeX
@article{Yoo2026,
author = {Yoo, Jooyoung and Qi, Yi and Ashe-McNalley, Isaac and MacDonald, Beau and Wilson, John P},
title = {An Open and Transferable Deep Learning Framework for Mapping Urban Tree Canopy Using NAIP Imagery},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {12},
pages = {1899},
doi = {10.3390/rs18121899}
}
EUVIMED