Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10174/31995 https://doi.org/Raiyani, K.; Gonçalves, T.; Rato, L.; Salgueiro, P.; Marques da Silva, J.R. Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach. Remote Sens. 2021, 13, 300. https://doi.org/10.3390/rs13020300 https://doi.org/10.3390/rs13020300 |
Resumo: | Given the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge. Several approaches have been proposed either by using static rule-based thresholds (with limitation of diversity) or neural network (with data-dependent limitations). This paper adopts the inductive approach to learning from surface reflectances. A manually labeled Sentinel-2 dataset was used to build a Machine Learning (ML) model for scene classification, distinguishing six classes (Water, Shadow, Cirrus, Cloud, Snow, and Other). This models was accessed and further compared to the European Space Agency (ESA) Sen2Cor package. The proposed ML model presents a Micro-F1 value of 0.84, a considerable improvement when compared to the Sen2Cor corresponding performance of 0.59. Focusing on the problem of optical satellite image scene classification, the main research contributions of this paper are: (a) an extended manually labeled Sentinel-2 database adding surface reflectance values to an existing dataset; (b) an ensemble-based and a Neural-Network-based ML models; (c) an evaluation of model sensitivity, biasness, and diverse ability in classifying multiple classes over different geographic Sentinel-2 imagery, and finally, (d) the benchmarking of the ML approach against the Sen2Cor package. |
id |
RCAP_fe7a375641487486792495395438d275 |
---|---|
oai_identifier_str |
oai:dspace.uevora.pt:10174/31995 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning ApproachSentinel-2high-resolution imageryscene classificationSen2Corsurface reflectanceartificial intelligencemachine learningGiven the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge. Several approaches have been proposed either by using static rule-based thresholds (with limitation of diversity) or neural network (with data-dependent limitations). This paper adopts the inductive approach to learning from surface reflectances. A manually labeled Sentinel-2 dataset was used to build a Machine Learning (ML) model for scene classification, distinguishing six classes (Water, Shadow, Cirrus, Cloud, Snow, and Other). This models was accessed and further compared to the European Space Agency (ESA) Sen2Cor package. The proposed ML model presents a Micro-F1 value of 0.84, a considerable improvement when compared to the Sen2Cor corresponding performance of 0.59. Focusing on the problem of optical satellite image scene classification, the main research contributions of this paper are: (a) an extended manually labeled Sentinel-2 database adding surface reflectance values to an existing dataset; (b) an ensemble-based and a Neural-Network-based ML models; (c) an evaluation of model sensitivity, biasness, and diverse ability in classifying multiple classes over different geographic Sentinel-2 imagery, and finally, (d) the benchmarking of the ML approach against the Sen2Cor package.MDPI2022-05-03T14:42:55Z2022-05-032021-01-16T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10174/31995https://doi.org/Raiyani, K.; Gonçalves, T.; Rato, L.; Salgueiro, P.; Marques da Silva, J.R. Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach. Remote Sens. 2021, 13, 300. https://doi.org/10.3390/rs13020300http://hdl.handle.net/10174/31995https://doi.org/10.3390/rs13020300porhttps://www.mdpi.com/2072-4292/13/2/300#citekshyp22@gmail.comtcg@uevora.ptlmr@uevora.ptpds@uevora.ptnd283Raiyani, KashyapGonçalves, TeresaRato, LuísSalgueiro, PedroR. Marques da Silva, Joséinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-01-03T19:32:09Zoai:dspace.uevora.pt:10174/31995Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T01:21:03.815420Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
title |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
spellingShingle |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach Raiyani, Kashyap Sentinel-2 high-resolution imagery scene classification Sen2Cor surface reflectance artificial intelligence machine learning |
title_short |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
title_full |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
title_fullStr |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
title_full_unstemmed |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
title_sort |
Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach |
author |
Raiyani, Kashyap |
author_facet |
Raiyani, Kashyap Gonçalves, Teresa Rato, Luís Salgueiro, Pedro R. Marques da Silva, José |
author_role |
author |
author2 |
Gonçalves, Teresa Rato, Luís Salgueiro, Pedro R. Marques da Silva, José |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Raiyani, Kashyap Gonçalves, Teresa Rato, Luís Salgueiro, Pedro R. Marques da Silva, José |
dc.subject.por.fl_str_mv |
Sentinel-2 high-resolution imagery scene classification Sen2Cor surface reflectance artificial intelligence machine learning |
topic |
Sentinel-2 high-resolution imagery scene classification Sen2Cor surface reflectance artificial intelligence machine learning |
description |
Given the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge. Several approaches have been proposed either by using static rule-based thresholds (with limitation of diversity) or neural network (with data-dependent limitations). This paper adopts the inductive approach to learning from surface reflectances. A manually labeled Sentinel-2 dataset was used to build a Machine Learning (ML) model for scene classification, distinguishing six classes (Water, Shadow, Cirrus, Cloud, Snow, and Other). This models was accessed and further compared to the European Space Agency (ESA) Sen2Cor package. The proposed ML model presents a Micro-F1 value of 0.84, a considerable improvement when compared to the Sen2Cor corresponding performance of 0.59. Focusing on the problem of optical satellite image scene classification, the main research contributions of this paper are: (a) an extended manually labeled Sentinel-2 database adding surface reflectance values to an existing dataset; (b) an ensemble-based and a Neural-Network-based ML models; (c) an evaluation of model sensitivity, biasness, and diverse ability in classifying multiple classes over different geographic Sentinel-2 imagery, and finally, (d) the benchmarking of the ML approach against the Sen2Cor package. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-16T00:00:00Z 2022-05-03T14:42:55Z 2022-05-03 |
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://hdl.handle.net/10174/31995 https://doi.org/Raiyani, K.; Gonçalves, T.; Rato, L.; Salgueiro, P.; Marques da Silva, J.R. Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach. Remote Sens. 2021, 13, 300. https://doi.org/10.3390/rs13020300 http://hdl.handle.net/10174/31995 https://doi.org/10.3390/rs13020300 |
url |
http://hdl.handle.net/10174/31995 https://doi.org/Raiyani, K.; Gonçalves, T.; Rato, L.; Salgueiro, P.; Marques da Silva, J.R. Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach. Remote Sens. 2021, 13, 300. https://doi.org/10.3390/rs13020300 https://doi.org/10.3390/rs13020300 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://www.mdpi.com/2072-4292/13/2/300#cite kshyp22@gmail.com tcg@uevora.pt lmr@uevora.pt pds@uevora.pt nd 283 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
MDPI |
publisher.none.fl_str_mv |
MDPI |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799136692197654528 |