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

Wu, Zijing, Zhang, Ce, Gu, Xiaowei, Duporge, Isla, Hughey, Lacey, Stabach, Jared, Skidmore, Andrew, Hopcraft, Grant, Lee, Stephen, Atkinson, Peter, and others. (2023) Deep learning enables satellite-based monitoring of large populations of terrestrial mammals across heterogeneous landscapes. Nature Communications, 14 (1). Article Number 3072. E-ISSN 2041-1723. (doi:10.1038/s41467-023-38901-y) (KAR id:101405)

PDF Publisher pdf Language: English This work is licensed under a Creative Commons Attribution 4.0 International License.
Download this file (PDF/9MB)	Preview
Request a format suitable for use with assistive technology e.g. a screenreader
PDF Author's Accepted Manuscript Language: English Restricted to Repository staff only
Contact us about this Publication
Official URL: https://doi.org/10.1038/s41467-023-38901-y

Abstract

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.

Item Type:	Article
DOI/Identification number:	10.1038/s41467-023-38901-y
Uncontrolled keywords:	Animals, Mammals, Ecosystem, Biodiversity, Remote Sensing Technology, Deep Learning
Subjects:	Q Science > QA Mathematics (inc Computing science)
Divisions:	Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Funders:	Microsoft Research (United Kingdom) (https://ror.org/05k87vq12) European Council (https://ror.org/001b17f86)
Depositing User:	Xiaowei Gu
Date Deposited:	25 May 2023 06:52 UTC
Last Modified:	05 Nov 2024 13:07 UTC
Resource URI:	https://kar.kent.ac.uk/id/eprint/101405 (The current URI for this page, for reference purposes)

University of Kent Author Information

Gu, Xiaowei.

Creator's ORCID:	https://orcid.org/0000-0001-9116-4761
CReDIT Contributor Roles:

Depositors only (login required):

Altmetric

Download Statistics

Total unique views for this document in KAR since July 2020. For more details click on the image.