Show simple item record

2021-11-03Zeitschriftenartikel DOI: 10.3390/app112110309
Integration of Sentinel-1 and Sentinel-2 Data with the G-SMOTE Technique for Boosting Land Cover Classification Accuracy
dc.contributor.authorEbrahimy, Hamid
dc.contributor.authorNaboureh, Amin
dc.contributor.authorFeizizadeh, Bakhtiar
dc.contributor.authorAryal, Jagannath
dc.contributor.authorGhorbanzadeh, Omid
dc.contributor.editorJung, Hyung-Sup
dc.date.accessioned2022-01-13T11:56:51Z
dc.date.available2022-01-13T11:56:51Z
dc.date.issued2021-11-03none
dc.date.updated2021-12-01T14:49:11Z
dc.identifier.urihttp://edoc.hu-berlin.de/18452/24561
dc.description.abstractThe importance of Land Cover (LC) classification is recognized by an increasing number of scholars who employ LC information in various applications (i.e., address global climate change and achieve sustainable development). However, studying the roles of balancing data, image integration, and performance of different machine learning algorithms in various landscapes has not received as much attention from scientists. Therefore, the present study investigates the performance of three frequently used Machine Learning (ML) algorithms, including Extreme Learning Machines (ELM), Support Vector Machines (SVM), and Random Forest (RF) in LC mapping at six different landscapes. Moreover, the Geometric Synthetic Minority Over-sampling Technique (G-SMOTE) was adopted to deal with the class imbalance problem. In this work, the time-series of Sentinel-1 and Sentinel-2 data were integrated to improve LC mapping accuracy, taking advantage of both data. Moreover, Support Vector Machine-Recursive Feature Elimination (SVM-RFE) was implemented to distinguish the most informative features. Based on the results, the RF integrated with G-SMOTE showed the best result for four landscapes (coastal, cropland, desert, and semi-arid). SVM integrated with G-SMOTE had the highest accuracy in the remaining two landscapes (plain and mountain). Applied ML algorithms showed good performances in various landscapes, ranging Overall Accuracy (OA) from 85% to 93% for RF, 83% to 94% for SVM, and 84% to 92% for ELM. The outcomes exhibit that although applying G-SMOTE may slightly decrease OA values, it generally boosts the results of LC classification accuracies in various landscapes, particularly for minority classes.eng
dc.language.isoengnone
dc.publisherHumboldt-Universität zu Berlin
dc.rights(CC BY 4.0) Attribution 4.0 Internationalger
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectMachine Learning (ML)eng
dc.subjectGeometric Synthetic Minority Over-Sampling Technique (G-SMOTE)eng
dc.subjectland cover mappingeng
dc.subjectEuropean Space Agency (ESA)eng
dc.subjectclass imbalance problemeng
dc.subject.ddc004 Informatiknone
dc.subject.ddc910 Geografie und Reisennone
dc.titleIntegration of Sentinel-1 and Sentinel-2 Data with the G-SMOTE Technique for Boosting Land Cover Classification Accuracynone
dc.typearticle
dc.identifier.urnurn:nbn:de:kobv:11-110-18452/24561-0
dc.identifier.doi10.3390/app112110309none
dc.identifier.doihttp://dx.doi.org/10.18452/23930
dc.type.versionpublishedVersionnone
local.edoc.container-titleApplied Sciences : open access journalnone
local.edoc.pages12none
local.edoc.type-nameZeitschriftenartikel
local.edoc.institutionMathematisch-Naturwissenschaftliche Fakultätnone
local.edoc.container-typeperiodical
local.edoc.container-type-nameZeitschrift
local.edoc.container-publisher-nameMDPInone
local.edoc.container-publisher-placeBaselnone
local.edoc.container-volume11none
local.edoc.container-issue21none
dc.description.versionPeer Reviewednone
local.edoc.container-articlenumber10309none
dc.identifier.eissn2076-3417

Show simple item record