Are we there yet? Reliable occupancy modeling from AI ‐labeled trail camera data
Conservation Science and Practice · 2026-08 · 8 (8)
DOI: 10.1111/csp2.70367 ↗Kurz gefasst
Fachartikel in der Zeitschrift Conservation Science and Practice, online erschienen am 05.08.2026. Verfasst von Mohamed Khalil Meliane und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agricultural Research Service, National Fish and Wildlife Foundation.
Abstract (Originalsprache)
Computer vision is increasingly adopted to automate wildlife image classification, but its ecological reliability remains largely untested. We evaluated SpeciesNet, a global wildlife classifier on widespread mammal species of Florida, USA: the white‐tailed deer ( Odocoileus virginianus ), wild pig ( Sus scrofa ), coyote ( Canis latrans ) and bobcat ( Lynx rufus ). While conventional computer‐vision evaluation scores were high (e.g., F1 = 98.2% for the white‐tailed deer), they masked species‐specific false‐positive rates (FPRs) that drove bias in downstream occupancy estimates. The white‐tailed deer with FPR = 0.14% produced the largest divergence from the human‐labeled data, whereas bobcat, with a lower F1 (94.5%) but FPR = 0.01%, yielded near‐identical estimates. We show that FPRs, not conventional metrics like F1‐scores, are key factors for occupancy estimate accuracy when using standard models. Our findings highlight the limitations of conventional performance metrics when evaluating AI tools for ecological applications and the need of false‐positive‐adequate methods as AI‐classifiers gain popularity. Our analysis shows that false‐positive‐informed occupancy models quickly outperform standard models as FPRs increase. Standard models still retain an advantage at low false positive rates (
Förderung
- Agricultural Research Service
- National Fish and Wildlife Foundation
Zitieren
APA
Meliane, M. K., Guthrie, J. M., & Ellington, E. H. (2026). Are we there yet? Reliable occupancy modeling from AI ‐labeled trail camera data. Conservation Science and Practice, 8(8). https://doi.org/10.1111/csp2.70367
Vancouver
Meliane MK, Guthrie JM, Ellington EH. Are we there yet? Reliable occupancy modeling from AI ‐labeled trail camera data. Conservation Science and Practice. 2026;8(8). doi:10.1111/csp2.70367
BibTeX
@article{Meliane2026,
author = {Meliane, Mohamed Khalil and Guthrie, Joseph M. and Ellington, E. Hance},
title = {Are we there yet? Reliable occupancy modeling from AI ‐labeled trail camera data},
journal = {Conservation Science and Practice},
year = {2026},
volume = {8},
number = {8},
doi = {10.1111/csp2.70367}
}
EUVIMED