Incorporating spatial dependence in predictive vegetation models

Jennifer Miller, Janet Franklin, Richard Aspinall

Research output: Contribution to journalArticle

172 Citations (Scopus)

Abstract

Predictive vegetation modeling (PVM), is defined as predicting the distribution of vegetation across a landscape based on the relationship between the spatial distribution of vegetation and environmental variables. PVM requires digital maps of the environmental variables, as well as spatial information on the vegetation attribute of interest (e.g., species, type, abundance), usually from a sample of locations. Often these predictive models are developed using traditional statistical methods and are based on the implicit assumption that the distribution of vegetation is random and, therefore, each observation is independent. This approach violates one of the basic tenets of geography, the direct relationship between distance and likeness, as well as of ecological theory, that elements of an ecosystem close to one another are more likely to be influenced by the same generating process and will therefore be similar. Some of the spatial structure can be explained by the predictor variables used in the model. Environmental variables such as precipitation, temperature and elevation exhibit spatial dependence, some of which is responsible for spatial clustering in vegetation distribution, but remaining spatial dependence can result from either unmeasured environmental variables or biotic processes that cause spatial clustering. Spatial dependence in biogeographical data has been recently identified as an important area of future PVM research, and many studies have begun to explore ways to incorporate spatial dependence in predictive models. Here we review the different approaches to incorporating spatial dependence into predictive vegetation models focusing on four statistical methods: autoregressive models, geostatistics, geographically weighted regression, and parameter estimation models. Autoregressive models may be more capable of describing the fine-scaled spatial dependence that results from local biotic factors, such as disturbance, competition, or dispersal, while geostatistical methods may be more suitable for modeling broad-scale spatial dependence. The other methods focus on global and local parameter estimation in the presence of spatially structured or nonstationary data. While this review focuses on incorporating spatial dependence into statistical models for predictive purposes, explicitly including spatial dependence in models can also aid in clarifying the effect of different explanatory variables, thereby improving inferences.

Original languageEnglish (US)
Pages (from-to)225-242
Number of pages18
JournalEcological Modelling
Volume202
Issue number3-4
DOIs
StatePublished - Apr 10 2007
Externally publishedYes

Fingerprint

vegetation
environmental factors
modeling
ecological theory
digital map
statistical analysis
biotic factor
geostatistics
geography
statistical models
spatial distribution
disturbance
method
ecosystem
distribution
ecosystems
temperature
methodology
parameter estimation

Keywords

  • GIS
  • Habitat distribution models
  • Spatial dependence
  • Species distribution models

ASJC Scopus subject areas

  • Ecology, Evolution, Behavior and Systematics
  • Ecological Modeling
  • Ecology

Cite this

Incorporating spatial dependence in predictive vegetation models. / Miller, Jennifer; Franklin, Janet; Aspinall, Richard.

In: Ecological Modelling, Vol. 202, No. 3-4, 10.04.2007, p. 225-242.

Research output: Contribution to journalArticle

Miller, Jennifer ; Franklin, Janet ; Aspinall, Richard. / Incorporating spatial dependence in predictive vegetation models. In: Ecological Modelling. 2007 ; Vol. 202, No. 3-4. pp. 225-242.
@article{7813a77b536b4268833a563f56ba1e08,
title = "Incorporating spatial dependence in predictive vegetation models",
abstract = "Predictive vegetation modeling (PVM), is defined as predicting the distribution of vegetation across a landscape based on the relationship between the spatial distribution of vegetation and environmental variables. PVM requires digital maps of the environmental variables, as well as spatial information on the vegetation attribute of interest (e.g., species, type, abundance), usually from a sample of locations. Often these predictive models are developed using traditional statistical methods and are based on the implicit assumption that the distribution of vegetation is random and, therefore, each observation is independent. This approach violates one of the basic tenets of geography, the direct relationship between distance and likeness, as well as of ecological theory, that elements of an ecosystem close to one another are more likely to be influenced by the same generating process and will therefore be similar. Some of the spatial structure can be explained by the predictor variables used in the model. Environmental variables such as precipitation, temperature and elevation exhibit spatial dependence, some of which is responsible for spatial clustering in vegetation distribution, but remaining spatial dependence can result from either unmeasured environmental variables or biotic processes that cause spatial clustering. Spatial dependence in biogeographical data has been recently identified as an important area of future PVM research, and many studies have begun to explore ways to incorporate spatial dependence in predictive models. Here we review the different approaches to incorporating spatial dependence into predictive vegetation models focusing on four statistical methods: autoregressive models, geostatistics, geographically weighted regression, and parameter estimation models. Autoregressive models may be more capable of describing the fine-scaled spatial dependence that results from local biotic factors, such as disturbance, competition, or dispersal, while geostatistical methods may be more suitable for modeling broad-scale spatial dependence. The other methods focus on global and local parameter estimation in the presence of spatially structured or nonstationary data. While this review focuses on incorporating spatial dependence into statistical models for predictive purposes, explicitly including spatial dependence in models can also aid in clarifying the effect of different explanatory variables, thereby improving inferences.",
keywords = "GIS, Habitat distribution models, Spatial dependence, Species distribution models",
author = "Jennifer Miller and Janet Franklin and Richard Aspinall",
year = "2007",
month = "4",
day = "10",
doi = "10.1016/j.ecolmodel.2006.12.012",
language = "English (US)",
volume = "202",
pages = "225--242",
journal = "Ecological Modelling",
issn = "0304-3800",
publisher = "Elsevier",
number = "3-4",

}

TY - JOUR

T1 - Incorporating spatial dependence in predictive vegetation models

AU - Miller, Jennifer

AU - Franklin, Janet

AU - Aspinall, Richard

PY - 2007/4/10

Y1 - 2007/4/10

N2 - Predictive vegetation modeling (PVM), is defined as predicting the distribution of vegetation across a landscape based on the relationship between the spatial distribution of vegetation and environmental variables. PVM requires digital maps of the environmental variables, as well as spatial information on the vegetation attribute of interest (e.g., species, type, abundance), usually from a sample of locations. Often these predictive models are developed using traditional statistical methods and are based on the implicit assumption that the distribution of vegetation is random and, therefore, each observation is independent. This approach violates one of the basic tenets of geography, the direct relationship between distance and likeness, as well as of ecological theory, that elements of an ecosystem close to one another are more likely to be influenced by the same generating process and will therefore be similar. Some of the spatial structure can be explained by the predictor variables used in the model. Environmental variables such as precipitation, temperature and elevation exhibit spatial dependence, some of which is responsible for spatial clustering in vegetation distribution, but remaining spatial dependence can result from either unmeasured environmental variables or biotic processes that cause spatial clustering. Spatial dependence in biogeographical data has been recently identified as an important area of future PVM research, and many studies have begun to explore ways to incorporate spatial dependence in predictive models. Here we review the different approaches to incorporating spatial dependence into predictive vegetation models focusing on four statistical methods: autoregressive models, geostatistics, geographically weighted regression, and parameter estimation models. Autoregressive models may be more capable of describing the fine-scaled spatial dependence that results from local biotic factors, such as disturbance, competition, or dispersal, while geostatistical methods may be more suitable for modeling broad-scale spatial dependence. The other methods focus on global and local parameter estimation in the presence of spatially structured or nonstationary data. While this review focuses on incorporating spatial dependence into statistical models for predictive purposes, explicitly including spatial dependence in models can also aid in clarifying the effect of different explanatory variables, thereby improving inferences.

AB - Predictive vegetation modeling (PVM), is defined as predicting the distribution of vegetation across a landscape based on the relationship between the spatial distribution of vegetation and environmental variables. PVM requires digital maps of the environmental variables, as well as spatial information on the vegetation attribute of interest (e.g., species, type, abundance), usually from a sample of locations. Often these predictive models are developed using traditional statistical methods and are based on the implicit assumption that the distribution of vegetation is random and, therefore, each observation is independent. This approach violates one of the basic tenets of geography, the direct relationship between distance and likeness, as well as of ecological theory, that elements of an ecosystem close to one another are more likely to be influenced by the same generating process and will therefore be similar. Some of the spatial structure can be explained by the predictor variables used in the model. Environmental variables such as precipitation, temperature and elevation exhibit spatial dependence, some of which is responsible for spatial clustering in vegetation distribution, but remaining spatial dependence can result from either unmeasured environmental variables or biotic processes that cause spatial clustering. Spatial dependence in biogeographical data has been recently identified as an important area of future PVM research, and many studies have begun to explore ways to incorporate spatial dependence in predictive models. Here we review the different approaches to incorporating spatial dependence into predictive vegetation models focusing on four statistical methods: autoregressive models, geostatistics, geographically weighted regression, and parameter estimation models. Autoregressive models may be more capable of describing the fine-scaled spatial dependence that results from local biotic factors, such as disturbance, competition, or dispersal, while geostatistical methods may be more suitable for modeling broad-scale spatial dependence. The other methods focus on global and local parameter estimation in the presence of spatially structured or nonstationary data. While this review focuses on incorporating spatial dependence into statistical models for predictive purposes, explicitly including spatial dependence in models can also aid in clarifying the effect of different explanatory variables, thereby improving inferences.

KW - GIS

KW - Habitat distribution models

KW - Spatial dependence

KW - Species distribution models

UR - http://www.scopus.com/inward/record.url?scp=33847632066&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847632066&partnerID=8YFLogxK

U2 - 10.1016/j.ecolmodel.2006.12.012

DO - 10.1016/j.ecolmodel.2006.12.012

M3 - Article

VL - 202

SP - 225

EP - 242

JO - Ecological Modelling

JF - Ecological Modelling

SN - 0304-3800

IS - 3-4

ER -