AI Science Tracker
EN

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

Department of Natural Resources, Faculty of Geo-Information Science and Earth Observation, University of Twente, Enschede, The Netherlands · 27 May 2023 · biology

Discovery

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

Source check: Source checked. Not independent scientific confirmation.

Finding: Nearly 500,000 wildebeest and zebra were counted across heterogeneous satellite imagery with reported precision, recall and F1. The result is bounded to the studied Serengeti-Mara ecosystem and imagery; performance in other species or regions is not established.

Technology: A U-Net ensemble produces satellite-image probability maps and K-means converts detections into individual ungulates.

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
A U-Net ensemble produces satellite-image probability maps and K-means converts detections into individual ungulates.
Test and result
Nearly 500,000 wildebeest and zebra were counted across heterogeneous satellite imagery with reported precision, recall and F1.
Limitation / still unknown
The result is bounded to the studied Serengeti-Mara ecosystem and imagery; performance in other species or regions is not established.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41467-023-38901-y

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse biology discoveries.