Semantic Segmentation of Coral Reefs Using Convolutional Neural Networks: A Case Study in Kiritimati, Kiribati
Remote Sensing · 24.10.2025 · 17 (21) · 3529
DOI: 10.3390/rs17213529 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.10.2025. Verfasst von Dominica E. Harrison und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Canada Foundation for Innovation, NSERC Research Tools and Instruments.
Abstract (Originalsprache)
Habitat complexity plays a critical role in coral reef ecosystems by enhancing habitat availability, increasing ecological resilience, and offering coastal protection. Structure-from-motion (SfM) photogrammetry has become a standard approach for quantifying habitat complexity in reef monitoring programs. However, a major bottleneck remains in the two-dimensional (2D) classification of benthic cover in three-dimensional (3D) models, where experts are required to manually annotate individual colonies and identify coral species or taxonomic groups. With recent advances in deep learning and computer vision, automated classification of benthic habitats is possible. While some semi-automated tools exist, they are often limited in scope or do not provide semantic segmentation. In this investigation, we trained a convolutional neural network with the ResNet101 architecture on three years (2015, 2017, and 2019) of human-annotated 2D orthomosaics from Kiritimati, Kiribati. Our model accuracy ranged from 71% to 95%, with an overall accuracy of 84% and a mean intersection of union of 0.82, despite highly imbalanced training data, and it demonstrated successful generalizability when applied to new, untrained 2023 plots. Successful automation depends on training data that captures local ecological variation. As coral monitoring efforts move toward standardized workflows, locally developed models will be key to achieving fully automated, high-resolution classification of benthic communities across diverse reef environments.
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Canada Foundation for Innovation
- NSERC Research Tools and Instruments
- National Science Foundation
- National Geographic Society
- Pew Charitable Trusts through the Pew Fellowship in Marine Conservation
- Rufford Maurice Laing Foundation
Zitieren
APA
Harrison, D. E., Asner, G. P., Vaughn, N. R., Guimond, C. E., & Baum, J. K. (2025). Semantic Segmentation of Coral Reefs Using Convolutional Neural Networks: A Case Study in Kiritimati, Kiribati. Remote Sensing, 17(21), 3529. https://doi.org/10.3390/rs17213529
Vancouver
Harrison DE, Asner GP, Vaughn NR, Guimond CE, Baum JK. Semantic Segmentation of Coral Reefs Using Convolutional Neural Networks: A Case Study in Kiritimati, Kiribati. Remote Sensing. 2025;17(21):3529. doi:10.3390/rs17213529
BibTeX
@article{Harrison2025,
author = {Harrison, Dominica E. and Asner, Gregory P. and Vaughn, Nicholas R. and Guimond, Calder E. and Baum, Julia K.},
title = {Semantic Segmentation of Coral Reefs Using Convolutional Neural Networks: A Case Study in Kiritimati, Kiribati},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {21},
pages = {3529},
doi = {10.3390/rs17213529}
}
EUVIMED