Remote Sensing for Land Use / Land Cover Mapping in Almada
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/151807 |
Resumo: | Monitoring land use and land cover is an extremely important task which, if properly carried out, can assist in decision making about urban and territorial planning, thus pro- viding an improvement in the citizens’ quality of life. In Portugal, and more specifically in the Almada municipality , the main tool used in this task is Carta de Ocupação de Solo (COS), a map which represents 83 classes of land use and land cover. Despite its useful- ness, COS has certain limitations, such as low spatial resolution, due to the minimum mapping unit of 1 hectare, and low temporal resolution, as it is developed through the analysis of orthophotos and released every 3 to 5 years. These constraints lead to a map which is not adequate to continuously track land-use and land-cover changes, especially with the increasingly fast pace of urbanization. This research work investigated the application of machine learning classification algorithms with Sentinel-1 and Sentinel-2 imagery, and derived products, to LULC map- ping in Almada. As such, maps were developed for 2018 using the two most common approaches to LULC classification: pixel-based (PBIA) and object-based (OBIA). Multiple combinations of satellite data and derived products, as well as two classifiers were tested for each approach. A comparison of two methods of collecting ground truth data, manual and semi-automatic, was also produced. The best results were obtained in the PBIA approach, using the manually collected ground truth and the Extreme Gradient Boosting (XGBoost) classifier with the combina- tion of Sentinel-1 and Sentinel-2 imagery and textural features obtained through Sentinel- 2 data. The classification model obtained a kappa score of 0.994, and produced an ac- curate LULC map, which has some limitations in separating Agriculture and Other Vegetation, but is able to identify with great precision Artificial Territories, Forests and Bare and sparsely vegetated areas. |
id |
RCAP_7047f250daff867d0b1f39c81f395ddf |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/151807 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Remote Sensing for Land Use / Land Cover Mapping in AlmadaRemote sensingSentinel-1Sentinel-2Machine LearningLULC MappingObject-based LULC ClassificationDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaMonitoring land use and land cover is an extremely important task which, if properly carried out, can assist in decision making about urban and territorial planning, thus pro- viding an improvement in the citizens’ quality of life. In Portugal, and more specifically in the Almada municipality , the main tool used in this task is Carta de Ocupação de Solo (COS), a map which represents 83 classes of land use and land cover. Despite its useful- ness, COS has certain limitations, such as low spatial resolution, due to the minimum mapping unit of 1 hectare, and low temporal resolution, as it is developed through the analysis of orthophotos and released every 3 to 5 years. These constraints lead to a map which is not adequate to continuously track land-use and land-cover changes, especially with the increasingly fast pace of urbanization. This research work investigated the application of machine learning classification algorithms with Sentinel-1 and Sentinel-2 imagery, and derived products, to LULC map- ping in Almada. As such, maps were developed for 2018 using the two most common approaches to LULC classification: pixel-based (PBIA) and object-based (OBIA). Multiple combinations of satellite data and derived products, as well as two classifiers were tested for each approach. A comparison of two methods of collecting ground truth data, manual and semi-automatic, was also produced. The best results were obtained in the PBIA approach, using the manually collected ground truth and the Extreme Gradient Boosting (XGBoost) classifier with the combina- tion of Sentinel-1 and Sentinel-2 imagery and textural features obtained through Sentinel- 2 data. The classification model obtained a kappa score of 0.994, and produced an ac- curate LULC map, which has some limitations in separating Agriculture and Other Vegetation, but is able to identify with great precision Artificial Territories, Forests and Bare and sparsely vegetated areas.A monitorização da utilização e ocupação do solo (LULC) é uma tarefa de extrema im- portância que, sendo adequadamente realizada, pode auxiliar na tomada de decisões de ordenamento do território, providenciando assim uma melhoria na qualidade de vida dos cidadãos. Em Portugal, e mais especificamente no concelho de Almada, a principal ferramenta utilizada nesta tarefa é a Carta de Uso e Ocupação do Solo (COS), um mapa que divide o solo em 83 classes. Embora notavelmente útil, a COS possui determinadas limitações, entre as quais baixa resolução espacial, devido á unidade mínima cartográfica de 1 hectare, e baixa resolução espacial, sendo desenvolvida através da análise de ortofo- tos e disponibilizada a cada 3 a 5 anos. Estas limitações levam a que este mapa não seja adequado para a monitorização contínua de alterações ao nível da utilização e ocupação do solo, especialmente com o ritmo cada vez mais acelerado do crescimento urbano. Este trabalho de investigação estudou a aplicação de algoritmos de classificação de machine learning com imagens de Sentinel-1 e Sentinel-2 e produtos derivados, para a cartografia de uso e ocupação de solo em Almada. Assim, foram desenvolvidos mapas para o ano 2018 explorando duas metodologias frequentemente utilizadas em problemas de classificação de uso e ocupação do solo: baseada em píxeis (PBIA) e baseada em objetos (OBIA). Para cada abordagem foram testadas várias combinações de imagens de satélite e produtos derivados, assim como dois classificadores automáticos. Foi também produzida uma comparação entre dois tipos de ground truth: obtida manualmente, e de uma forma semi-automática. Os melhores resultados foram obtidos na abordagem baseada em pixeis, utilizando a ground truth manual e o classificador Extreme Gradient Boosting (XGBoost) com a combinação de imagens de Sentinel-1, Sentinel-2 e atributos de textura calculados através de imagens de Sentinel-2. Este modelo de classificação obteve um coeficiente kappa de 0.994 e produziu um mapa de uso e ocupação do solo com boa precisão e que, embora tenha algumas limitações ao nível de separação das classes 2. Agricultura e 3. Outra vegetação, identifica com exatidão as classes Territórios Artificializados, Florestas e Espaços descobertos ou com pouca vegetação.Damásio, CarlosPires, JoãoRUNOliveira, Inês Cardoso Leitão Barata de2023-04-14T10:29:42Z2022-072022-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/151807enginfo: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:RCAAP2024-03-11T05:34:11Zoai:run.unl.pt:10362/151807Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:54:42.313872Repositório 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 |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
title |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
spellingShingle |
Remote Sensing for Land Use / Land Cover Mapping in Almada Oliveira, Inês Cardoso Leitão Barata de Remote sensing Sentinel-1 Sentinel-2 Machine Learning LULC Mapping Object-based LULC Classification Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
title_full |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
title_fullStr |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
title_full_unstemmed |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
title_sort |
Remote Sensing for Land Use / Land Cover Mapping in Almada |
author |
Oliveira, Inês Cardoso Leitão Barata de |
author_facet |
Oliveira, Inês Cardoso Leitão Barata de |
author_role |
author |
dc.contributor.none.fl_str_mv |
Damásio, Carlos Pires, João RUN |
dc.contributor.author.fl_str_mv |
Oliveira, Inês Cardoso Leitão Barata de |
dc.subject.por.fl_str_mv |
Remote sensing Sentinel-1 Sentinel-2 Machine Learning LULC Mapping Object-based LULC Classification Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
Remote sensing Sentinel-1 Sentinel-2 Machine Learning LULC Mapping Object-based LULC Classification Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
Monitoring land use and land cover is an extremely important task which, if properly carried out, can assist in decision making about urban and territorial planning, thus pro- viding an improvement in the citizens’ quality of life. In Portugal, and more specifically in the Almada municipality , the main tool used in this task is Carta de Ocupação de Solo (COS), a map which represents 83 classes of land use and land cover. Despite its useful- ness, COS has certain limitations, such as low spatial resolution, due to the minimum mapping unit of 1 hectare, and low temporal resolution, as it is developed through the analysis of orthophotos and released every 3 to 5 years. These constraints lead to a map which is not adequate to continuously track land-use and land-cover changes, especially with the increasingly fast pace of urbanization. This research work investigated the application of machine learning classification algorithms with Sentinel-1 and Sentinel-2 imagery, and derived products, to LULC map- ping in Almada. As such, maps were developed for 2018 using the two most common approaches to LULC classification: pixel-based (PBIA) and object-based (OBIA). Multiple combinations of satellite data and derived products, as well as two classifiers were tested for each approach. A comparison of two methods of collecting ground truth data, manual and semi-automatic, was also produced. The best results were obtained in the PBIA approach, using the manually collected ground truth and the Extreme Gradient Boosting (XGBoost) classifier with the combina- tion of Sentinel-1 and Sentinel-2 imagery and textural features obtained through Sentinel- 2 data. The classification model obtained a kappa score of 0.994, and produced an ac- curate LULC map, which has some limitations in separating Agriculture and Other Vegetation, but is able to identify with great precision Artificial Territories, Forests and Bare and sparsely vegetated areas. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-07 2022-07-01T00:00:00Z 2023-04-14T10:29:42Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/151807 |
url |
http://hdl.handle.net/10362/151807 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
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_ |
1799138135380066304 |