Mapping species abundance by a spatial zero-inflated Poisson model: A case study in the Wadden Sea, the Netherlands

Olga Lyashevska, D.J. Brus, Jaap van der Meer

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)

Abstract

The objective of the study was to provide a general procedure for mapping species abundance when data are zero-inflated and spatially correlated counts. The bivalve species Macoma balthica was observed on a 500×500 m grid in the Dutch part of the Wadden Sea. In total, 66% of the 3451 counts were zeros. A zero-inflated Poisson mixture model was used to relate counts to environmental covariates. Two models were considered, one with relatively fewer covariates (model "small") than the other (model "large"). The models contained two processes: a Bernoulli (species prevalence) and a Poisson (species intensity, when the Bernoulli process predicts presence). The model was used to make predictions for sites where only environmental data are available. Predicted prevalences and intensities show that the model "small" predicts lower mean prevalence and higher mean intensity, than the model "large". Yet, the product of prevalence and intensity, which might be called the unconditional intensity, is very similar. Cross-validation showed that the model "small" performed slightly better, but the difference was small. The proposed methodology might be generally applicable, but is computer intensive.

LanguageEnglish
Pages532-543
JournalEcology and Evolution
Volume6
Issue number2
DOIs
Publication statusPublished - 2016

Fingerprint

North Sea
Netherlands
case studies
Wadden Sea
model validation
Bivalvia
bivalve
prediction
methodology

Keywords

  • Benthic species
  • Count data
  • Generalized linear spatial modeling
  • Spatial correlation

Cite this

@article{c0b7a0f668934e6a80090e8aaf9c06e1,
title = "Mapping species abundance by a spatial zero-inflated Poisson model: A case study in the Wadden Sea, the Netherlands",
abstract = "The objective of the study was to provide a general procedure for mapping species abundance when data are zero-inflated and spatially correlated counts. The bivalve species Macoma balthica was observed on a 500×500 m grid in the Dutch part of the Wadden Sea. In total, 66{\%} of the 3451 counts were zeros. A zero-inflated Poisson mixture model was used to relate counts to environmental covariates. Two models were considered, one with relatively fewer covariates (model {"}small{"}) than the other (model {"}large{"}). The models contained two processes: a Bernoulli (species prevalence) and a Poisson (species intensity, when the Bernoulli process predicts presence). The model was used to make predictions for sites where only environmental data are available. Predicted prevalences and intensities show that the model {"}small{"} predicts lower mean prevalence and higher mean intensity, than the model {"}large{"}. Yet, the product of prevalence and intensity, which might be called the unconditional intensity, is very similar. Cross-validation showed that the model {"}small{"} performed slightly better, but the difference was small. The proposed methodology might be generally applicable, but is computer intensive.",
keywords = "Benthic species, Count data, Generalized linear spatial modeling, Spatial correlation",
author = "Olga Lyashevska and D.J. Brus and {van der Meer}, Jaap",
year = "2016",
doi = "10.1002/ece3.1880",
language = "English",
volume = "6",
pages = "532--543",
journal = "Ecology and Evolution",
issn = "2045-7758",
publisher = "Wiley",
number = "2",

}

Mapping species abundance by a spatial zero-inflated Poisson model : A case study in the Wadden Sea, the Netherlands. / Lyashevska, Olga; Brus, D.J.; van der Meer, Jaap.

In: Ecology and Evolution, Vol. 6, No. 2, 2016, p. 532-543.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Mapping species abundance by a spatial zero-inflated Poisson model

T2 - Ecology and Evolution

AU - Lyashevska, Olga

AU - Brus, D.J.

AU - van der Meer, Jaap

PY - 2016

Y1 - 2016

N2 - The objective of the study was to provide a general procedure for mapping species abundance when data are zero-inflated and spatially correlated counts. The bivalve species Macoma balthica was observed on a 500×500 m grid in the Dutch part of the Wadden Sea. In total, 66% of the 3451 counts were zeros. A zero-inflated Poisson mixture model was used to relate counts to environmental covariates. Two models were considered, one with relatively fewer covariates (model "small") than the other (model "large"). The models contained two processes: a Bernoulli (species prevalence) and a Poisson (species intensity, when the Bernoulli process predicts presence). The model was used to make predictions for sites where only environmental data are available. Predicted prevalences and intensities show that the model "small" predicts lower mean prevalence and higher mean intensity, than the model "large". Yet, the product of prevalence and intensity, which might be called the unconditional intensity, is very similar. Cross-validation showed that the model "small" performed slightly better, but the difference was small. The proposed methodology might be generally applicable, but is computer intensive.

AB - The objective of the study was to provide a general procedure for mapping species abundance when data are zero-inflated and spatially correlated counts. The bivalve species Macoma balthica was observed on a 500×500 m grid in the Dutch part of the Wadden Sea. In total, 66% of the 3451 counts were zeros. A zero-inflated Poisson mixture model was used to relate counts to environmental covariates. Two models were considered, one with relatively fewer covariates (model "small") than the other (model "large"). The models contained two processes: a Bernoulli (species prevalence) and a Poisson (species intensity, when the Bernoulli process predicts presence). The model was used to make predictions for sites where only environmental data are available. Predicted prevalences and intensities show that the model "small" predicts lower mean prevalence and higher mean intensity, than the model "large". Yet, the product of prevalence and intensity, which might be called the unconditional intensity, is very similar. Cross-validation showed that the model "small" performed slightly better, but the difference was small. The proposed methodology might be generally applicable, but is computer intensive.

KW - Benthic species

KW - Count data

KW - Generalized linear spatial modeling

KW - Spatial correlation

U2 - 10.1002/ece3.1880

DO - 10.1002/ece3.1880

M3 - Article

VL - 6

SP - 532

EP - 543

JO - Ecology and Evolution

JF - Ecology and Evolution

SN - 2045-7758

IS - 2

ER -