Spatiotemporal exploratory models for broad-scale survey data

Daniel Fink, Wesley M. Hochachka, Benjamin Zuckerberg, David W. Winkler, Ben Shaby, M. Arthur Munson, Giles Hooker, Mirek Riedewald, Daniel Sheldon, Steve Kelling

Research output: Contribution to journalArticle

123 Citations (Scopus)

Abstract

The distributions of animal populations change and evolve through time. Migratory species exploit different habitats at different times of the year. Biotic and abiotic features that determine where a species lives vary due to natural and anthropogenic factors. This spatiotemporal variation needs to be accounted for in any modeling of species' distributions. In this paper we introduce a semiparametric model that provides a flexible framework for analyzing dynamic patterns of species occurrence and abundance from broadscale survey data. The spatiotemporal exploratory model (STEM) adds essential spatiotemporal structure to existing techniques for developing species distribution models through a simple parametric structure without requiring a detailed understanding of the underlying dynamic processes. STEMs use a multi-scale strategy to differentiate between local and globalscale spatiotemporal structure. A user-specified species distribution model accounts for spatial and temporal patterning at the local level. These local patterns are then allowed to "scale up" via ensemble averaging to larger scales. This makes STEMs especially well suited for exploring distributional dynamics arising from a variety of processes. Using data from eBird, an online citizen science bird-monitoring project, we demonstrate that monthly changes in distribution of a migratory species, the Tree Swallow (Tachycineta bicolor), can be more accurately described with a STEM than a conventional bagged decision tree model in which spatiotemporal structure has not been imposed. We also demonstrate that there is no loss of model predictive power when a STEM is used to describe a spatiotemporal distribution with very little spatiotemporal variation; the distribution of a nonmigratory species, the Northern Cardinal (Cardinalis cardinalis).

Original languageEnglish (US)
Pages (from-to)2131-2147
Number of pages17
JournalEcological Applications
Volume20
Issue number8
DOIs
StatePublished - Dec 1 2010

Fingerprint

migratory species
species occurrence
distribution
bird
habitat
monitoring
modeling
science
citizen
anthropogenic factor
animal population
loss
project
decision

All Science Journal Classification (ASJC) codes

  • Ecology

Cite this

Fink, D., Hochachka, W. M., Zuckerberg, B., Winkler, D. W., Shaby, B., Munson, M. A., ... Kelling, S. (2010). Spatiotemporal exploratory models for broad-scale survey data. Ecological Applications, 20(8), 2131-2147. https://doi.org/10.1890/09-1340.1
Fink, Daniel ; Hochachka, Wesley M. ; Zuckerberg, Benjamin ; Winkler, David W. ; Shaby, Ben ; Munson, M. Arthur ; Hooker, Giles ; Riedewald, Mirek ; Sheldon, Daniel ; Kelling, Steve. / Spatiotemporal exploratory models for broad-scale survey data. In: Ecological Applications. 2010 ; Vol. 20, No. 8. pp. 2131-2147.
@article{5c3074a9792f473da54b142a0d22406e,
title = "Spatiotemporal exploratory models for broad-scale survey data",
abstract = "The distributions of animal populations change and evolve through time. Migratory species exploit different habitats at different times of the year. Biotic and abiotic features that determine where a species lives vary due to natural and anthropogenic factors. This spatiotemporal variation needs to be accounted for in any modeling of species' distributions. In this paper we introduce a semiparametric model that provides a flexible framework for analyzing dynamic patterns of species occurrence and abundance from broadscale survey data. The spatiotemporal exploratory model (STEM) adds essential spatiotemporal structure to existing techniques for developing species distribution models through a simple parametric structure without requiring a detailed understanding of the underlying dynamic processes. STEMs use a multi-scale strategy to differentiate between local and globalscale spatiotemporal structure. A user-specified species distribution model accounts for spatial and temporal patterning at the local level. These local patterns are then allowed to {"}scale up{"} via ensemble averaging to larger scales. This makes STEMs especially well suited for exploring distributional dynamics arising from a variety of processes. Using data from eBird, an online citizen science bird-monitoring project, we demonstrate that monthly changes in distribution of a migratory species, the Tree Swallow (Tachycineta bicolor), can be more accurately described with a STEM than a conventional bagged decision tree model in which spatiotemporal structure has not been imposed. We also demonstrate that there is no loss of model predictive power when a STEM is used to describe a spatiotemporal distribution with very little spatiotemporal variation; the distribution of a nonmigratory species, the Northern Cardinal (Cardinalis cardinalis).",
author = "Daniel Fink and Hochachka, {Wesley M.} and Benjamin Zuckerberg and Winkler, {David W.} and Ben Shaby and Munson, {M. Arthur} and Giles Hooker and Mirek Riedewald and Daniel Sheldon and Steve Kelling",
year = "2010",
month = "12",
day = "1",
doi = "10.1890/09-1340.1",
language = "English (US)",
volume = "20",
pages = "2131--2147",
journal = "Ecological Applications",
issn = "1051-0761",
publisher = "Ecological Society of America",
number = "8",

}

Fink, D, Hochachka, WM, Zuckerberg, B, Winkler, DW, Shaby, B, Munson, MA, Hooker, G, Riedewald, M, Sheldon, D & Kelling, S 2010, 'Spatiotemporal exploratory models for broad-scale survey data', Ecological Applications, vol. 20, no. 8, pp. 2131-2147. https://doi.org/10.1890/09-1340.1

Spatiotemporal exploratory models for broad-scale survey data. / Fink, Daniel; Hochachka, Wesley M.; Zuckerberg, Benjamin; Winkler, David W.; Shaby, Ben; Munson, M. Arthur; Hooker, Giles; Riedewald, Mirek; Sheldon, Daniel; Kelling, Steve.

In: Ecological Applications, Vol. 20, No. 8, 01.12.2010, p. 2131-2147.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spatiotemporal exploratory models for broad-scale survey data

AU - Fink, Daniel

AU - Hochachka, Wesley M.

AU - Zuckerberg, Benjamin

AU - Winkler, David W.

AU - Shaby, Ben

AU - Munson, M. Arthur

AU - Hooker, Giles

AU - Riedewald, Mirek

AU - Sheldon, Daniel

AU - Kelling, Steve

PY - 2010/12/1

Y1 - 2010/12/1

N2 - The distributions of animal populations change and evolve through time. Migratory species exploit different habitats at different times of the year. Biotic and abiotic features that determine where a species lives vary due to natural and anthropogenic factors. This spatiotemporal variation needs to be accounted for in any modeling of species' distributions. In this paper we introduce a semiparametric model that provides a flexible framework for analyzing dynamic patterns of species occurrence and abundance from broadscale survey data. The spatiotemporal exploratory model (STEM) adds essential spatiotemporal structure to existing techniques for developing species distribution models through a simple parametric structure without requiring a detailed understanding of the underlying dynamic processes. STEMs use a multi-scale strategy to differentiate between local and globalscale spatiotemporal structure. A user-specified species distribution model accounts for spatial and temporal patterning at the local level. These local patterns are then allowed to "scale up" via ensemble averaging to larger scales. This makes STEMs especially well suited for exploring distributional dynamics arising from a variety of processes. Using data from eBird, an online citizen science bird-monitoring project, we demonstrate that monthly changes in distribution of a migratory species, the Tree Swallow (Tachycineta bicolor), can be more accurately described with a STEM than a conventional bagged decision tree model in which spatiotemporal structure has not been imposed. We also demonstrate that there is no loss of model predictive power when a STEM is used to describe a spatiotemporal distribution with very little spatiotemporal variation; the distribution of a nonmigratory species, the Northern Cardinal (Cardinalis cardinalis).

AB - The distributions of animal populations change and evolve through time. Migratory species exploit different habitats at different times of the year. Biotic and abiotic features that determine where a species lives vary due to natural and anthropogenic factors. This spatiotemporal variation needs to be accounted for in any modeling of species' distributions. In this paper we introduce a semiparametric model that provides a flexible framework for analyzing dynamic patterns of species occurrence and abundance from broadscale survey data. The spatiotemporal exploratory model (STEM) adds essential spatiotemporal structure to existing techniques for developing species distribution models through a simple parametric structure without requiring a detailed understanding of the underlying dynamic processes. STEMs use a multi-scale strategy to differentiate between local and globalscale spatiotemporal structure. A user-specified species distribution model accounts for spatial and temporal patterning at the local level. These local patterns are then allowed to "scale up" via ensemble averaging to larger scales. This makes STEMs especially well suited for exploring distributional dynamics arising from a variety of processes. Using data from eBird, an online citizen science bird-monitoring project, we demonstrate that monthly changes in distribution of a migratory species, the Tree Swallow (Tachycineta bicolor), can be more accurately described with a STEM than a conventional bagged decision tree model in which spatiotemporal structure has not been imposed. We also demonstrate that there is no loss of model predictive power when a STEM is used to describe a spatiotemporal distribution with very little spatiotemporal variation; the distribution of a nonmigratory species, the Northern Cardinal (Cardinalis cardinalis).

UR - http://www.scopus.com/inward/record.url?scp=78149373096&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149373096&partnerID=8YFLogxK

U2 - 10.1890/09-1340.1

DO - 10.1890/09-1340.1

M3 - Article

C2 - 21265447

AN - SCOPUS:78149373096

VL - 20

SP - 2131

EP - 2147

JO - Ecological Applications

JF - Ecological Applications

SN - 1051-0761

IS - 8

ER -

Fink D, Hochachka WM, Zuckerberg B, Winkler DW, Shaby B, Munson MA et al. Spatiotemporal exploratory models for broad-scale survey data. Ecological Applications. 2010 Dec 1;20(8):2131-2147. https://doi.org/10.1890/09-1340.1