Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series

Detalhes bibliográficos
Autor(a) principal: Gino, Vinicius L. S. [UNESP]
Data de Publicação: 2023
Outros Autores: Negri, Rogerio G. [UNESP], Souza, Felipe N. [UNESP], Silva, Erivaldo A. [UNESP], Bressane, Adriano [UNESP], Mendes, Tatiana S. G. [UNESP], Casaca, Wallace [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.3390/su15064725
http://hdl.handle.net/11449/245606
Resumo: The synergistic use of remote sensing and unsupervised machine learning has emerged as a potential tool for addressing a variety of environmental monitoring applications, such as detecting disaster-affected areas and deforestation. This paper proposes a new machine-intelligent approach to detecting and characterizing spatio-temporal changes on the Earth's surface by using remote sensing data and unsupervised learning. Our framework was designed to be fully automatic by integrating unsupervised anomaly detection models, remote sensing image series, and open data extracted from the Google Earth Engine platform. The methodology was evaluated by taking both simulated and real-world environmental data acquired from several imaging sensors, including Landsat-8 OLI, Sentinel-2 MSI, and Terra MODIS. The experimental results were measured with the kappa and F1-score metrics, and they indicated an assertiveness level of 0.85 for the change detection task, demonstrating the accuracy and robustness of the proposed approach when addressing distinct environmental monitoring applications, including the detection of disaster-affected areas and deforestation mapping.
id UNSP_f121d18a8b1843acca49e7b352f15644
oai_identifier_str oai:repositorio.unesp.br:11449/245606
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Seriesanomaly detectiontime serieslandscape dynamicsframeworkThe synergistic use of remote sensing and unsupervised machine learning has emerged as a potential tool for addressing a variety of environmental monitoring applications, such as detecting disaster-affected areas and deforestation. This paper proposes a new machine-intelligent approach to detecting and characterizing spatio-temporal changes on the Earth's surface by using remote sensing data and unsupervised learning. Our framework was designed to be fully automatic by integrating unsupervised anomaly detection models, remote sensing image series, and open data extracted from the Google Earth Engine platform. The methodology was evaluated by taking both simulated and real-world environmental data acquired from several imaging sensors, including Landsat-8 OLI, Sentinel-2 MSI, and Terra MODIS. The experimental results were measured with the kappa and F1-score metrics, and they indicated an assertiveness level of 0.85 for the change detection task, demonstrating the accuracy and robustness of the proposed approach when addressing distinct environmental monitoring applications, including the detection of disaster-affected areas and deforestation mapping.Funda��o de Amparo � Pesquisa do Estado de S�o Paulo (FAPESP)Conselho Nacional de Desenvolvimento Cient�fico e Tecnol�gico (CNPq)Sao Paulo State University (UNESP)Sao Paulo State Univ UNESP, Sci & Technol Inst ICT, BR-12245000 Sao Jose Dos Campos, BrazilSao Paulo State Univ UNESP, Fac Sci & Technol FCT, BR-19060080 Presidente Prudente, BrazilSao Paulo State Univ UNESP, Inst Biosci Letters & Exact Sci IBILCE, BR-15054000 Sao Jose Do Rio Preto, BrazilSao Paulo State Univ UNESP, Sci & Technol Inst ICT, BR-12245000 Sao Jose Dos Campos, BrazilSao Paulo State Univ UNESP, Fac Sci & Technol FCT, BR-19060080 Presidente Prudente, BrazilSao Paulo State Univ UNESP, Inst Biosci Letters & Exact Sci IBILCE, BR-15054000 Sao Jose Do Rio Preto, BrazilFAPESP: 2021/01305-6FAPESP: 2021/03328-3CNPq: 316228/2021-4MdpiUniversidade Estadual Paulista (UNESP)Gino, Vinicius L. S. [UNESP]Negri, Rogerio G. [UNESP]Souza, Felipe N. [UNESP]Silva, Erivaldo A. [UNESP]Bressane, Adriano [UNESP]Mendes, Tatiana S. G. [UNESP]Casaca, Wallace [UNESP]2023-07-29T11:59:52Z2023-07-29T11:59:52Z2023-03-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article19http://dx.doi.org/10.3390/su15064725Sustainability. Basel: Mdpi, v. 15, n. 6, 19 p., 2023.http://hdl.handle.net/11449/24560610.3390/su15064725WOS:000959505400001Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengSustainabilityinfo:eu-repo/semantics/openAccess2024-06-18T18:18:17Zoai:repositorio.unesp.br:11449/245606Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:42:53.021981Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
title Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
spellingShingle Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
Gino, Vinicius L. S. [UNESP]
anomaly detection
time series
landscape dynamics
framework
title_short Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
title_full Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
title_fullStr Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
title_full_unstemmed Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
title_sort Integrating Unsupervised Machine Intelligence and Anomaly Detection for Spatio-Temporal Dynamic Mapping Using Remote Sensing Image Series
author Gino, Vinicius L. S. [UNESP]
author_facet Gino, Vinicius L. S. [UNESP]
Negri, Rogerio G. [UNESP]
Souza, Felipe N. [UNESP]
Silva, Erivaldo A. [UNESP]
Bressane, Adriano [UNESP]
Mendes, Tatiana S. G. [UNESP]
Casaca, Wallace [UNESP]
author_role author
author2 Negri, Rogerio G. [UNESP]
Souza, Felipe N. [UNESP]
Silva, Erivaldo A. [UNESP]
Bressane, Adriano [UNESP]
Mendes, Tatiana S. G. [UNESP]
Casaca, Wallace [UNESP]
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (UNESP)
dc.contributor.author.fl_str_mv Gino, Vinicius L. S. [UNESP]
Negri, Rogerio G. [UNESP]
Souza, Felipe N. [UNESP]
Silva, Erivaldo A. [UNESP]
Bressane, Adriano [UNESP]
Mendes, Tatiana S. G. [UNESP]
Casaca, Wallace [UNESP]
dc.subject.por.fl_str_mv anomaly detection
time series
landscape dynamics
framework
topic anomaly detection
time series
landscape dynamics
framework
description The synergistic use of remote sensing and unsupervised machine learning has emerged as a potential tool for addressing a variety of environmental monitoring applications, such as detecting disaster-affected areas and deforestation. This paper proposes a new machine-intelligent approach to detecting and characterizing spatio-temporal changes on the Earth's surface by using remote sensing data and unsupervised learning. Our framework was designed to be fully automatic by integrating unsupervised anomaly detection models, remote sensing image series, and open data extracted from the Google Earth Engine platform. The methodology was evaluated by taking both simulated and real-world environmental data acquired from several imaging sensors, including Landsat-8 OLI, Sentinel-2 MSI, and Terra MODIS. The experimental results were measured with the kappa and F1-score metrics, and they indicated an assertiveness level of 0.85 for the change detection task, demonstrating the accuracy and robustness of the proposed approach when addressing distinct environmental monitoring applications, including the detection of disaster-affected areas and deforestation mapping.
publishDate 2023
dc.date.none.fl_str_mv 2023-07-29T11:59:52Z
2023-07-29T11:59:52Z
2023-03-01
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/10.3390/su15064725
Sustainability. Basel: Mdpi, v. 15, n. 6, 19 p., 2023.
http://hdl.handle.net/11449/245606
10.3390/su15064725
WOS:000959505400001
url http://dx.doi.org/10.3390/su15064725
http://hdl.handle.net/11449/245606
identifier_str_mv Sustainability. Basel: Mdpi, v. 15, n. 6, 19 p., 2023.
10.3390/su15064725
WOS:000959505400001
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Sustainability
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 19
dc.publisher.none.fl_str_mv Mdpi
publisher.none.fl_str_mv Mdpi
dc.source.none.fl_str_mv Web of Science
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_ 1808129453789806592