Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images
Descripción del Articulo
Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment...
Autores: | , , , , , , |
---|---|
Formato: | artículo |
Fecha de Publicación: | 2020 |
Institución: | Consejo Nacional de Ciencia Tecnología e Innovación |
Repositorio: | CONCYTEC-Institucional |
Lenguaje: | inglés |
OAI Identifier: | oai:repositorio.concytec.gob.pe:20.500.12390/2532 |
Enlace del recurso: | https://hdl.handle.net/20.500.12390/2532 https://doi.org/10.3390/rs12142225 |
Nivel de acceso: | acceso abierto |
Materia: | Very high resolution images Deep learning Semantic segmentation Species distribution U-net http://purl.org/pe-repo/ocde/ford#2.07.01 |
id |
CONC_c4700f60d222d4204b6f89f8ab164559 |
---|---|
oai_identifier_str |
oai:repositorio.concytec.gob.pe:20.500.12390/2532 |
network_acronym_str |
CONC |
network_name_str |
CONCYTEC-Institucional |
repository_id_str |
4689 |
dc.title.none.fl_str_mv |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
title |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
spellingShingle |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images Wagner F.H. Very high resolution images Deep learning Semantic segmentation Species distribution U-net http://purl.org/pe-repo/ocde/ford#2.07.01 |
title_short |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
title_full |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
title_fullStr |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
title_full_unstemmed |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
title_sort |
Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images |
author |
Wagner F.H. |
author_facet |
Wagner F.H. Dalagnol R. Casapia X.T. Streher A.S. Phillips O.L. Gloor E. Aragăo L.E.O.C. |
author_role |
author |
author2 |
Dalagnol R. Casapia X.T. Streher A.S. Phillips O.L. Gloor E. Aragăo L.E.O.C. |
author2_role |
author author author author author author |
dc.contributor.author.fl_str_mv |
Wagner F.H. Dalagnol R. Casapia X.T. Streher A.S. Phillips O.L. Gloor E. Aragăo L.E.O.C. |
dc.subject.none.fl_str_mv |
Very high resolution images |
topic |
Very high resolution images Deep learning Semantic segmentation Species distribution U-net http://purl.org/pe-repo/ocde/ford#2.07.01 |
dc.subject.es_PE.fl_str_mv |
Deep learning Semantic segmentation Species distribution U-net |
dc.subject.ocde.none.fl_str_mv |
http://purl.org/pe-repo/ocde/ford#2.07.01 |
description |
Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ~3000 km2 of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees' distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity. © 2020 by the authors. |
publishDate |
2020 |
dc.date.accessioned.none.fl_str_mv |
2024-05-30T23:13:38Z |
dc.date.available.none.fl_str_mv |
2024-05-30T23:13:38Z |
dc.date.issued.fl_str_mv |
2020 |
dc.type.none.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12390/2532 |
dc.identifier.doi.none.fl_str_mv |
https://doi.org/10.3390/rs12142225 |
dc.identifier.scopus.none.fl_str_mv |
2-s2.0-85088628575 |
url |
https://hdl.handle.net/20.500.12390/2532 https://doi.org/10.3390/rs12142225 |
identifier_str_mv |
2-s2.0-85088628575 |
dc.language.iso.none.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.none.fl_str_mv |
Remote Sensing |
dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
dc.rights.uri.none.fl_str_mv |
https://creativecommons.org/licenses/by/4.0/ |
eu_rights_str_mv |
openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0/ |
dc.publisher.none.fl_str_mv |
MDPI AG |
publisher.none.fl_str_mv |
MDPI AG |
dc.source.none.fl_str_mv |
reponame:CONCYTEC-Institucional instname:Consejo Nacional de Ciencia Tecnología e Innovación instacron:CONCYTEC |
instname_str |
Consejo Nacional de Ciencia Tecnología e Innovación |
instacron_str |
CONCYTEC |
institution |
CONCYTEC |
reponame_str |
CONCYTEC-Institucional |
collection |
CONCYTEC-Institucional |
bitstream.url.fl_str_mv |
https://repositorio.concytec.gob.pe/bitstreams/7842c22b-ef22-4010-b8aa-4ec6c36e0824/download https://repositorio.concytec.gob.pe/bitstreams/25f93afc-facb-4efc-b41e-ad6595346e6b/download https://repositorio.concytec.gob.pe/bitstreams/a16617b4-1599-4f4b-9ab1-0d5fd19b503c/download |
bitstream.checksum.fl_str_mv |
58670976bead7c82aa90f0d185b0c76e b72f9478e83d276173d7155ca478aee8 b25ef54a57fa3a0fc38c1776b51da029 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositorio Institucional CONCYTEC |
repository.mail.fl_str_mv |
repositorio@concytec.gob.pe |
_version_ |
1844883013270241280 |
spelling |
Publicationrp06514600rp06513600rp06516600rp06518600rp06517600rp06515600rp06512600Wagner F.H.Dalagnol R.Casapia X.T.Streher A.S.Phillips O.L.Gloor E.Aragăo L.E.O.C.2024-05-30T23:13:38Z2024-05-30T23:13:38Z2020https://hdl.handle.net/20.500.12390/2532https://doi.org/10.3390/rs121422252-s2.0-85088628575Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ~3000 km2 of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees' distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity. © 2020 by the authors.Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - ConcytecengMDPI AGRemote Sensinginfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/4.0/Very high resolution imagesDeep learning-1Semantic segmentation-1Species distribution-1U-net-1http://purl.org/pe-repo/ocde/ford#2.07.01-1Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR imagesinfo:eu-repo/semantics/articlereponame:CONCYTEC-Institucionalinstname:Consejo Nacional de Ciencia Tecnología e Innovacióninstacron:CONCYTECORIGINALRegional Mapping and Spatial Distribution Analysis of Canopy.pdfRegional Mapping and Spatial Distribution Analysis of Canopy.pdfapplication/pdf8531826https://repositorio.concytec.gob.pe/bitstreams/7842c22b-ef22-4010-b8aa-4ec6c36e0824/download58670976bead7c82aa90f0d185b0c76eMD51TEXTRegional Mapping and Spatial Distribution Analysis of Canopy.pdf.txtRegional Mapping and Spatial Distribution Analysis of Canopy.pdf.txtExtracted texttext/plain70350https://repositorio.concytec.gob.pe/bitstreams/25f93afc-facb-4efc-b41e-ad6595346e6b/downloadb72f9478e83d276173d7155ca478aee8MD52THUMBNAILRegional Mapping and Spatial Distribution Analysis of Canopy.pdf.jpgRegional Mapping and Spatial Distribution Analysis of Canopy.pdf.jpgGenerated Thumbnailimage/jpeg5521https://repositorio.concytec.gob.pe/bitstreams/a16617b4-1599-4f4b-9ab1-0d5fd19b503c/downloadb25ef54a57fa3a0fc38c1776b51da029MD5320.500.12390/2532oai:repositorio.concytec.gob.pe:20.500.12390/25322025-01-14 22:00:45.907https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessopen accesshttps://repositorio.concytec.gob.peRepositorio Institucional CONCYTECrepositorio@concytec.gob.pe#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="aa1d62ba-0fe2-4fd2-8789-639a052fb62c"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Regional mapping and spatial distribution analysis of Canopy palms in an Amazon forest using deep learning and VHR images</Title> <PublishedIn> <Publication> <Title>Remote Sensing</Title> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <DOI>https://doi.org/10.3390/rs12142225</DOI> <SCP-Number>2-s2.0-85088628575</SCP-Number> <Authors> <Author> <DisplayName>Wagner F.H.</DisplayName> <Person id="rp06514" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Dalagnol R.</DisplayName> <Person id="rp06513" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Casapia X.T.</DisplayName> <Person id="rp06516" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Streher A.S.</DisplayName> <Person id="rp06518" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Phillips O.L.</DisplayName> <Person id="rp06517" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Gloor E.</DisplayName> <Person id="rp06515" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Aragăo L.E.O.C.</DisplayName> <Person id="rp06512" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>MDPI AG</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by/4.0/</License> <Keyword>Very high resolution images</Keyword> <Keyword>Deep learning</Keyword> <Keyword>Semantic segmentation</Keyword> <Keyword>Species distribution</Keyword> <Keyword>U-net</Keyword> <Abstract>Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ~3000 km2 of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees' distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity. © 2020 by the authors.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication> -1 |
score |
13.062656 |
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).