Loading…
ntbox: An r package with graphical user interface for modelling and evaluating multidimensional ecological niches
Biodiversity studies rely heavily on estimates of species' distributions often obtained through ecological niche modelling. Numerous software packages exist that allow users to model ecological niches using machine learning and statistical methods. However, no existing package with a graphical...
Saved in:
| Published in: | Methods in ecology and evolution 2020-10, Vol.11 (10), p.1199-1206 |
|---|---|
| Main Authors: | , , , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3 |
| container_end_page | 1206 |
| container_issue | 10 |
| container_start_page | 1199 |
| container_title | Methods in ecology and evolution |
| container_volume | 11 |
| creator | Osorio‐Olvera, Luis Lira‐Noriega, Andrés Soberón, Jorge Peterson, Andrew Townsend Falconi, Manuel Contreras‐Díaz, Rusby G. Martínez‐Meyer, Enrique Barve, Vijay Barve, Narayani Qiao, Huijie |
| description | Biodiversity studies rely heavily on estimates of species' distributions often obtained through ecological niche modelling. Numerous software packages exist that allow users to model ecological niches using machine learning and statistical methods. However, no existing package with a graphical user interface allows users to perform model calibration and selection based on convex forms such as ellipsoids, which may match fundamental ecological niche shapes better, incorporating tools for exploring, modelling, and evaluating niches and distributions that are intuitive for both novice and proficient users.
Here we describe an r package, NicheToolBox (ntbox), that allows users to conduct all processing steps involved in ecological niche modelling: downloading and curating occurrence data, obtaining and transforming environmental data layers, selecting environmental variables, exploring relationships between geographic and environmental spaces, calibrating and selecting ellipsoid models, evaluating models using binomial and partial ROC tests, assessing extrapolation risk, and performing geographic information system operations via a graphical user interface. A summary of the entire workflow is produced for use as a stand‐alone algorithm or as part of research reports.
The method is explained in detail and tested via modelling the threatened feline species Leopardus wiedii. Georeferenced occurrence data for this species are queried to display both point occurrences and the IUCN extent of occurrence polygon (IUCN, 2007). This information is used to illustrate tools available for accessing, processing and exploring biodiversity data (e.g. number of occurrences and chronology of collecting) and transforming environmental data (e.g. a summary PCA for 19 bioclimatic layers). Visualizations of three‐dimensional ecological niches modelled as minimum volume ellipsoids are developed with ancillary statistics. This niche model is then projected to geographic space, to represent a corresponding potential suitability map.
Using ntbox allows a fast and straightforward means by which to retrieve and manipulate occurrence and environmental data, which can then be implemented in model calibration, projection and evaluation for assessing distributions of species in geographic space and their corresponding environmental combinations.
Resumen
Los estudios de biodiversidad dependen en gran medida de las estimaciones de las distribuciones de especies obtenidas a menudo a través de m |
| doi_str_mv | 10.1111/2041-210X.13452 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2447397380</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2447397380</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3</originalsourceid><addsrcrecordid>eNqFkDtPwzAUhS0EEhV0ZrXEnNaPtHHYqqo8pCIWkNgsx71OXZI4tRNK_z1JgxAbd7kPfefo6iB0Q8mEdjVlJKYRo-R9Qnk8Y2do9Hs5_zNfonEIO9IVFylh8QjtqyZzX3d4UWGPa6U_VA74YJstzr2qt1arArcBPLZVA94oDdg4j0u3gaKwVY5VtcHwqYpWNf1atkVjN7aEKlhXdWLQrnD5yaeyegvhGl0YVQQY__Qr9Ha_el0-RuuXh6flYh1pTgWLBAWjGUs1yUyazXhMMpUAZSRjHUBSos1MCJ3wuUgFEEPUPE0ZBxBCEMEVv0K3g2_t3b6F0Mida333UpAsjhOeJlyQjpoOlPYuBA9G1t6Wyh8lJbKPVvbhyT48eYq2U8wHxcEWcPwPl8-rFR-E3-vWe7k</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2447397380</pqid></control><display><type>article</type><title>ntbox: An r package with graphical user interface for modelling and evaluating multidimensional ecological niches</title><source>Wiley-Blackwell Journals</source><creator>Osorio‐Olvera, Luis ; Lira‐Noriega, Andrés ; Soberón, Jorge ; Peterson, Andrew Townsend ; Falconi, Manuel ; Contreras‐Díaz, Rusby G. ; Martínez‐Meyer, Enrique ; Barve, Vijay ; Barve, Narayani ; Qiao, Huijie</creator><contributor>Qiao, Huijie</contributor><creatorcontrib>Osorio‐Olvera, Luis ; Lira‐Noriega, Andrés ; Soberón, Jorge ; Peterson, Andrew Townsend ; Falconi, Manuel ; Contreras‐Díaz, Rusby G. ; Martínez‐Meyer, Enrique ; Barve, Vijay ; Barve, Narayani ; Qiao, Huijie ; Qiao, Huijie</creatorcontrib><description>Biodiversity studies rely heavily on estimates of species' distributions often obtained through ecological niche modelling. Numerous software packages exist that allow users to model ecological niches using machine learning and statistical methods. However, no existing package with a graphical user interface allows users to perform model calibration and selection based on convex forms such as ellipsoids, which may match fundamental ecological niche shapes better, incorporating tools for exploring, modelling, and evaluating niches and distributions that are intuitive for both novice and proficient users.
Here we describe an r package, NicheToolBox (ntbox), that allows users to conduct all processing steps involved in ecological niche modelling: downloading and curating occurrence data, obtaining and transforming environmental data layers, selecting environmental variables, exploring relationships between geographic and environmental spaces, calibrating and selecting ellipsoid models, evaluating models using binomial and partial ROC tests, assessing extrapolation risk, and performing geographic information system operations via a graphical user interface. A summary of the entire workflow is produced for use as a stand‐alone algorithm or as part of research reports.
The method is explained in detail and tested via modelling the threatened feline species Leopardus wiedii. Georeferenced occurrence data for this species are queried to display both point occurrences and the IUCN extent of occurrence polygon (IUCN, 2007). This information is used to illustrate tools available for accessing, processing and exploring biodiversity data (e.g. number of occurrences and chronology of collecting) and transforming environmental data (e.g. a summary PCA for 19 bioclimatic layers). Visualizations of three‐dimensional ecological niches modelled as minimum volume ellipsoids are developed with ancillary statistics. This niche model is then projected to geographic space, to represent a corresponding potential suitability map.
Using ntbox allows a fast and straightforward means by which to retrieve and manipulate occurrence and environmental data, which can then be implemented in model calibration, projection and evaluation for assessing distributions of species in geographic space and their corresponding environmental combinations.
Resumen
Los estudios de biodiversidad dependen en gran medida de las estimaciones de las distribuciones de especies obtenidas a menudo a través de modelos de nicho ecológico. Existen numerosos paquetes de software diseñados para modelar nichos ecológicos y proyectar proyectar áreas de distribución potenciales utilizando técnicas de aprendizaje automático y métodos estadísticos. Sin embargo, ningún paquete cuenta con una interfaz gráfica que permite a los usuarios realizar calibraciones y selección de modelos (i.e. buscar el modelo con el mejor rendimiento) de modelos basadas en formas convexas como los elipsoides, estos pueden coincidir mejor con las formas del nicho ecológico fundamental, incorporando herramientas para explorar, modelar y evaluar nichos y distribuciones que son intuitivas tanto para principiantes como para usuarios expertos.
Aquí describimos un paquete de r, NicheToolBox (ntbox), que permite a los usuarios realizar todos los pasos de procesamiento involucrados en el modelado de nicho ecológico: descargar y curar datos de presencia, obtener y transformar capas de datos ambientales, seleccionar variables ambientales, explorar relaciones entre los espacios geográfico y ecológico, calibrar y seleccionar modelos de elipsoides, evaluar modelos utilizando pruebas ROC binomiales y parciales, evaluar el riesgo de extrapolación y realizar operaciones de sistemas de información geográfica a través de una interfaz gráfica. Además, se puede generar un resumen de todo el flujo de trabajo para su uso como algoritmo independiente o como parte de informes de investigación.
El método se explica en detalle y se prueba mediante el modelado de la especie de felino amenazada Leopardus wiedii. Los datos de presencia georreferenciados para esta especie se muestran de manera puntual y con el polígono de la UICN. Esta información se utiliza para ilustrar las herramientas disponibles para acceder, procesar y explorar datos de biodiversidad (e.g. número de puntos y cronología de recolección) y la transformación de datos ambientales (e.g. un PCA resumido para 19 capas bioclimáticas). También se muestran visualizaciones de nichos ecológicos tridimensionales modelados como elipsoides de volumen mínimo y sus estadísticas. Finalmente, el modelo de nicho se proyecta al espacio geográfico, para representar un mapa de idoneidad potencial correspondiente.
El uso de ntbox permite un medio rápido y directo para recuperar y manipular datos de localidades de presencia y ambientales, que luego se pueden utilizar en la calibración, proyección y evaluación del modelo para estimar las distribuciones de especies en el espacio geográfico y sus correspondientes combinaciones ambientales.</description><identifier>ISSN: 2041-210X</identifier><identifier>EISSN: 2041-210X</identifier><identifier>DOI: 10.1111/2041-210X.13452</identifier><language>eng</language><publisher>London: John Wiley & Sons, Inc</publisher><subject>Algorithms ; Bioclimatology ; Biodiversity ; biodiversity informatics ; Calibration ; Computer programs ; ecological niche modelling ; Ecological niches ; Ellipsoids ; Evaluation ; Geographic information systems ; GIS tools ; Graphical user interface ; Learning algorithms ; Leopardus wiedii ; Machine learning ; minimum volume ellipsoid ; model evaluation ; model selection ; model uncertainty ; Niches ; Remote sensing ; Software ; Software packages ; species distribution ; Statistical methods ; Threatened species ; User interface ; Workflow</subject><ispartof>Methods in ecology and evolution, 2020-10, Vol.11 (10), p.1199-1206</ispartof><rights>2020 British Ecological Society</rights><rights>Methods in Ecology and Evolution © 2020 British Ecological Society</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3</citedby><cites>FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3</cites><orcidid>0000-0002-4296-7258 ; 0000-0003-1184-9264 ; 0000-0002-7893-8774 ; 0000-0002-3219-0019 ; 0000-0003-2160-4148 ; 0000-0002-0569-8984 ; 0000-0003-0701-5398 ; 0000-0002-4852-2567 ; 0000-0003-0243-2379</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1111%2F2041-210X.13452$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1111%2F2041-210X.13452$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>315,786,790,27957,27958,50923,51032</link.rule.ids></links><search><contributor>Qiao, Huijie</contributor><creatorcontrib>Osorio‐Olvera, Luis</creatorcontrib><creatorcontrib>Lira‐Noriega, Andrés</creatorcontrib><creatorcontrib>Soberón, Jorge</creatorcontrib><creatorcontrib>Peterson, Andrew Townsend</creatorcontrib><creatorcontrib>Falconi, Manuel</creatorcontrib><creatorcontrib>Contreras‐Díaz, Rusby G.</creatorcontrib><creatorcontrib>Martínez‐Meyer, Enrique</creatorcontrib><creatorcontrib>Barve, Vijay</creatorcontrib><creatorcontrib>Barve, Narayani</creatorcontrib><creatorcontrib>Qiao, Huijie</creatorcontrib><title>ntbox: An r package with graphical user interface for modelling and evaluating multidimensional ecological niches</title><title>Methods in ecology and evolution</title><description>Biodiversity studies rely heavily on estimates of species' distributions often obtained through ecological niche modelling. Numerous software packages exist that allow users to model ecological niches using machine learning and statistical methods. However, no existing package with a graphical user interface allows users to perform model calibration and selection based on convex forms such as ellipsoids, which may match fundamental ecological niche shapes better, incorporating tools for exploring, modelling, and evaluating niches and distributions that are intuitive for both novice and proficient users.
Here we describe an r package, NicheToolBox (ntbox), that allows users to conduct all processing steps involved in ecological niche modelling: downloading and curating occurrence data, obtaining and transforming environmental data layers, selecting environmental variables, exploring relationships between geographic and environmental spaces, calibrating and selecting ellipsoid models, evaluating models using binomial and partial ROC tests, assessing extrapolation risk, and performing geographic information system operations via a graphical user interface. A summary of the entire workflow is produced for use as a stand‐alone algorithm or as part of research reports.
The method is explained in detail and tested via modelling the threatened feline species Leopardus wiedii. Georeferenced occurrence data for this species are queried to display both point occurrences and the IUCN extent of occurrence polygon (IUCN, 2007). This information is used to illustrate tools available for accessing, processing and exploring biodiversity data (e.g. number of occurrences and chronology of collecting) and transforming environmental data (e.g. a summary PCA for 19 bioclimatic layers). Visualizations of three‐dimensional ecological niches modelled as minimum volume ellipsoids are developed with ancillary statistics. This niche model is then projected to geographic space, to represent a corresponding potential suitability map.
Using ntbox allows a fast and straightforward means by which to retrieve and manipulate occurrence and environmental data, which can then be implemented in model calibration, projection and evaluation for assessing distributions of species in geographic space and their corresponding environmental combinations.
Resumen
Los estudios de biodiversidad dependen en gran medida de las estimaciones de las distribuciones de especies obtenidas a menudo a través de modelos de nicho ecológico. Existen numerosos paquetes de software diseñados para modelar nichos ecológicos y proyectar proyectar áreas de distribución potenciales utilizando técnicas de aprendizaje automático y métodos estadísticos. Sin embargo, ningún paquete cuenta con una interfaz gráfica que permite a los usuarios realizar calibraciones y selección de modelos (i.e. buscar el modelo con el mejor rendimiento) de modelos basadas en formas convexas como los elipsoides, estos pueden coincidir mejor con las formas del nicho ecológico fundamental, incorporando herramientas para explorar, modelar y evaluar nichos y distribuciones que son intuitivas tanto para principiantes como para usuarios expertos.
Aquí describimos un paquete de r, NicheToolBox (ntbox), que permite a los usuarios realizar todos los pasos de procesamiento involucrados en el modelado de nicho ecológico: descargar y curar datos de presencia, obtener y transformar capas de datos ambientales, seleccionar variables ambientales, explorar relaciones entre los espacios geográfico y ecológico, calibrar y seleccionar modelos de elipsoides, evaluar modelos utilizando pruebas ROC binomiales y parciales, evaluar el riesgo de extrapolación y realizar operaciones de sistemas de información geográfica a través de una interfaz gráfica. Además, se puede generar un resumen de todo el flujo de trabajo para su uso como algoritmo independiente o como parte de informes de investigación.
El método se explica en detalle y se prueba mediante el modelado de la especie de felino amenazada Leopardus wiedii. Los datos de presencia georreferenciados para esta especie se muestran de manera puntual y con el polígono de la UICN. Esta información se utiliza para ilustrar las herramientas disponibles para acceder, procesar y explorar datos de biodiversidad (e.g. número de puntos y cronología de recolección) y la transformación de datos ambientales (e.g. un PCA resumido para 19 capas bioclimáticas). También se muestran visualizaciones de nichos ecológicos tridimensionales modelados como elipsoides de volumen mínimo y sus estadísticas. Finalmente, el modelo de nicho se proyecta al espacio geográfico, para representar un mapa de idoneidad potencial correspondiente.
El uso de ntbox permite un medio rápido y directo para recuperar y manipular datos de localidades de presencia y ambientales, que luego se pueden utilizar en la calibración, proyección y evaluación del modelo para estimar las distribuciones de especies en el espacio geográfico y sus correspondientes combinaciones ambientales.</description><subject>Algorithms</subject><subject>Bioclimatology</subject><subject>Biodiversity</subject><subject>biodiversity informatics</subject><subject>Calibration</subject><subject>Computer programs</subject><subject>ecological niche modelling</subject><subject>Ecological niches</subject><subject>Ellipsoids</subject><subject>Evaluation</subject><subject>Geographic information systems</subject><subject>GIS tools</subject><subject>Graphical user interface</subject><subject>Learning algorithms</subject><subject>Leopardus wiedii</subject><subject>Machine learning</subject><subject>minimum volume ellipsoid</subject><subject>model evaluation</subject><subject>model selection</subject><subject>model uncertainty</subject><subject>Niches</subject><subject>Remote sensing</subject><subject>Software</subject><subject>Software packages</subject><subject>species distribution</subject><subject>Statistical methods</subject><subject>Threatened species</subject><subject>User interface</subject><subject>Workflow</subject><issn>2041-210X</issn><issn>2041-210X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNqFkDtPwzAUhS0EEhV0ZrXEnNaPtHHYqqo8pCIWkNgsx71OXZI4tRNK_z1JgxAbd7kPfefo6iB0Q8mEdjVlJKYRo-R9Qnk8Y2do9Hs5_zNfonEIO9IVFylh8QjtqyZzX3d4UWGPa6U_VA74YJstzr2qt1arArcBPLZVA94oDdg4j0u3gaKwVY5VtcHwqYpWNf1atkVjN7aEKlhXdWLQrnD5yaeyegvhGl0YVQQY__Qr9Ha_el0-RuuXh6flYh1pTgWLBAWjGUs1yUyazXhMMpUAZSRjHUBSos1MCJ3wuUgFEEPUPE0ZBxBCEMEVv0K3g2_t3b6F0Mida333UpAsjhOeJlyQjpoOlPYuBA9G1t6Wyh8lJbKPVvbhyT48eYq2U8wHxcEWcPwPl8-rFR-E3-vWe7k</recordid><startdate>202010</startdate><enddate>202010</enddate><creator>Osorio‐Olvera, Luis</creator><creator>Lira‐Noriega, Andrés</creator><creator>Soberón, Jorge</creator><creator>Peterson, Andrew Townsend</creator><creator>Falconi, Manuel</creator><creator>Contreras‐Díaz, Rusby G.</creator><creator>Martínez‐Meyer, Enrique</creator><creator>Barve, Vijay</creator><creator>Barve, Narayani</creator><creator>Qiao, Huijie</creator><general>John Wiley & Sons, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QG</scope><scope>7SN</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>P64</scope><scope>RC3</scope><orcidid>https://orcid.org/0000-0002-4296-7258</orcidid><orcidid>https://orcid.org/0000-0003-1184-9264</orcidid><orcidid>https://orcid.org/0000-0002-7893-8774</orcidid><orcidid>https://orcid.org/0000-0002-3219-0019</orcidid><orcidid>https://orcid.org/0000-0003-2160-4148</orcidid><orcidid>https://orcid.org/0000-0002-0569-8984</orcidid><orcidid>https://orcid.org/0000-0003-0701-5398</orcidid><orcidid>https://orcid.org/0000-0002-4852-2567</orcidid><orcidid>https://orcid.org/0000-0003-0243-2379</orcidid></search><sort><creationdate>202010</creationdate><title>ntbox: An r package with graphical user interface for modelling and evaluating multidimensional ecological niches</title><author>Osorio‐Olvera, Luis ; Lira‐Noriega, Andrés ; Soberón, Jorge ; Peterson, Andrew Townsend ; Falconi, Manuel ; Contreras‐Díaz, Rusby G. ; Martínez‐Meyer, Enrique ; Barve, Vijay ; Barve, Narayani ; Qiao, Huijie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Bioclimatology</topic><topic>Biodiversity</topic><topic>biodiversity informatics</topic><topic>Calibration</topic><topic>Computer programs</topic><topic>ecological niche modelling</topic><topic>Ecological niches</topic><topic>Ellipsoids</topic><topic>Evaluation</topic><topic>Geographic information systems</topic><topic>GIS tools</topic><topic>Graphical user interface</topic><topic>Learning algorithms</topic><topic>Leopardus wiedii</topic><topic>Machine learning</topic><topic>minimum volume ellipsoid</topic><topic>model evaluation</topic><topic>model selection</topic><topic>model uncertainty</topic><topic>Niches</topic><topic>Remote sensing</topic><topic>Software</topic><topic>Software packages</topic><topic>species distribution</topic><topic>Statistical methods</topic><topic>Threatened species</topic><topic>User interface</topic><topic>Workflow</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Osorio‐Olvera, Luis</creatorcontrib><creatorcontrib>Lira‐Noriega, Andrés</creatorcontrib><creatorcontrib>Soberón, Jorge</creatorcontrib><creatorcontrib>Peterson, Andrew Townsend</creatorcontrib><creatorcontrib>Falconi, Manuel</creatorcontrib><creatorcontrib>Contreras‐Díaz, Rusby G.</creatorcontrib><creatorcontrib>Martínez‐Meyer, Enrique</creatorcontrib><creatorcontrib>Barve, Vijay</creatorcontrib><creatorcontrib>Barve, Narayani</creatorcontrib><creatorcontrib>Qiao, Huijie</creatorcontrib><collection>CrossRef</collection><collection>Animal Behavior Abstracts</collection><collection>Ecology Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><jtitle>Methods in ecology and evolution</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Osorio‐Olvera, Luis</au><au>Lira‐Noriega, Andrés</au><au>Soberón, Jorge</au><au>Peterson, Andrew Townsend</au><au>Falconi, Manuel</au><au>Contreras‐Díaz, Rusby G.</au><au>Martínez‐Meyer, Enrique</au><au>Barve, Vijay</au><au>Barve, Narayani</au><au>Qiao, Huijie</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ntbox: An r package with graphical user interface for modelling and evaluating multidimensional ecological niches</atitle><jtitle>Methods in ecology and evolution</jtitle><date>2020-10</date><risdate>2020</risdate><volume>11</volume><issue>10</issue><spage>1199</spage><epage>1206</epage><pages>1199-1206</pages><issn>2041-210X</issn><eissn>2041-210X</eissn><notes>Funding information</notes><notes>This work was partially supported by Consejo Nacional de Ciencia y Tecnología (CONACyT; postdoctoral fellowship number 740751; CVU: 368747 and project FORDECyT 273646), PAPIIT IN116018 and Google Summer of Code 2016 and the NSF grant ABI 1458640.</notes><abstract>Biodiversity studies rely heavily on estimates of species' distributions often obtained through ecological niche modelling. Numerous software packages exist that allow users to model ecological niches using machine learning and statistical methods. However, no existing package with a graphical user interface allows users to perform model calibration and selection based on convex forms such as ellipsoids, which may match fundamental ecological niche shapes better, incorporating tools for exploring, modelling, and evaluating niches and distributions that are intuitive for both novice and proficient users.
Here we describe an r package, NicheToolBox (ntbox), that allows users to conduct all processing steps involved in ecological niche modelling: downloading and curating occurrence data, obtaining and transforming environmental data layers, selecting environmental variables, exploring relationships between geographic and environmental spaces, calibrating and selecting ellipsoid models, evaluating models using binomial and partial ROC tests, assessing extrapolation risk, and performing geographic information system operations via a graphical user interface. A summary of the entire workflow is produced for use as a stand‐alone algorithm or as part of research reports.
The method is explained in detail and tested via modelling the threatened feline species Leopardus wiedii. Georeferenced occurrence data for this species are queried to display both point occurrences and the IUCN extent of occurrence polygon (IUCN, 2007). This information is used to illustrate tools available for accessing, processing and exploring biodiversity data (e.g. number of occurrences and chronology of collecting) and transforming environmental data (e.g. a summary PCA for 19 bioclimatic layers). Visualizations of three‐dimensional ecological niches modelled as minimum volume ellipsoids are developed with ancillary statistics. This niche model is then projected to geographic space, to represent a corresponding potential suitability map.
Using ntbox allows a fast and straightforward means by which to retrieve and manipulate occurrence and environmental data, which can then be implemented in model calibration, projection and evaluation for assessing distributions of species in geographic space and their corresponding environmental combinations.
Resumen
Los estudios de biodiversidad dependen en gran medida de las estimaciones de las distribuciones de especies obtenidas a menudo a través de modelos de nicho ecológico. Existen numerosos paquetes de software diseñados para modelar nichos ecológicos y proyectar proyectar áreas de distribución potenciales utilizando técnicas de aprendizaje automático y métodos estadísticos. Sin embargo, ningún paquete cuenta con una interfaz gráfica que permite a los usuarios realizar calibraciones y selección de modelos (i.e. buscar el modelo con el mejor rendimiento) de modelos basadas en formas convexas como los elipsoides, estos pueden coincidir mejor con las formas del nicho ecológico fundamental, incorporando herramientas para explorar, modelar y evaluar nichos y distribuciones que son intuitivas tanto para principiantes como para usuarios expertos.
Aquí describimos un paquete de r, NicheToolBox (ntbox), que permite a los usuarios realizar todos los pasos de procesamiento involucrados en el modelado de nicho ecológico: descargar y curar datos de presencia, obtener y transformar capas de datos ambientales, seleccionar variables ambientales, explorar relaciones entre los espacios geográfico y ecológico, calibrar y seleccionar modelos de elipsoides, evaluar modelos utilizando pruebas ROC binomiales y parciales, evaluar el riesgo de extrapolación y realizar operaciones de sistemas de información geográfica a través de una interfaz gráfica. Además, se puede generar un resumen de todo el flujo de trabajo para su uso como algoritmo independiente o como parte de informes de investigación.
El método se explica en detalle y se prueba mediante el modelado de la especie de felino amenazada Leopardus wiedii. Los datos de presencia georreferenciados para esta especie se muestran de manera puntual y con el polígono de la UICN. Esta información se utiliza para ilustrar las herramientas disponibles para acceder, procesar y explorar datos de biodiversidad (e.g. número de puntos y cronología de recolección) y la transformación de datos ambientales (e.g. un PCA resumido para 19 capas bioclimáticas). También se muestran visualizaciones de nichos ecológicos tridimensionales modelados como elipsoides de volumen mínimo y sus estadísticas. Finalmente, el modelo de nicho se proyecta al espacio geográfico, para representar un mapa de idoneidad potencial correspondiente.
El uso de ntbox permite un medio rápido y directo para recuperar y manipular datos de localidades de presencia y ambientales, que luego se pueden utilizar en la calibración, proyección y evaluación del modelo para estimar las distribuciones de especies en el espacio geográfico y sus correspondientes combinaciones ambientales.</abstract><cop>London</cop><pub>John Wiley & Sons, Inc</pub><doi>10.1111/2041-210X.13452</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-4296-7258</orcidid><orcidid>https://orcid.org/0000-0003-1184-9264</orcidid><orcidid>https://orcid.org/0000-0002-7893-8774</orcidid><orcidid>https://orcid.org/0000-0002-3219-0019</orcidid><orcidid>https://orcid.org/0000-0003-2160-4148</orcidid><orcidid>https://orcid.org/0000-0002-0569-8984</orcidid><orcidid>https://orcid.org/0000-0003-0701-5398</orcidid><orcidid>https://orcid.org/0000-0002-4852-2567</orcidid><orcidid>https://orcid.org/0000-0003-0243-2379</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2041-210X |
| ispartof | Methods in ecology and evolution, 2020-10, Vol.11 (10), p.1199-1206 |
| issn | 2041-210X 2041-210X |
| language | eng |
| recordid | cdi_proquest_journals_2447397380 |
| source | Wiley-Blackwell Journals |
| subjects | Algorithms Bioclimatology Biodiversity biodiversity informatics Calibration Computer programs ecological niche modelling Ecological niches Ellipsoids Evaluation Geographic information systems GIS tools Graphical user interface Learning algorithms Leopardus wiedii Machine learning minimum volume ellipsoid model evaluation model selection model uncertainty Niches Remote sensing Software Software packages species distribution Statistical methods Threatened species User interface Workflow |
| title | ntbox: An r package with graphical user interface for modelling and evaluating multidimensional ecological niches |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-21T23%3A13%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ntbox:%20An%20r%20package%20with%20graphical%20user%20interface%20for%20modelling%20and%20evaluating%20multidimensional%20ecological%20niches&rft.jtitle=Methods%20in%20ecology%20and%20evolution&rft.au=Osorio%E2%80%90Olvera,%20Luis&rft.date=2020-10&rft.volume=11&rft.issue=10&rft.spage=1199&rft.epage=1206&rft.pages=1199-1206&rft.issn=2041-210X&rft.eissn=2041-210X&rft_id=info:doi/10.1111/2041-210X.13452&rft_dat=%3Cproquest_cross%3E2447397380%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c3182-81efc229c0bf9b5340ba7e120b2c31090cf588c736898e0f0a69923ee888083a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2447397380&rft_id=info:pmid/&rfr_iscdi=true |