The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests
Abstract Understanding and predicting the effect of global change phenomena on biodiversity is challenging given that biodiversity data are highly multivariate, containing information from tens to hundreds of species in any given location and time. The Latent Dirichlet Allocation (LDA) model has bee...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-06-01
|
| Series: | Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ece3.7626 |
| _version_ | 1819045226364272640 |
|---|---|
| author | Denis Valle Gilson Shimizu Rafael Izbicki Leandro Maracahipes Divino Vicente Silverio Lucas N. Paolucci Yusuf Jameel Paulo Brando |
| author_facet | Denis Valle Gilson Shimizu Rafael Izbicki Leandro Maracahipes Divino Vicente Silverio Lucas N. Paolucci Yusuf Jameel Paulo Brando |
| author_sort | Denis Valle |
| collection | DOAJ |
| description | Abstract Understanding and predicting the effect of global change phenomena on biodiversity is challenging given that biodiversity data are highly multivariate, containing information from tens to hundreds of species in any given location and time. The Latent Dirichlet Allocation (LDA) model has been recently proposed to decompose biodiversity data into latent communities. While LDA is a very useful exploratory tool and overcomes several limitations of earlier methods, it has limited inferential and predictive skill given that covariates cannot be included in the model. We introduce a modified LDA model (called LDAcov) which allows the incorporation of covariates, enabling inference on the drivers of change of latent communities, spatial interpolation of results, and prediction based on future environmental change scenarios. We show with simulated data that our approach to fitting LDAcov is able to estimate well the number of groups and all model parameters. We illustrate LDAcov using data from two experimental studies on the long‐term effects of fire on southeastern Amazonian forests in Brazil. Our results reveal that repeated fires can have a strong impact on plant assemblages, particularly if fuel is allowed to build up between consecutive fires. The effect of fire is exacerbated as distance to the edge of the forest decreases, with small‐sized species and species with thin bark being impacted the most. These results highlight the compounding impacts of multiple fire events and fragmentation, a scenario commonly found across the southern edge of Amazon. We believe that LDAcov will be of wide interest to scientists studying the effect of global change phenomena on biodiversity using high‐dimensional datasets. Thus, we developed the R package LDAcov to enable the straightforward use of this model. |
| first_indexed | 2024-12-21T10:25:12Z |
| format | Article |
| id | doaj.art-c45b9e5f1996458f96d0930c57534dca |
| institution | Directory Open Access Journal |
| issn | 2045-7758 |
| language | English |
| last_indexed | 2024-12-21T10:25:12Z |
| publishDate | 2021-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Ecology and Evolution |
| spelling | doaj.art-c45b9e5f1996458f96d0930c57534dca2022-12-21T19:07:20ZengWileyEcology and Evolution2045-77582021-06-0111127970797910.1002/ece3.7626The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forestsDenis Valle0Gilson Shimizu1Rafael Izbicki2Leandro Maracahipes3Divino Vicente Silverio4Lucas N. Paolucci5Yusuf Jameel6Paulo Brando7School of Forest, Fisheries, and Geomatics Sciences University of Florida Gainesville Florida USADepartment of Statistics Federal University of Sao Carlos Sao Paulo BrazilDepartment of Statistics Federal University of Sao Carlos Sao Paulo BrazilInstituto de Pesquisa Ambiental da Amazonia Brasilia BrazilDepartamento de Biologia Universidade Federal Rural da Amazônia Capitão Poço BrazilDepartamento de Biologia Geral Universidade Federal de Viçosa Viçosa BrazilSchool of Forest, Fisheries, and Geomatics Sciences University of Florida Gainesville Florida USADepartment of Earth System Science University of California, Irvine Irvine California USAAbstract Understanding and predicting the effect of global change phenomena on biodiversity is challenging given that biodiversity data are highly multivariate, containing information from tens to hundreds of species in any given location and time. The Latent Dirichlet Allocation (LDA) model has been recently proposed to decompose biodiversity data into latent communities. While LDA is a very useful exploratory tool and overcomes several limitations of earlier methods, it has limited inferential and predictive skill given that covariates cannot be included in the model. We introduce a modified LDA model (called LDAcov) which allows the incorporation of covariates, enabling inference on the drivers of change of latent communities, spatial interpolation of results, and prediction based on future environmental change scenarios. We show with simulated data that our approach to fitting LDAcov is able to estimate well the number of groups and all model parameters. We illustrate LDAcov using data from two experimental studies on the long‐term effects of fire on southeastern Amazonian forests in Brazil. Our results reveal that repeated fires can have a strong impact on plant assemblages, particularly if fuel is allowed to build up between consecutive fires. The effect of fire is exacerbated as distance to the edge of the forest decreases, with small‐sized species and species with thin bark being impacted the most. These results highlight the compounding impacts of multiple fire events and fragmentation, a scenario commonly found across the southern edge of Amazon. We believe that LDAcov will be of wide interest to scientists studying the effect of global change phenomena on biodiversity using high‐dimensional datasets. Thus, we developed the R package LDAcov to enable the straightforward use of this model.https://doi.org/10.1002/ece3.7626Amazonbiodiversitycommunity ecologyforest fireforest fragmentationmixed‐membership model |
| spellingShingle | Denis Valle Gilson Shimizu Rafael Izbicki Leandro Maracahipes Divino Vicente Silverio Lucas N. Paolucci Yusuf Jameel Paulo Brando The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests Ecology and Evolution Amazon biodiversity community ecology forest fire forest fragmentation mixed‐membership model |
| title | The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests |
| title_full | The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests |
| title_fullStr | The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests |
| title_full_unstemmed | The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests |
| title_short | The Latent Dirichlet Allocation model with covariates (LDAcov): A case study on the effect of fire on species composition in Amazonian forests |
| title_sort | latent dirichlet allocation model with covariates ldacov a case study on the effect of fire on species composition in amazonian forests |
| topic | Amazon biodiversity community ecology forest fire forest fragmentation mixed‐membership model |
| url | https://doi.org/10.1002/ece3.7626 |
| work_keys_str_mv | AT denisvalle thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT gilsonshimizu thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT rafaelizbicki thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT leandromaracahipes thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT divinovicentesilverio thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT lucasnpaolucci thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT yusufjameel thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT paulobrando thelatentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT denisvalle latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT gilsonshimizu latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT rafaelizbicki latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT leandromaracahipes latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT divinovicentesilverio latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT lucasnpaolucci latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT yusufjameel latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests AT paulobrando latentdirichletallocationmodelwithcovariatesldacovacasestudyontheeffectoffireonspeciescompositioninamazonianforests |