Optimizing automated photo identification for population assessments.

Journal: Conservation biology : the journal of the Society for Conservation Biology
Published Date:

Abstract

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. To that end, we conducted a simulation study informed by 39 photo-ID datasets representing 24 cetacean species. We fed the results into a custom optimization tool to discern the optimal strategy for each dataset. Our strategies included choosing between truly and partially automated photo-ID and, in the case of the latter, choosing the number of suggested matches to inspect. True automation was optimal for datasets for which the algorithm identified individuals well. As identification performance declined, the optimization recommended that users inspect more suggested matches from the ID algorithm, particularly for small datasets. False negatives (i.e., individual was resighted but erroneously marked as a first capture) strongly predicted estimation error. A 2% increase in the false negative rate translated to a 5% increase in the relative bias in abundance estimates. Our framework can be used to estimate expected error of the abundance estimate, project labor effort, and find the optimal strategy for a dataset and algorithm. We recommend estimating a strategy's false negative rate before implementing the strategy in a population assessment. Our framework provides organizations with insights into the conservation benefits and consequences of automation as conservation enters a new era of artificial intelligence for population assessments.

Authors

  • Philip T Patton
    Marine Mammal Research Program, Hawai'i Institute of Marine Biology, University of Hawai'i at Mānoa, Kāne'ohe, Hawai'i, USA.
  • Krishna Pacifici
    Department of Forestry and Environmental Resources, North Carolina State University, Raleigh, North Carolina, USA.
  • Robin W Baird
    Cascadia Research Collective, Olympia, Washington, USA.
  • Erin M Oleson
    NOAA Fisheries Pacific Islands Fisheries Science Center, Honolulu, Hawai'i, USA.
  • Jason B Allen
    Chicago Zoological Society's Sarasota Dolphin Research Program, c/o Mote Marine Laboratory, Sarasota, Florida, USA.
  • Erin Ashe
    Oceans Initiative, Seattle, Washington, USA.
  • Aline Athayde
    Projeto Baleia à Vista (ProBaV), Ilhabela, Brazil.
  • Charla J Basran
    Research Center in Húsavík, University of Iceland, Húsavík, Iceland.
  • Elsa Cabrera
    Centro de Conservación Cetacea (CCC), Santiago, Chile.
  • John Calambokidis
    Cascadia Research Collective, Olympia, Washington, USA.
  • Júlio Cardoso
    Projeto Baleia à Vista (ProBaV), Ilhabela, Brazil.
  • Emma L Carroll
    School of Biological Sciences, University of Auckland - Waipapa Taumata Rau, Auckland, New Zealand.
  • Amina Cesario
    Tethys Research Institute, Milano, Italy.
  • Barbara J Cheney
    School of Biological Sciences, University of Aberdeen, Cromarty, UK.
  • Ted Cheeseman
    Marine Ecological Research Centre, Southern Cross University, Lismore, New South Wales, Australia.
  • Enrico Corsi
    Cascadia Research Collective, Olympia, Washington, USA.
  • Jens J Currie
    Marine Mammal Research Program, Hawai'i Institute of Marine Biology, University of Hawai'i at Mānoa, Kāne'ohe, Hawai'i, USA.
  • John W Durban
    SR3, SeaLife Response, Rehabilitation and Research, Des Moines, Iowa, USA.
  • Erin A Falcone
    Marine Ecology and Telemetry Research, Seabeck, Washington, USA.
  • Holly Fearnbach
    SR3, SeaLife Response, Rehabilitation and Research, Des Moines, Iowa, USA.
  • Kiirsten Flynn
    Cascadia Research Collective, Olympia, Washington, USA.
  • Trish Franklin
    Marine Ecological Research Centre, Southern Cross University, Lismore, New South Wales, Australia.
  • Wally Franklin
    Marine Ecological Research Centre, Southern Cross University, Lismore, New South Wales, Australia.
  • Bárbara Galletti Vernazzani
    Centro de Conservación Cetacea (CCC), Santiago, Chile.
  • Tilen Genov
    Morigenos - Slovenian Marine Mammal Society, Piran, Slovenia.
  • Marie Hill
    NOAA Fisheries Pacific Islands Fisheries Science Center, Honolulu, Hawai'i, USA.
  • David R Johnston
    Marine Science Department, Te Tari Putaiao Taimoana, University of Otago, Otago, New Zealand.
  • Erin L Keene
    Marine Ecology and Telemetry Research, Seabeck, Washington, USA.
  • Claire Lacey
    Marine Mammal Research Program, Hawai'i Institute of Marine Biology, University of Hawai'i at Mānoa, Kāne'ohe, Hawai'i, USA.
  • Sabre D Mahaffy
    Cascadia Research Collective, Olympia, Washington, USA.
  • Tamara L McGuire
    The Cook Inlet Beluga Whale Photo-ID Project, Anchorage, Alaska, USA.
  • Liah McPherson
    Marine Mammal Research Program, Hawai'i Institute of Marine Biology, University of Hawai'i at Mānoa, Kāne'ohe, Hawai'i, USA.
  • Catherine Meyer
    School of Biological Sciences, Te Kura Mātauranga Koiora, University of Auckland, Auckland, New Zealand.
  • Robert Michaud
    Groupe de Recherche et D'éducation sur les Mammifères Marins (GREMM), Tadoussac, Quebec, Canada.
  • Anastasia Miliou
    Archipelagos Institute of Marine Conservation, Samos Island, Greece.
  • Grace L Olson
    Pacific Whale Foundation, Wailuku, Hawai'i, USA.
  • Dara N Orbach
    Department of Life Sciences, Texas A&M University-Corpus Christi, Corpus Christi, Texas, USA.
  • Heidi C Pearson
    Department of Natural Sciences, University of Alaska Southeast, Juneau, Alaska, USA.
  • Marianne H Rasmussen
    Research Center in Húsavík, University of Iceland, Húsavík, Iceland.
  • William J Rayment
    Marine Science Department, Te Tari Putaiao Taimoana, University of Otago, Otago, New Zealand.
  • Caroline Rinaldi
    L'association Evasion Tropicale, Bouillante, France.
  • Renato Rinaldi
    L'association Evasion Tropicale, Bouillante, France.
  • Salvatore Siciliano
    Departamento de Ciências Biológicas, Escola Nacional de Saúde Pública/Fiocruz, Rio de Janeiro, Brazil.
  • Stephanie H Stack
    Pacific Whale Foundation, Wailuku, Hawai'i, USA.
  • Beatriz Tintore
    Archipelagos Institute of Marine Conservation, Samos Island, Greece.
  • Leigh G Torres
    Marine Mammal Institute, Oregon State University, Newport, Oregon, USA.
  • Jared R Towers
    Bay Cetology, Alert Bay, British Columbia, Canada.
  • Reny B Tyson Moore
    Sarasota Dolphin Research Program, Brookfield Zoo Chicago, c/o Mote Marine Laboratory, Sarasota, Florida, USA.
  • Caroline R Weir
    Falklands Conservation, Stanley, Falkland Islands.
  • Rebecca Wellard
    Centre for Marine Science and Technology, Curtin University, Bentley, Western Australia, Australia.
  • Randall S Wells
    Chicago Zoological Society's Sarasota Dolphin Research Program, c/o Mote Marine Laboratory, Sarasota, Florida, USA.
  • Kymberly M Yano
    NOAA Fisheries Pacific Islands Fisheries Science Center, Honolulu, Hawai'i, USA.
  • Jochen R Zaeschmar
    Far Out Ocean Research Collective, Paihia, New Zealand.
  • Lars Bejder
    Marine Mammal Research Program, Hawai'i Institute of Marine Biology, University of Hawai'i at Mānoa, Kāne'ohe, Hawai'i, USA.