A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia

ABSTRACT : In this work, we first present a methodology for preparing 10 m to 60 m spatial resolution Sentinel-1, Sentinel-2, and ALOS DSM imagery of forest/grassland areas in Colombia to train a DeepLabV3+ convolutional neural network model. Our preprocessing pipeline for the Sentinel-2 imagery com...

Full description

Autores:
Ceballos Arroyo, Alberto Mario
Tipo de recurso:
Tesis
Fecha de publicación:
2021
Institución:
Universidad de Antioquia
Repositorio:
Repositorio UdeA
Idioma:
eng
OAI Identifier:
oai:bibliotecadigital.udea.edu.co:10495/20659
Acceso en línea:
http://hdl.handle.net/10495/20659
Palabra clave:
Remote sensing
Teledetección
Machine learning
Aprendizaje electrónico
Imágenes por satélites
Satellite imagery
Redes de neuronas
Neural networks
Tratamiento de imágenes
Image processing
Deep Learning
Sentinel-2
Convolutional Neural Network
Satellite Imagery
http://aims.fao.org/aos/agrovoc/c_49834
http://aims.fao.org/aos/agrovoc/c_37359
http://aims.fao.org/aos/agrovoc/c_36761
http://aims.fao.org/aos/agrovoc/c_37467
http://vocabularies.unesco.org/thesaurus/concept1557
Rights
openAccess
License
http://creativecommons.org/publicdomain/zero/1.0/
id UDEA2_4dfc4fde7c0faff410dfd651c26148e1
oai_identifier_str oai:bibliotecadigital.udea.edu.co:10495/20659
network_acronym_str UDEA2
network_name_str Repositorio UdeA
repository_id_str
dc.title.spa.fl_str_mv A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
title A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
spellingShingle A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
Remote sensing
Teledetección
Machine learning
Aprendizaje electrónico
Imágenes por satélites
Satellite imagery
Redes de neuronas
Neural networks
Tratamiento de imágenes
Image processing
Deep Learning
Sentinel-2
Convolutional Neural Network
Satellite Imagery
http://aims.fao.org/aos/agrovoc/c_49834
http://aims.fao.org/aos/agrovoc/c_37359
http://aims.fao.org/aos/agrovoc/c_36761
http://aims.fao.org/aos/agrovoc/c_37467
http://vocabularies.unesco.org/thesaurus/concept1557
title_short A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
title_full A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
title_fullStr A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
title_full_unstemmed A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
title_sort A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: Colombia
dc.creator.fl_str_mv Ceballos Arroyo, Alberto Mario
dc.contributor.advisor.none.fl_str_mv Ramos Pollán, Raul
dc.contributor.author.none.fl_str_mv Ceballos Arroyo, Alberto Mario
dc.subject.unesco.none.fl_str_mv Remote sensing
Teledetección
topic Remote sensing
Teledetección
Machine learning
Aprendizaje electrónico
Imágenes por satélites
Satellite imagery
Redes de neuronas
Neural networks
Tratamiento de imágenes
Image processing
Deep Learning
Sentinel-2
Convolutional Neural Network
Satellite Imagery
http://aims.fao.org/aos/agrovoc/c_49834
http://aims.fao.org/aos/agrovoc/c_37359
http://aims.fao.org/aos/agrovoc/c_36761
http://aims.fao.org/aos/agrovoc/c_37467
http://vocabularies.unesco.org/thesaurus/concept1557
dc.subject.agrovoc.none.fl_str_mv Machine learning
Aprendizaje electrónico
Imágenes por satélites
Satellite imagery
Redes de neuronas
Neural networks
Tratamiento de imágenes
Image processing
dc.subject.proposal.spa.fl_str_mv Deep Learning
Sentinel-2
Convolutional Neural Network
Satellite Imagery
dc.subject.agrovocuri.none.fl_str_mv http://aims.fao.org/aos/agrovoc/c_49834
http://aims.fao.org/aos/agrovoc/c_37359
http://aims.fao.org/aos/agrovoc/c_36761
http://aims.fao.org/aos/agrovoc/c_37467
dc.subject.unescouri.none.fl_str_mv http://vocabularies.unesco.org/thesaurus/concept1557
description ABSTRACT : In this work, we first present a methodology for preparing 10 m to 60 m spatial resolution Sentinel-1, Sentinel-2, and ALOS DSM imagery of forest/grassland areas in Colombia to train a DeepLabV3+ convolutional neural network model. Our preprocessing pipeline for the Sentinel-2 imagery comprises cloud and shadow removal, atmospheric correction, and topographical correction, resulting in mostly cloud-free mosaics of tropical areas. At first, we train the network on very low spatial resolution (500 m) labels of the Colombian Amazonas region resampled to 10 m (+100000 samples after augmentation). Then, we fine-tune the network on medium spatial resolution data (30 m) of northern Antioquia, also resampled to 10 m, resulting in faster convergence and higher accuracy despite the limited number of labelled samples (~5000 samples after augmentation). Our results validate recent proposals where low spatial resolution data is used for training neural networks, and motivate us to keep exploring this line of research.
publishDate 2021
dc.date.accessioned.none.fl_str_mv 2021-07-06T21:38:06Z
dc.date.available.none.fl_str_mv 2021-07-06T21:38:06Z
dc.date.issued.none.fl_str_mv 2021
dc.type.spa.fl_str_mv info:eu-repo/semantics/other
dc.type.coarversion.fl_str_mv http://purl.org/coar/version/c_b1a7d7d4d402bcce
dc.type.hasversion.spa.fl_str_mv info:eu-repo/semantics/draft
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_46ec
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/COther
dc.type.local.spa.fl_str_mv Tesis/Trabajo de grado - Monografía - Especialización
format http://purl.org/coar/resource_type/c_46ec
status_str draft
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/10495/20659
url http://hdl.handle.net/10495/20659
dc.language.iso.spa.fl_str_mv eng
language eng
dc.rights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.uri.*.fl_str_mv http://creativecommons.org/publicdomain/zero/1.0/
dc.rights.accessrights.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.creativecommons.spa.fl_str_mv https://creativecommons.org/licenses/by-nc-sa/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/publicdomain/zero/1.0/
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by-nc-sa/4.0/
dc.format.extent.spa.fl_str_mv 22
dc.format.mimetype.spa.fl_str_mv pdf
dc.publisher.place.spa.fl_str_mv Medellín, Colombia
institution Universidad de Antioquia
bitstream.url.fl_str_mv http://bibliotecadigital.udea.edu.co/bitstream/10495/20659/2/Ceballos_Alberto_2021_ML_LULC_Colombia.pdf
http://bibliotecadigital.udea.edu.co/bitstream/10495/20659/3/license_rdf
http://bibliotecadigital.udea.edu.co/bitstream/10495/20659/6/license.txt
bitstream.checksum.fl_str_mv 79b6cabd5ad872427257694e511d20f4
fd0548b8694973befb689f3e7a707f1d
8a4605be74aa9ea9d79846c1fba20a33
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositorio Institucional Universidad de Antioquia
repository.mail.fl_str_mv andres.perez@udea.edu.co
_version_ 1812173227944837120
spelling Ramos Pollán, RaulCeballos Arroyo, Alberto Mario2021-07-06T21:38:06Z2021-07-06T21:38:06Z2021http://hdl.handle.net/10495/20659ABSTRACT : In this work, we first present a methodology for preparing 10 m to 60 m spatial resolution Sentinel-1, Sentinel-2, and ALOS DSM imagery of forest/grassland areas in Colombia to train a DeepLabV3+ convolutional neural network model. Our preprocessing pipeline for the Sentinel-2 imagery comprises cloud and shadow removal, atmospheric correction, and topographical correction, resulting in mostly cloud-free mosaics of tropical areas. At first, we train the network on very low spatial resolution (500 m) labels of the Colombian Amazonas region resampled to 10 m (+100000 samples after augmentation). Then, we fine-tune the network on medium spatial resolution data (30 m) of northern Antioquia, also resampled to 10 m, resulting in faster convergence and higher accuracy despite the limited number of labelled samples (~5000 samples after augmentation). Our results validate recent proposals where low spatial resolution data is used for training neural networks, and motivate us to keep exploring this line of research.22pdfenginfo:eu-repo/semantics/draftinfo:eu-repo/semantics/otherhttp://purl.org/coar/resource_type/c_46echttp://purl.org/redcol/resource_type/COtherTesis/Trabajo de grado - Monografía - Especializaciónhttp://purl.org/coar/version/c_b1a7d7d4d402bcceinfo:eu-repo/semantics/openAccesshttp://creativecommons.org/publicdomain/zero/1.0/http://purl.org/coar/access_right/c_abf2https://creativecommons.org/licenses/by-nc-sa/4.0/A machine learning methodology for land use/land cover classification in tropical areas using medium resolution satellite imagery, case: ColombiaMedellín, ColombiaRemote sensingTeledetecciónMachine learningAprendizaje electrónicoImágenes por satélitesSatellite imageryRedes de neuronasNeural networksTratamiento de imágenesImage processingDeep LearningSentinel-2Convolutional Neural NetworkSatellite Imageryhttp://aims.fao.org/aos/agrovoc/c_49834http://aims.fao.org/aos/agrovoc/c_37359http://aims.fao.org/aos/agrovoc/c_36761http://aims.fao.org/aos/agrovoc/c_37467http://vocabularies.unesco.org/thesaurus/concept1557https://drive.google.com/file/d/1uYiQiuiUTjwVbnYwZTNRQJpLWR-XFYtc/view?usp=sharingEspecialista en Analítica y Ciencia de DatosEspecializaciónFacultad de Ingeniería. Especialización en Analítica y Ciencia de DatosUniversidad de AntioquiaORIGINALCeballos_Alberto_2021_ML_LULC_Colombia.pdfCeballos_Alberto_2021_ML_LULC_Colombia.pdfTrabajo de grado de especializaciónapplication/pdf2065897http://bibliotecadigital.udea.edu.co/bitstream/10495/20659/2/Ceballos_Alberto_2021_ML_LULC_Colombia.pdf79b6cabd5ad872427257694e511d20f4MD52CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8712http://bibliotecadigital.udea.edu.co/bitstream/10495/20659/3/license_rdffd0548b8694973befb689f3e7a707f1dMD53LICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://bibliotecadigital.udea.edu.co/bitstream/10495/20659/6/license.txt8a4605be74aa9ea9d79846c1fba20a33MD5610495/20659oai:bibliotecadigital.udea.edu.co:10495/206592021-07-06 16:41:24.937Repositorio Institucional Universidad de Antioquiaandres.perez@udea.edu.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