Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3389/fenvs.2023.1083328 http://hdl.handle.net/11449/249685 |
Resumo: | Modern UAS (Unmanned Aerial Vehicles) or just drones have emerged with the primary goal of producing maps and imagery with extremely high spatial resolution. The refined information provides a good opportunity to quantify the distribution of vegetation across heterogeneous landscapes, revealing an important strategy for biodiversity conservation. We investigate whether computer vision and machine learning techniques (Object-Based Image Analysis—OBIA method, associated with Random Forest classifier) are effective to classify heterogeneous vegetation arising from ultrahigh-resolution data generated by UAS images. We focus our fieldwork in a highly diverse, seasonally dry, complex mountaintop vegetation system, the campo rupestre or rupestrian grassland, located at Serra do Cipó, Espinhaço Range, Southeastern Brazil. According to our results, all classifications received general accuracy above 0.95, indicating that the methodological approach enabled the identification of subtle variations in species composition, the capture of detailed vegetation and landscape features, and the recognition of vegetation types’ phenophases. Therefore, our study demonstrated that the machine learning approach and combination between OBIA method and Random Forest classifier, generated extremely high accuracy classification, reducing the misclassified pixels, and providing valuable data for the classification of complex vegetation systems such as the campo rupestre mountaintop grassland. |
id |
UNSP_b3c7b73083021dbff4f8870eb5a2d757 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/249685 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by dronesheterogeneous vegetationmachine learningphenologyrandom forestrupestrian grasslandUASunmanned aerial systemModern UAS (Unmanned Aerial Vehicles) or just drones have emerged with the primary goal of producing maps and imagery with extremely high spatial resolution. The refined information provides a good opportunity to quantify the distribution of vegetation across heterogeneous landscapes, revealing an important strategy for biodiversity conservation. We investigate whether computer vision and machine learning techniques (Object-Based Image Analysis—OBIA method, associated with Random Forest classifier) are effective to classify heterogeneous vegetation arising from ultrahigh-resolution data generated by UAS images. We focus our fieldwork in a highly diverse, seasonally dry, complex mountaintop vegetation system, the campo rupestre or rupestrian grassland, located at Serra do Cipó, Espinhaço Range, Southeastern Brazil. According to our results, all classifications received general accuracy above 0.95, indicating that the methodological approach enabled the identification of subtle variations in species composition, the capture of detailed vegetation and landscape features, and the recognition of vegetation types’ phenophases. Therefore, our study demonstrated that the machine learning approach and combination between OBIA method and Random Forest classifier, generated extremely high accuracy classification, reducing the misclassified pixels, and providing valuable data for the classification of complex vegetation systems such as the campo rupestre mountaintop grassland.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Graduate Program of Remote Sensing National Institute for Space Research (INPE) Earth Observation and Geoinformatics Division (DIOTG)Phenology Lab Institute of Biosciences Despartment of Biodiversity São Paulo State University (UNESP)Ecosystem Dynamics Observatory (EcoDyn) Biological and Environmental Sciences Faculty of Natural Sciences University of StirlingPhenology Lab Institute of Biosciences Despartment of Biodiversity São Paulo State University (UNESP)FAPESP: #2010/521113-5 #2009/54208-6 #2019/03269-7Earth Observation and Geoinformatics Division (DIOTG)Universidade Estadual Paulista (UNESP)University of StirlingMedeiros, Thaís Pereira de [UNESP]Morellato, Leonor Patrícia Cerdeira [UNESP]Silva, Thiago Sanna Freire2023-07-29T16:06:28Z2023-07-29T16:06:28Z2023-02-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3389/fenvs.2023.1083328Frontiers in Environmental Science, v. 11.2296-665Xhttp://hdl.handle.net/11449/24968510.3389/fenvs.2023.10833282-s2.0-85148653208Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengFrontiers in Environmental Scienceinfo:eu-repo/semantics/openAccess2023-07-29T16:06:28Zoai:repositorio.unesp.br:11449/249685Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-07-29T16:06:28Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
title |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
spellingShingle |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones Medeiros, Thaís Pereira de [UNESP] heterogeneous vegetation machine learning phenology random forest rupestrian grassland UAS unmanned aerial system |
title_short |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
title_full |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
title_fullStr |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
title_full_unstemmed |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
title_sort |
Spatial distribution and temporal variation of tropical mountaintop vegetation through images obtained by drones |
author |
Medeiros, Thaís Pereira de [UNESP] |
author_facet |
Medeiros, Thaís Pereira de [UNESP] Morellato, Leonor Patrícia Cerdeira [UNESP] Silva, Thiago Sanna Freire |
author_role |
author |
author2 |
Morellato, Leonor Patrícia Cerdeira [UNESP] Silva, Thiago Sanna Freire |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Earth Observation and Geoinformatics Division (DIOTG) Universidade Estadual Paulista (UNESP) University of Stirling |
dc.contributor.author.fl_str_mv |
Medeiros, Thaís Pereira de [UNESP] Morellato, Leonor Patrícia Cerdeira [UNESP] Silva, Thiago Sanna Freire |
dc.subject.por.fl_str_mv |
heterogeneous vegetation machine learning phenology random forest rupestrian grassland UAS unmanned aerial system |
topic |
heterogeneous vegetation machine learning phenology random forest rupestrian grassland UAS unmanned aerial system |
description |
Modern UAS (Unmanned Aerial Vehicles) or just drones have emerged with the primary goal of producing maps and imagery with extremely high spatial resolution. The refined information provides a good opportunity to quantify the distribution of vegetation across heterogeneous landscapes, revealing an important strategy for biodiversity conservation. We investigate whether computer vision and machine learning techniques (Object-Based Image Analysis—OBIA method, associated with Random Forest classifier) are effective to classify heterogeneous vegetation arising from ultrahigh-resolution data generated by UAS images. We focus our fieldwork in a highly diverse, seasonally dry, complex mountaintop vegetation system, the campo rupestre or rupestrian grassland, located at Serra do Cipó, Espinhaço Range, Southeastern Brazil. According to our results, all classifications received general accuracy above 0.95, indicating that the methodological approach enabled the identification of subtle variations in species composition, the capture of detailed vegetation and landscape features, and the recognition of vegetation types’ phenophases. Therefore, our study demonstrated that the machine learning approach and combination between OBIA method and Random Forest classifier, generated extremely high accuracy classification, reducing the misclassified pixels, and providing valuable data for the classification of complex vegetation systems such as the campo rupestre mountaintop grassland. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T16:06:28Z 2023-07-29T16:06:28Z 2023-02-10 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3389/fenvs.2023.1083328 Frontiers in Environmental Science, v. 11. 2296-665X http://hdl.handle.net/11449/249685 10.3389/fenvs.2023.1083328 2-s2.0-85148653208 |
url |
http://dx.doi.org/10.3389/fenvs.2023.1083328 http://hdl.handle.net/11449/249685 |
identifier_str_mv |
Frontiers in Environmental Science, v. 11. 2296-665X 10.3389/fenvs.2023.1083328 2-s2.0-85148653208 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Frontiers in Environmental Science |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799964824555225088 |