Show simple item record

dc.description.abstractGenerating annual land cover maps in the tropics based on optical data is challenging because of the large amount of invalid observations resulting from the presence of clouds and haze or high moisture content in the atmosphere. This study proposes a strategy to build an annual time series from multi-year data to fill data gaps. The approach was tested using the Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation index and spectral bands as input for land cover classification of Colombia. In a second step, selected ancillary variables, such as elevation, L-band Radar, and precipitation were added to improve overall accuracy. Decision-tree classification was used for assigning eleven land cover classes using the International Geosphere-Biosphere Programme (IGBP) legend. Maps were assessed by their spatial confidence derived from the decision tree approach and conventional accuracy measures using reference data and statistics based on the error matrix. The multi-year data integration approach drastically decreased the area covered by invalid pixels. Overall accuracy of land cover maps significantly increased from 58.36% using only optical time series of 2011 filtered for low quality observations, to 68.79% when using data for 2011 ± 2 years. Adding elevation to the feature set resulted in 70.50% accuracy.eng
dc.publisherMDPI AGspa
dc.subjectLand coverspa
dc.subjectQuality assessmentspa
dc.subjectTime seriesspa
dc.subjectTree classifiersspa
dc.titleLand cover mapping of a tropical region by integrating multi-year data into an annual time seriesspa
dc.contributor.affiliationFacultad de Ingenierías, Universidad de Medellín, Carrera 87 Nro. 30-65, Medellín, Colombiaspa
dc.contributor.affiliationNational Commission for the Knowledge and Use of Biodiversity (CONABIO), Av. Liga Periférico-Insurgentes Sur 4903, Parques del Pedregal, Tlalpan, Ciudad de México, DF, Mexicospa
dc.contributor.affiliationFacultad de Ingenierías, Universidad de San Buenaventura, Carrera 56C Nro. 51-90, Medellín, Colombiaspa
dc.subject.keywordDecision treeseng
dc.subject.keywordError statisticseng
dc.subject.keywordImage reconstructioneng
dc.subject.keywordSatellite imageryeng
dc.subject.keywordTime serieseng
dc.subject.keywordTrees (mathematics)eng
dc.subject.keywordDecision tree classificationeng
dc.subject.keywordHigh moisture contentseng
dc.subject.keywordIntegration approacheng
dc.subject.keywordLand covereng
dc.subject.keywordLand cover classificationeng
dc.subject.keywordModerate resolution imaging spectroradiometereng
dc.subject.keywordQuality assessmenteng
dc.subject.keywordTree classifierseng
dc.subject.keywordData integrationeng
dc.relation.ispartofesRemote Sensingspa

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record