Rubén G. Mateo, Jennifer Morales‐Barbero, Alejandra Zarzo‐Arias, Herlander Lima, Virgilio Gómez‐Rubio, Teresa Goicolea
{"title":"sabinaNSDM:用于空间嵌套分层物种分布建模的 R 软件包","authors":"Rubén G. Mateo, Jennifer Morales‐Barbero, Alejandra Zarzo‐Arias, Herlander Lima, Virgilio Gómez‐Rubio, Teresa Goicolea","doi":"10.1111/2041-210x.14417","DOIUrl":null,"url":null,"abstract":"<jats:list> <jats:list-item>Species distribution models have evolved to combine species‐environment interactions across multiple scales. Spatially nested hierarchical models (NSDMs) offer a promising avenue by integrating datasets and predictive models from broad to fine scales. But a user‐friendly tool to execute these models remains an important ongoing challenge.</jats:list-item> <jats:list-item>To address this gap, we introduce the <jats:italic>sabinaNSDM</jats:italic> R package that provides a straightforward approach to develop NSDMs. This package merges global scale models, capturing extensive ecological niches, with regional scale models featuring high‐resolution covariates, to form a unified hierarchical modelling framework. This toolkit is designed to facilitate the implementation of NSDMs for ecologists, conservationists and researchers aiming to produce more reliable species distribution predictions.</jats:list-item> <jats:list-item><jats:italic>sabinaNSDM</jats:italic> streamlines the data preparation, calibration, integration and projection of models across two scales. It automates (if necessary) the generation of background points, spatial thinning of species occurrence and absence (if available) data, covariate selection and the generation of NSDMs.</jats:list-item> <jats:list-item>This paper outlines the workflow and functions integrated into the <jats:italic>sabinaNSDM</jats:italic> package, complemented by an applied case study involving a pool of 76 tree species. Consistent with previous publications, the generated NSDMs facilitated precise predictions (mean AUC value through independent evaluation higher than 0.88) of species distributions under current and future environmental scenarios.</jats:list-item> </jats:list>","PeriodicalId":208,"journal":{"name":"Methods in Ecology and Evolution","volume":null,"pages":null},"PeriodicalIF":6.3000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"sabinaNSDM: An R package for spatially nested hierarchical species distribution modelling\",\"authors\":\"Rubén G. Mateo, Jennifer Morales‐Barbero, Alejandra Zarzo‐Arias, Herlander Lima, Virgilio Gómez‐Rubio, Teresa Goicolea\",\"doi\":\"10.1111/2041-210x.14417\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<jats:list> <jats:list-item>Species distribution models have evolved to combine species‐environment interactions across multiple scales. Spatially nested hierarchical models (NSDMs) offer a promising avenue by integrating datasets and predictive models from broad to fine scales. But a user‐friendly tool to execute these models remains an important ongoing challenge.</jats:list-item> <jats:list-item>To address this gap, we introduce the <jats:italic>sabinaNSDM</jats:italic> R package that provides a straightforward approach to develop NSDMs. This package merges global scale models, capturing extensive ecological niches, with regional scale models featuring high‐resolution covariates, to form a unified hierarchical modelling framework. This toolkit is designed to facilitate the implementation of NSDMs for ecologists, conservationists and researchers aiming to produce more reliable species distribution predictions.</jats:list-item> <jats:list-item><jats:italic>sabinaNSDM</jats:italic> streamlines the data preparation, calibration, integration and projection of models across two scales. It automates (if necessary) the generation of background points, spatial thinning of species occurrence and absence (if available) data, covariate selection and the generation of NSDMs.</jats:list-item> <jats:list-item>This paper outlines the workflow and functions integrated into the <jats:italic>sabinaNSDM</jats:italic> package, complemented by an applied case study involving a pool of 76 tree species. Consistent with previous publications, the generated NSDMs facilitated precise predictions (mean AUC value through independent evaluation higher than 0.88) of species distributions under current and future environmental scenarios.</jats:list-item> </jats:list>\",\"PeriodicalId\":208,\"journal\":{\"name\":\"Methods in Ecology and Evolution\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.3000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Methods in Ecology and Evolution\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://doi.org/10.1111/2041-210x.14417\",\"RegionNum\":2,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Methods in Ecology and Evolution","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1111/2041-210x.14417","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECOLOGY","Score":null,"Total":0}
sabinaNSDM: An R package for spatially nested hierarchical species distribution modelling
Species distribution models have evolved to combine species‐environment interactions across multiple scales. Spatially nested hierarchical models (NSDMs) offer a promising avenue by integrating datasets and predictive models from broad to fine scales. But a user‐friendly tool to execute these models remains an important ongoing challenge.To address this gap, we introduce the sabinaNSDM R package that provides a straightforward approach to develop NSDMs. This package merges global scale models, capturing extensive ecological niches, with regional scale models featuring high‐resolution covariates, to form a unified hierarchical modelling framework. This toolkit is designed to facilitate the implementation of NSDMs for ecologists, conservationists and researchers aiming to produce more reliable species distribution predictions.sabinaNSDM streamlines the data preparation, calibration, integration and projection of models across two scales. It automates (if necessary) the generation of background points, spatial thinning of species occurrence and absence (if available) data, covariate selection and the generation of NSDMs.This paper outlines the workflow and functions integrated into the sabinaNSDM package, complemented by an applied case study involving a pool of 76 tree species. Consistent with previous publications, the generated NSDMs facilitated precise predictions (mean AUC value through independent evaluation higher than 0.88) of species distributions under current and future environmental scenarios.
期刊介绍:
A British Ecological Society journal, Methods in Ecology and Evolution (MEE) promotes the development of new methods in ecology and evolution, and facilitates their dissemination and uptake by the research community. MEE brings together papers from previously disparate sub-disciplines to provide a single forum for tracking methodological developments in all areas.
MEE publishes methodological papers in any area of ecology and evolution, including:
-Phylogenetic analysis
-Statistical methods
-Conservation & management
-Theoretical methods
-Practical methods, including lab and field
-This list is not exhaustive, and we welcome enquiries about possible submissions. Methods are defined in the widest terms and may be analytical, practical or conceptual.
A primary aim of the journal is to maximise the uptake of techniques by the community. We recognise that a major stumbling block in the uptake and application of new methods is the accessibility of methods. For example, users may need computer code, example applications or demonstrations of methods.