Land use and land cover classification in the northern region of Mozambique based on Landsat time series and machine learning.

dc.contributorLUCRÊNCIO SILVESTRE MACARRINGUE, UNIVERSIDADE ESTADUAL DE CAMPINAS; EDSON LUIS BOLFE, CNPTIA, UNIVERSIDADE ESTADUAL DE CAMPINAS; SOLTAN GALANO DUVERGER, UNIVERSIDADE FEDERAL DA BAHIA; EDSON EYJI SANO, CPAC; MARCELLUS MARQUES CALDAS, KANSAS STATE UNIVERSITY; MARCOS CÉSAR FERREIRA, UNIVERSIDADE ESTADUAL DE CAMPINAS; JURANDIR ZULLO JUNIOR, UNIVERSIDADE ESTADUAL DE CAMPINAS; LINDON FONSECA MATIAS, UNIVERSIDADE ESTADUAL DE CAMPINAS.
dc.creatorMACARRINGUE, L. S.
dc.creatorBOLFE, E. L.
dc.creatorDUVERGER, S. G.
dc.creatorSANO, E. E.
dc.creatorCALDAS, M. M.
dc.creatorFERREIRA, M. C.
dc.creatorZULLO JUNIOR, J.
dc.creatorMATIAS, L. F.
dc.date2023-08-18T12:23:52Z
dc.date2023-08-18T12:23:52Z
dc.date2023-08-18
dc.date2023
dc.date.accessioned2023-09-05T03:06:08Z
dc.date.available2023-09-05T03:06:08Z
dc.identifierISPRS International Journal of Geo-Information, v. 12, n. 8, 342, Aug. 2023.
dc.identifier2220-9964
dc.identifierhttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1155979
dc.identifierhttps://doi.org/10.3390/ijgi12080342
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8638494
dc.descriptionAccurate land use and land cover (LULC) mapping is essential for scientific and decision-making purposes. The objective of this paper was to map LULC classes in the northern region of Mozambique between 2011 and 2020 based on Landsat time series processed by the Random Forest classifier in the Google Earth Engine platform. The feature selection method was used to reduce redundant data. The final maps comprised five LULC classes (non-vegetated areas, built-up areas, croplands, open evergreen and deciduous forests, and dense vegetation) with an overall accuracy ranging from 80.5% to 88.7%. LULC change detection between 2011 and 2020 revealed that non-vegetated areas had increased by 0.7%, built-up by 2.0%, and dense vegetation by 1.3%. On the other hand, open evergreen and deciduous forests had decreased by 4.1% and croplands by 0.01%. The approach used in this paper improves the current systematic mapping approach in Mozambique by minimizing the methodological gaps and reducing the temporal amplitude, thus supporting regional territorial development policies.
dc.languageIngles
dc.languageen
dc.rightsopenAccess
dc.subjectCobertura da terra
dc.subjectFloresta aleatória
dc.subjectSéries temporais
dc.subjectAprendizado de máquina
dc.subjectGoogle Earth Engine
dc.subjectFeature selection
dc.subjectMiombo
dc.subjectRandom forest
dc.subjectMachine learning
dc.subjectDesmatamento
dc.subjectUso da Terra
dc.subjectDeforestation
dc.subjectLand use
dc.subjectLand cover
dc.titleLand use and land cover classification in the northern region of Mozambique based on Landsat time series and machine learning.
dc.typeArtigo de periódico


Este ítem pertenece a la siguiente institución