Mostrar el registro sencillo del ítem
Land cover mapping of a tropical region by integrating multi-year data into an annual time series
dc.creator | Anaya J.A. | spa |
dc.creator | Colditz R.R. | spa |
dc.creator | Valencia G.M. | spa |
dc.date.accessioned | 2016-10-28T16:44:54Z | |
dc.date.available | 2016-10-28T16:44:54Z | |
dc.date.created | 2015 | |
dc.identifier.issn | 20724292 | |
dc.identifier.uri | http://hdl.handle.net/11407/2867 | |
dc.description.abstract | Generating 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.language.iso | eng | |
dc.publisher | MDPI AG | spa |
dc.relation.isversionof | http://www.mdpi.com/2072-4292/7/12/15833 | spa |
dc.source | Scopus | spa |
dc.subject | Land cover | spa |
dc.subject | Quality assessment | spa |
dc.subject | Time series | spa |
dc.subject | Tree classifiers | spa |
dc.title | Land cover mapping of a tropical region by integrating multi-year data into an annual time series | spa |
dc.type | Article | eng |
dc.rights.accessrights | info:eu-repo/semantics/restrictedAccess | |
dc.rights.accessrights | info:eu-repo/semantics/restrictedAccess | |
dc.contributor.affiliation | Facultad de Ingenierías, Universidad de Medellín, Carrera 87 Nro. 30-65, Medellín, Colombia | spa |
dc.contributor.affiliation | National Commission for the Knowledge and Use of Biodiversity (CONABIO), Av. Liga Periférico-Insurgentes Sur 4903, Parques del Pedregal, Tlalpan, Ciudad de México, DF, Mexico | spa |
dc.contributor.affiliation | Facultad de Ingenierías, Universidad de San Buenaventura, Carrera 56C Nro. 51-90, Medellín, Colombia | spa |
dc.identifier.doi | 10.3390/rs71215833 | |
dc.subject.keyword | Decision trees | eng |
dc.subject.keyword | Error statistics | eng |
dc.subject.keyword | Image reconstruction | eng |
dc.subject.keyword | Radiometers | eng |
dc.subject.keyword | Satellite imagery | eng |
dc.subject.keyword | Time series | eng |
dc.subject.keyword | Trees (mathematics) | eng |
dc.subject.keyword | Decision tree classification | eng |
dc.subject.keyword | High moisture contents | eng |
dc.subject.keyword | Integration approach | eng |
dc.subject.keyword | Land cover | eng |
dc.subject.keyword | Land cover classification | eng |
dc.subject.keyword | Moderate resolution imaging spectroradiometer | eng |
dc.subject.keyword | Quality assessment | eng |
dc.subject.keyword | Tree classifiers | eng |
dc.subject.keyword | Data integration | eng |
dc.relation.ispartofes | Remote Sensing | spa |
dc.type.driver | info:eu-repo/semantics/conferenceObject |
Ficheros en el ítem
Ficheros | Tamaño | Formato | Ver |
---|---|---|---|
No hay ficheros asociados a este ítem. |
Este ítem aparece en la(s) siguiente(s) colección(ones)
-
Indexados Scopus [1632]