Building use-inspired species distribution models: Using multiple data types to examine and improve model performance.
Autor: | Braun CD; Biology Department, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts, USA., Arostegui MC; Biology Department, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts, USA., Farchadi N; Institute for Ecological Monitoring and Management, San Diego State University, San Diego, California, USA., Alexander M; NOAA Earth System Research Laboratory, Boulder, Colorado, USA., Afonso P; Biology Department, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts, USA.; Okeanos and Institute of Marine Research, University of the Azores, Horta, Portugal., Allyn A; Gulf of Maine Research Institute, Portland, Maine, USA., Bograd SJ; Environmental Research Division, Southwest Fisheries Science Center, National Oceanic and Atmospheric Administration, Monterey, California, USA., Brodie S; Environmental Research Division, Southwest Fisheries Science Center, National Oceanic and Atmospheric Administration, Monterey, California, USA.; Institute of Marine Sciences, University of California, Santa Cruz, California, USA., Crear DP; ECS Federal, in Support of National Marine Fisheries Service, Atlantic Highly Migratory Species Management Division, Silver Spring, Maryland, USA., Culhane EF; Biology Department, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts, USA.; Massachusetts Institute of Technology-Woods Hole Oceanographic Institution Joint Program in Oceanography-Applied Ocean Science and Engineering, Cambridge, Massachusetts, USA., Curtis TH; National Marine Fisheries Service, Atlantic Highly Migratory Species Management Division, Gloucester, Massachusetts, USA., Hazen EL; Environmental Research Division, Southwest Fisheries Science Center, National Oceanic and Atmospheric Administration, Monterey, California, USA.; Institute of Marine Sciences, University of California, Santa Cruz, California, USA., Kerney A; Gulf of Maine Research Institute, Portland, Maine, USA., Lezama-Ochoa N; Environmental Research Division, Southwest Fisheries Science Center, National Oceanic and Atmospheric Administration, Monterey, California, USA.; Institute of Marine Sciences, University of California, Santa Cruz, California, USA., Mills KE; Gulf of Maine Research Institute, Portland, Maine, USA., Pugh D; Gulf of Maine Research Institute, Portland, Maine, USA., Queiroz N; Research Network in Biodiversity and Evolutionary Biology, Universidade do Porto, Vairão, Portugal.; Marine Biological Association of the United Kingdom, The Laboratory, Plymouth, UK., Scott JD; NOAA Earth System Research Laboratory, Boulder, Colorado, USA.; Cooperative Institute for Research in Environmental Sciences, University of Colorado Boulder, Boulder, Colorado, USA., Skomal GB; Massachusetts Division of Marine Fisheries, New Bedford, Massachusetts, USA., Sims DW; Marine Biological Association of the United Kingdom, The Laboratory, Plymouth, UK.; Ocean and Earth Science, National Oceanography Centre Southampton, University of Southampton, Southampton, UK., Thorrold SR; Biology Department, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts, USA., Welch H; Environmental Research Division, Southwest Fisheries Science Center, National Oceanic and Atmospheric Administration, Monterey, California, USA.; Institute of Marine Sciences, University of California, Santa Cruz, California, USA., Young-Morse R; Gulf of Maine Research Institute, Portland, Maine, USA., Lewison RL; Institute for Ecological Monitoring and Management, San Diego State University, San Diego, California, USA. |
---|---|
Jazyk: | angličtina |
Zdroj: | Ecological applications : a publication of the Ecological Society of America [Ecol Appl] 2023 Sep; Vol. 33 (6), pp. e2893. Date of Electronic Publication: 2023 Jul 10. |
DOI: | 10.1002/eap.2893 |
Abstrakt: | Species distribution models (SDMs) are becoming an important tool for marine conservation and management. Yet while there is an increasing diversity and volume of marine biodiversity data for training SDMs, little practical guidance is available on how to leverage distinct data types to build robust models. We explored the effect of different data types on the fit, performance and predictive ability of SDMs by comparing models trained with four data types for a heavily exploited pelagic fish, the blue shark (Prionace glauca), in the Northwest Atlantic: two fishery dependent (conventional mark-recapture tags, fisheries observer records) and two fishery independent (satellite-linked electronic tags, pop-up archival tags). We found that all four data types can result in robust models, but differences among spatial predictions highlighted the need to consider ecological realism in model selection and interpretation regardless of data type. Differences among models were primarily attributed to biases in how each data type, and the associated representation of absences, sampled the environment and summarized the resulting species distributions. Outputs from model ensembles and a model trained on all pooled data both proved effective for combining inferences across data types and provided more ecologically realistic predictions than individual models. Our results provide valuable guidance for practitioners developing SDMs. With increasing access to diverse data sources, future work should further develop truly integrative modeling approaches that can explicitly leverage the strengths of individual data types while statistically accounting for limitations, such as sampling biases. (© 2023 The Ecological Society of America.) |
Databáze: | MEDLINE |
Externí odkaz: |