Deep learning enables satellite-based monitoring of large populations of terrestrial mammals across heterogeneous landscape

New satellite remote sensing and machine learning techniques offer untapped possibilities to monitor global biodiversity with unprecedented speed and precision. These efficiencies promise to reveal novel ecological insights at spatial scales which are germane to the management of populations and ent...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nature communications Jg. 14; H. 1; S. 3072 - 15
Hauptverfasser: Wu, Zijing, Zhang, Ce, Gu, Xiaowei, Duporge, Isla, Hughey, Lacey F., Stabach, Jared A., Skidmore, Andrew K., Hopcraft, J. Grant C., Lee, Stephen J., Atkinson, Peter M., McCauley, Douglas J., Lamprey, Richard, Ngene, Shadrack, Wang, Tiejun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 27.05.2023
Nature Publishing Group
Nature Portfolio
Schlagworte:
639/624/1107/510
704/158/2039
Animal behavior
Animals
Biodiversity
Deep Learning
Ecosystem
Ecosystems
Humanities and Social Sciences
Learning algorithms
Machine learning
Mammals
multidisciplinary
Populations
Remote sensing
Remote Sensing Technology
Satellite imagery
Satellites
Science
Science (multidisciplinary)
Strategic management
Ungulates
ISSN:2041-1723, 2041-1723
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:New satellite remote sensing and machine learning techniques offer untapped possibilities to monitor global biodiversity with unprecedented speed and precision. These efficiencies promise to reveal novel ecological insights at spatial scales which are germane to the management of populations and entire ecosystems. Here, we present a robust transferable deep learning pipeline to automatically locate and count large herds of migratory ungulates (wildebeest and zebra) in the Serengeti-Mara ecosystem using fine-resolution (38-50 cm) satellite imagery. The results achieve accurate detection of nearly 500,000 individuals across thousands of square kilometers and multiple habitat types, with an overall F1-score of 84.75% (Precision: 87.85%, Recall: 81.86%). This research demonstrates the capability of satellite remote sensing and machine learning techniques to automatically and accurately count very large populations of terrestrial mammals across a highly heterogeneous landscape. We also discuss the potential for satellite-derived species detections to advance basic understanding of animal behavior and ecology. This study presents a deep learning pipeline to automatically locate and count large herds of migratory ungulates (wildebeest and zebra) in the Serengeti-Mara ecosystem using fine resolution satellite imagery. The results achieve accurate detection of nearly 500,000 individuals across thousands of square kilometers and multiple habitat types.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-023-38901-y