Optimizing Automated Photo Identification for Population Assessments
January 25, 2025
Researchers can use high-performance identification algorithms to reduce the cost of population assessments without biasing abundance estimates.
Several legal acts mandate that management agencies regularly assess biological populations. For species with distinct markings, these assessments can be conducted noninvasively via capture-recapture and photographic identification (photo-ID), which involves processing considerable quantities of photographic data. To ease this burden, agencies increasingly rely on automated identification (ID) algorithms. Identification algorithms present agencies with an opportunity—reducing the cost of population assessments—and a challenge—propagating misidentifications into abundance estimates at a large scale. We explored several strategies for generating capture histories with an ID algorithm, evaluating trade-offs between labor costs and estimation error in a hypothetical population assessment.
Patton PT, Pacifici K, Baird RW, Oleson EM, Allen JB, Ashe E, Athayde A, Basran CJ, Cabrera E, Calambokidis J, Cardoso, J, Carroll EL, Cesario A, Cheney BJ, Cheeseman T, Corsi E, Currie JJ, Durban JW, Falcone EA ... Bejder L 2025. Optimizing automated photo identification for population assessments Conservation Biology, e14436.
https://doi.org/10.1111/cobi.14436