Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models
Modeling species distributions over space and time is one of the major research topics in both ecology and conservation biology. Joint Species Distribution models (JSDMs) have recently been introduced as a tool to better model community data, by inferring a residual covariance matrix between species...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-03-01
|
| Series: | Frontiers in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fevo.2021.601384/full |
| _version_ | 1819203810061451264 |
|---|---|
| author | Daria Bystrova Daria Bystrova Giovanni Poggiato Giovanni Poggiato Billur Bektaş Julyan Arbel James S. Clark James S. Clark James S. Clark Alessandra Guglielmi Wilfried Thuiller |
| author_facet | Daria Bystrova Daria Bystrova Giovanni Poggiato Giovanni Poggiato Billur Bektaş Julyan Arbel James S. Clark James S. Clark James S. Clark Alessandra Guglielmi Wilfried Thuiller |
| author_sort | Daria Bystrova |
| collection | DOAJ |
| description | Modeling species distributions over space and time is one of the major research topics in both ecology and conservation biology. Joint Species Distribution models (JSDMs) have recently been introduced as a tool to better model community data, by inferring a residual covariance matrix between species, after accounting for species' response to the environment. However, these models are computationally demanding, even when latent factors, a common tool for dimension reduction, are used. To address this issue, Taylor-Rodriguez et al. (2017) proposed to use a Dirichlet process, a Bayesian nonparametric prior, to further reduce model dimension by clustering species in the residual covariance matrix. Here, we built on this approach to include a prior knowledge on the potential number of clusters, and instead used a Pitman–Yor process to address some critical limitations of the Dirichlet process. We therefore propose a framework that includes prior knowledge in the residual covariance matrix, providing a tool to analyze clusters of species that share the same residual associations with respect to other species. We applied our methodology to a case study of plant communities in a protected area of the French Alps (the Bauges Regional Park), and demonstrated that our extensions improve dimension reduction and reveal additional information from the residual covariance matrix, notably showing how the estimated clusters are compatible with plant traits, endorsing their importance in shaping communities. |
| first_indexed | 2024-12-23T04:25:49Z |
| format | Article |
| id | doaj.art-f9a95abc40ba44e4803e96e7a9e8ab08 |
| institution | Directory Open Access Journal |
| issn | 2296-701X |
| language | English |
| last_indexed | 2024-12-23T04:25:49Z |
| publishDate | 2021-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Ecology and Evolution |
| spelling | doaj.art-f9a95abc40ba44e4803e96e7a9e8ab082022-12-21T18:00:08ZengFrontiers Media S.A.Frontiers in Ecology and Evolution2296-701X2021-03-01910.3389/fevo.2021.601384601384Clustering Species With Residual Covariance Matrix in Joint Species Distribution ModelsDaria Bystrova0Daria Bystrova1Giovanni Poggiato2Giovanni Poggiato3Billur Bektaş4Julyan Arbel5James S. Clark6James S. Clark7James S. Clark8Alessandra Guglielmi9Wilfried Thuiller10University of Grenoble Alpes, University of Savoie Mont Blanc, CNRS, LECA, Grenoble, FranceUniv. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, FranceUniversity of Grenoble Alpes, University of Savoie Mont Blanc, CNRS, LECA, Grenoble, FranceUniv. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, FranceUniversity of Grenoble Alpes, University of Savoie Mont Blanc, CNRS, LECA, Grenoble, FranceUniv. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, FranceUniversity of Grenoble Alpes, INRAE, LESSEM, Grenoble, FranceNicholas School of the Environment, Duke University, Durham, NC, United StatesDepartment of Statistical Science, Duke University, Durham, NC, United StatesDipartimento di Matematica, Politecnico di Milano, Milan, ItalyUniversity of Grenoble Alpes, University of Savoie Mont Blanc, CNRS, LECA, Grenoble, FranceModeling species distributions over space and time is one of the major research topics in both ecology and conservation biology. Joint Species Distribution models (JSDMs) have recently been introduced as a tool to better model community data, by inferring a residual covariance matrix between species, after accounting for species' response to the environment. However, these models are computationally demanding, even when latent factors, a common tool for dimension reduction, are used. To address this issue, Taylor-Rodriguez et al. (2017) proposed to use a Dirichlet process, a Bayesian nonparametric prior, to further reduce model dimension by clustering species in the residual covariance matrix. Here, we built on this approach to include a prior knowledge on the potential number of clusters, and instead used a Pitman–Yor process to address some critical limitations of the Dirichlet process. We therefore propose a framework that includes prior knowledge in the residual covariance matrix, providing a tool to analyze clusters of species that share the same residual associations with respect to other species. We applied our methodology to a case study of plant communities in a protected area of the French Alps (the Bauges Regional Park), and demonstrated that our extensions improve dimension reduction and reveal additional information from the residual covariance matrix, notably showing how the estimated clusters are compatible with plant traits, endorsing their importance in shaping communities.https://www.frontiersin.org/articles/10.3389/fevo.2021.601384/fullBiodiversity modelingdimension reductionjoint species distribution modellatent factorsBayesian nonparametricsplant communities |
| spellingShingle | Daria Bystrova Daria Bystrova Giovanni Poggiato Giovanni Poggiato Billur Bektaş Julyan Arbel James S. Clark James S. Clark James S. Clark Alessandra Guglielmi Wilfried Thuiller Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models Frontiers in Ecology and Evolution Biodiversity modeling dimension reduction joint species distribution model latent factors Bayesian nonparametrics plant communities |
| title | Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models |
| title_full | Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models |
| title_fullStr | Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models |
| title_full_unstemmed | Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models |
| title_short | Clustering Species With Residual Covariance Matrix in Joint Species Distribution Models |
| title_sort | clustering species with residual covariance matrix in joint species distribution models |
| topic | Biodiversity modeling dimension reduction joint species distribution model latent factors Bayesian nonparametrics plant communities |
| url | https://www.frontiersin.org/articles/10.3389/fevo.2021.601384/full |
| work_keys_str_mv | AT dariabystrova clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT dariabystrova clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT giovannipoggiato clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT giovannipoggiato clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT billurbektas clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT julyanarbel clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT jamessclark clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT jamessclark clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT jamessclark clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT alessandraguglielmi clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels AT wilfriedthuiller clusteringspecieswithresidualcovariancematrixinjointspeciesdistributionmodels |