Accepted author manuscript, 243 KB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Final published version
Licence: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Deep learning enables satellite-based monitoring of large populations of terrestrial mammals across heterogeneous landscape
AU - Wu, Zijing
AU - Zhang, Ce
AU - Gu, Xiaowei
AU - Duporge, Isla
AU - Hughey, Lacey
AU - Stabach, Jared
AU - Skidmore, Andrew
AU - Hopcraft, Grant
AU - Lee, Stephen
AU - Atkinson, Peter
AU - McCauley, Douglas
AU - Lamprey, Richard
AU - Ngene, Shadrack
AU - Wang, Tiejun
PY - 2023/5/27
Y1 - 2023/5/27
N2 - 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.
AB - 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.
U2 - 10.1038/s41467-023-38901-y
DO - 10.1038/s41467-023-38901-y
M3 - Journal article
C2 - 37244940
VL - 14
SP - 1
EP - 15
JO - Nature Communications
JF - Nature Communications
SN - 2041-1723
IS - 1
M1 - 3072
ER -