Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

An evaluation of methods for modelling species distributions

An evaluation of methods for modelling species distributions Aim Various statistical techniques have been used to model species probabilities of occurrence in response to environmental conditions. This paper provides a comprehensive assessment of methods and investigates whether errors in model predictions are associated to specific kinds of geographical and environmental distributions of species. Location Portugal, Western Europe. Methods Probabilities of occurrence for 44 species of amphibians and reptiles in Portugal were modelled using seven modelling techniques: Gower metric, Ecological Niche Factor Analysis, classification trees, neural networks, generalized linear models, generalized additive models and spatial interpolators. Generalized linear and additive models were constructed with and without a term accounting for spatial autocorrelation. Model performance was measured using two methods: sensitivity and Kappa index. Species were grouped according to their spatial (area of occupancy and extent of occurrence) and environmental (marginality and tolerance) distributions. Two‐way comparison tests were performed to detect significant interactions between models and species groups. Results Interaction between model and species groups was significant for both sensitivity and Kappa index. This indicates that model performance varied for species with different geographical and environmental distributions. Artificial neural networks performed generally better, immediately followed by generalized additive models including a covariate term for spatial autocorrelation. Non‐parametric methods were preferred to parametric approaches, especially when modelling distributions of species with a greater area of occupancy, a larger extent of occurrence, lower marginality and higher tolerance. Main conclusions This is a first attempt to relate performance of modelling techniques with species spatial and environmental distributions. Results indicate a strong relationship between model performance and the kinds of species distributions being modelled. Some methods performed generally better, but no method was superior in all circumstances. A suggestion is made that choice of the appropriate method should be contingent on the goals and kinds of distributions being modelled. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Biogeography Wiley

An evaluation of methods for modelling species distributions

Segurado, Pedro; Araújo, Miguel B.
Journal of Biogeography , Volume 31 (10) – Oct 1, 2004
Download PDF
14 pages
Read Article

Loading next page...
 
/lp/wiley/an-evaluation-of-methods-for-modelling-species-distributions-ki5gVzIk3e
Publisher
Wiley
Copyright
Copyright © 2004 Wiley Subscription Services, Inc., A Wiley Company
ISSN
0305-0270
eISSN
1365-2699
DOI
10.1111/j.1365-2699.2004.01076.x
Publisher site
See Article on Publisher Site

Abstract

Aim Various statistical techniques have been used to model species probabilities of occurrence in response to environmental conditions. This paper provides a comprehensive assessment of methods and investigates whether errors in model predictions are associated to specific kinds of geographical and environmental distributions of species. Location Portugal, Western Europe. Methods Probabilities of occurrence for 44 species of amphibians and reptiles in Portugal were modelled using seven modelling techniques: Gower metric, Ecological Niche Factor Analysis, classification trees, neural networks, generalized linear models, generalized additive models and spatial interpolators. Generalized linear and additive models were constructed with and without a term accounting for spatial autocorrelation. Model performance was measured using two methods: sensitivity and Kappa index. Species were grouped according to their spatial (area of occupancy and extent of occurrence) and environmental (marginality and tolerance) distributions. Two‐way comparison tests were performed to detect significant interactions between models and species groups. Results Interaction between model and species groups was significant for both sensitivity and Kappa index. This indicates that model performance varied for species with different geographical and environmental distributions. Artificial neural networks performed generally better, immediately followed by generalized additive models including a covariate term for spatial autocorrelation. Non‐parametric methods were preferred to parametric approaches, especially when modelling distributions of species with a greater area of occupancy, a larger extent of occurrence, lower marginality and higher tolerance. Main conclusions This is a first attempt to relate performance of modelling techniques with species spatial and environmental distributions. Results indicate a strong relationship between model performance and the kinds of species distributions being modelled. Some methods performed generally better, but no method was superior in all circumstances. A suggestion is made that choice of the appropriate method should be contingent on the goals and kinds of distributions being modelled.

Journal

Journal of Biogeography – Wiley

Published: Oct 1, 2004

References

  • Selecting areas for species persistence using occurrence data
    Araújo, Araújo; Williams, Williams
  • The bias of complementarity hotspots toward marginal populations
    Araújo, Araújo; Williams, Williams
  • Dynamics of extinction and the selection of nature reserves
    Araújo, Araújo; Williams, Williams; Fuller, Fuller
  • Downscaling European species atlas distributions to a finer resolution: implications for conservation planning
    Araújo, Araújo; Thuiller, Thuiller; Williams, Williams; Reginster, Reginster
  • An autologistic model for spatial distribution of wildlife
    Augustin, Augustin; Mugglestone, Mugglestone; Buckland, Buckland
  • Predicting the spatial distribution of buzzard Buteo buteo nesting areas using a Geographical Information System and remote sensing
    Austin, Austin; Thomas, Thomas; Houston, Houston; Thompson, Thompson
  • Building better wildlife‐habitat models
    Beutel, Beutel; Beeton, Beeton; Baxter, Baxter
  • Determining alternative models for vegetation response analysis – a non‐parametric approach
    Bio, Bio; Alkemande, Alkemande; Barendregt, Barendregt
  • DOMAIN: a flexible modelling procedure for mapping potential distributions of plants and animals
    Carpenter, Carpenter; Gillison, Gillison; Winter, Winter
  • Using mathematical programming to address the multiple reserve selection problem: an example from Eyre Peninsula, South Australia
    Cocks, Cocks; Baird, Baird
  • Using between‐model comparisons to fine‐tune linear models of species ranges
    Cumming, Cumming
  • Classification and regression trees: a powerful yet simple technique for ecological data analysis
    De'Ath, De'Ath; Fabricius, Fabricius
  • Spatial patterns of range contraction in British breeding birds
    Donald, Donald; Greenwood, Greenwood
  • Prediction of bird community composition based on point‐occurrence data and inferential algorithms: a valuable tool in biodiversity assessments
    Feria, Feria; Peterson, Peterson
  • A review of methods for the assessment of prediction errors in conservation presence/absence models
    Fielding, Fielding; Bell, Bell
  • Testing the generality of bird‐habitat models
    Fielding, Fielding; Haworth, Haworth
  • Predicting the distribution of shrub species in southern California from climate and terrain‐derived variables
    Franklin, Franklin
  • Species‐range‐size distributions: patterns, mechanisms and applications
    Gaston, Gaston
  • Local extinction of British farmland birds and the prediction of further loss
    Gates, Gates; Donald, Donald
  • Atlas of the continental Portuguese herpetofauna: an assemblage of published and new data
    Godinho, Godinho; Teixeira, Teixeira; Rebelo, Rebelo; Segurado, Segurado; Loureiro, Loureiro; Alvares, Alvares; Gomes, Gomes; Cardoso, Cardoso; Camilo‐Alves, Camilo‐Alves; Brito, Brito
  • Predictive habitat distribution models in ecology
    Guisan, Guisan; Zimmermann, Zimmermann
  • Spatial autocorrelation: trouble or new paradigm
    Legendre, Legendre
  • Application of neural networks to modelling nonlinear relationships in ecology
    Lek, Lek; Delacoste, Delacoste; Baran, Baran; Dimopoulos, Dimopoulos; Lauga, Lauga; Aulagnier, Aulagnier
  • On the relative abundance of bird species
    MacArthur, MacArthur
  • Towards a hierarchical framework for modelling the spatial distribution of animals
    Mackey, Mackey; Lindenmayer, Lindenmayer
  • Alternative methods for predicting species distribution: an illustration with Himalayan river birds
    Manel, Manel; Dias, Dias; Buckton, Buckton; Ormerod, Ormerod
  • Evaluating presence‐absence models in ecology: the need to account for prevalence
    Manel, Manel; Williams, Williams; Ormerod, Ormerod
  • The use of artificial neural networks to predict the presence of small‐bodied fish in a river
    Mastrorillo, Mastrorillo; Lek, Lek; Dauba, Dauba; Belaud, Belaud
  • Comparing global vegetation maps with the Kappa statistic
    Monserud, Monserud; Leemans, Leemans
  • Illuminating the ‘‘black box’’: Understanding variable contributions in artificial neural networks
    Olden, Olden; Jackson, Jackson
  • An artificial neural network approach to spatial habitat modelling with interspecific interaction
    Özesmi, Özesmi; Özesmi, Özesmi
  • An evaluation of alternative algorithms for fitting species distribution models using logistic regression
    Pearce, Pearce; Ferrier, Ferrier
  • An evaluation of the predictive performance distributional models for flora and fauna in north‐east New South Wales
    Pearce, Pearce; Ferrier, Ferrier; Scotts, Scotts
  • Species: a spatial evaluation of climate impact on the envelope of species
    Pearson, Pearson; Dawson, Dawson; Berry, Berry; Harrison, Harrison
  • GIS‐based habitat modeling using logistic multiple regression: a study of the Mt. Graham Red Squirrel
    Pereira, Pereira; Itami, Itami
  • The value of information in reserve site selection
    Polasky, Polasky; Solow, Solow
  • Autocorrelation in logistic regression modelling of species distributions
    Smith, Smith
  • The GARP modelling system: problems and solutions to automated spatial prediction
    Stockwell, Stockwell; Peters, Peters
  • BIOMOD – Optimising predictions of species distributions and projecting potential future shifts under global change
    Thuiller, Thuiller
  • Generalised models versus classification tree analysis: a comparative study for predicting spatial distributions of plant species at different spatial scales
    Thuiller, Thuiller; Araújo, Araújo; Lavorel, Lavorel
  • Classification trees: an alternative non‐parametric approach for predicting species distributions
    Vayssières, Vayssières; Plant, Plant; Allen‐Diaz, Allen‐Diaz
  • Comparing species temperature response curves: population density versus second‐hand data
    Vetaas, Vetaas
  • Modelling wildlife distribution using a geographic information system: kangaroos in relation to climate
    Walker, Walker
  • Using probability of persistence to identify important areas for biodiversity conservation
    Williams, Williams; Araújo, Araújo
  • Apples, oranges, and probabilities: integrating multiple factors into biodiversity conservation with consistency
    Williams, Williams; Araújo, Araújo

You’re reading a free preview. Subscribe to read the entire article.

Try 2 weeks free now

DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

or browse the journals available

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$499/year

Save searches from
Google Scholar,
PubMed

Create folders to
organize your research

Export folders, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

Sign up
for free
Start 14 day
Free Trial