Publicado

2020-11-05

Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia)

Clasificación de la cobertura del suelo en tres niveles de detalle diferentes a partir de datos ópticos y de radar SAR Sentinel: un estudio de caso en Cundinamarca (Colombia)

DOI:

https://doi.org/10.15446/dyna.v87n215.84915

Palabras clave:

Sentinel-1A, Sentinel-2A, Land Cover Classification, Random Forest, Object-based Analysis (en)
Sentinel-1A; Sentinel-2A; clasificación de coberturas; bosques aleatorios; análisis basado en objetos (es)

Autores/as

In this paper, the potential of Sentinel-1A and Sentinel-2A satellite images for land cover mapping is evaluated at three levels of spatial detail; exploratory, reconnaissance, and semi-detailed. To do so, two different image classification approaches are compared: (i) a traditional pixel-wise approach; and (ii) an object–oriented approach. In both cases, the classification task was conducted using the “RandomForest” algorithm. The case study was also intended to identify a set of radar channels, optical bands, and indices that are relevant for classification. The thematic accuracy of the classifications displays the best results for the object-oriented approach to exploratory and recognition levels. The results show that the integration of multispectral and radar data as explanatory variables for classification provides better results than the use of a single data source.

En este documento, se evalúa el potencial de las imágenes satelitales Sentinel-1A y Sentinel-2A para el mapeo de la cobertura del suelo en tres niveles de detalle; exploratorio, reconocimiento y semi-detallado. Se compara el rendimiento de dos enfoques diferentes de clasificación de imágenes: (i) un enfoque tradicional basado en píxeles; y (ii) un enfoque orientado a objetos. En ambos casos, el proceso de clasificación se realizó utilizando el algoritmo “RandomForest”. El estudio también aborda la identificación de un conjunto de canales de radar, bandas ópticas e índices relevantes para la clasificación. La exactitud temática de las clasificaciones, muestra los mejores resultados en el enfoque orientado a objetos para los niveles de exploración y reconocimiento. Los resultados muestran que la integración de datos multiespectrales y de radar como variables explicativas para la clasificación proporciona mejores resultados que el uso de una única fuente de datos.

Referencias

Giles-M .F., Status of land cover classification accuracy assessment. Remote Sensing of Environment 80(1), pp. 185-201, 2002. DOI: 10.1016/S0034-4257(01)00295-4

Ullmann, T., Schmitt, A., Roth, A., Duffe, J., Dech, S., Hubberten, H. W. and Baumhauer, R., Land cover characterization and classification of arctic tundra environments by means of polarized synthetic aperture X-and C-Band Radar (PolSAR) and Landsat 8, 2014. DOI: 10.3390/rs6098565

Falcucci, A., Maiorano, L. and Boitani, L., Changes in land-use/land-cover patterns in Italy and their implications for biodiversity conservation. Landscape ecology, 22(4), pp. 617-631, 2007. DOI: 10.1007/s10980-006-9056-4

Van der Sande, C.J., de Jong, S.M. and de Roo, A.P.J., A segmentation and classification approach of IKONOS-2 imagery for land cover mapping to assist flood risk and flood damage assessment, International Journal of Applied Earth Observation and Geoinformation, 4(3), pp. 217-229, 2003.DOI: 10.1016/S0303-2434(03)00003-5

Heymann, Y., Steenmans, C., Croisille, G. and Bossard, M., Corine land cover project-technical guide. European Commission, Directorate General Environment. Nuclear safety and civil protection, ECSC-EEC-EAEC, Brussels-Luxembourg, 1994, 136 P.

Bossard, M., Feranec, J. and Otahel, J., Corine land cover technical guide: Addendum, 2000.

Bussay, A., Tóth, T., Juškevičius, V. and Seguini, L., Evaluation of aridity indices using SPOT normalized difference vegetation index values calculated over different time frames on Iberian rain-fed arable land. Arid Land Research and Management, 26(4), pp. 271-284, 2012. DOI: 10.1080/15324982.2012.694398

IDEAM, IGAC y CORMAGDALENA., Mapa de cobertura de la tierra Cuenca Magdalena-Cauca: metodología CORINE Land Cover adaptada para Colombia a escala 1:100.000. Instituto de Hidrología, Meteorología y Estudios Ambientales, Instituto Geográfico Agustín Codazzi y Corporación Autónoma Regional del río Grande de La Magdalena. Bogotá, D.C., 2008, 200 P. + 164 hojas cartográficas.

IGAC y CORPORACION AUTONOMA REGIONAL DEL QUINDIO. Instituto Geográfico Agustín Codazzi. Coberturas y usos de la tierra del Departamento del Quindío Escala 1:10000. 2010.

Guzmán, I.D.G., Posada, E., Duarte, L.P.A. and García, J.E., Descripción del programa de investigación en desarrollo satelital y aplicaciones en el tema de observación de la tierra. Comisión Colombiana del Espacio–CCE Grupo de Observación de la Tierra, 4, 2010.

Beaulieu, N., Hill, P., Leclerc, G. y Escobar, G., Cartografía de la cobertura de la tierra en el municipio de Puerto López, Colombia, utilizando imágenes de RADARSAT-1 y de JERS-1. En Memoria del Simposio final GlobeSAR, Vol. 2, 1999, pp. 17-20.

Niu, X. and Ban, Y., Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach. International Journal of Remote Sensing, 34(1), pp. 1-26, 2013. DOI: 10.1080/01431161.2012.700133

Balzter, H., Cole, B., Thiel, C. and Schmullius, C., Mapping CORINE land cover from Sentinel-1A SAR and SRTM digital elevation model data using Random Forests. Remote Sensing, 7(11), pp. 14876-14898, 2015. DOI: 10.3390/rs71114876

Abdikan, S., Sanli, F.B., Ustuner, M. and Calò, F., Land cover mapping using SENTINEL-1 SAR data. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, pp. 757-761. DOI: 10.5194/isprsarchives-XLI-B7-757-2016

Addink, E.A., Van Coillie, F.M. and De Jong, S.M., Introduction to the GEOBIA 2010 special issue: from pixels to geographic objects in remote sensing image analysis. International Journal of Applied Earth Observation and Geoinformation, 15, pp. 1-6, 2012. DOI: 10.1016/j.jag.2011.12.001

Eastman, J.R. IDRISI Selva manual. Clark University. Worcester, Massachusetts, USA, [online]. 2012. Available at: https://scholar.google.com/scholar_lookup?title=IDRISI+Selva+Manual&author=Eastman,+J.R.&publication_year=2012

Hay, G.J. and Castilla, G., Geographic object-based image analysis (GEOBIA): a new name for a new discipline. In: Object-based image analysis. Springer, Berlin Heidelberg, 2008, pp. 75-89. DOI: 10.1007/978-3-540-77058-9_4

Lizarazo, I. and Elsner, P., Fuzzy regions for handling uncertainty in remote sensing image segmentation. In: International Conference on Computational Science and Its Applications. Springer, Berlin, Heidelberg, 2008, pp. 724-739. DOI: 10.1007/978-3-540-69839-5_53

UEGPS. Metodología para clasificación de coberturas a partir del procesamiento de imágenes satelitales. Unidad Ejecutora Gestión de Proyectos Sectoriales. Ministerio de Agricultura y Riego. Lima-Perú, 2018.

Gao, Y and Jf Mas., A comparison of the performance of pixel based and object based classifications over images with various spatial resolutions. Online Journal of Earth Sciences 2(8701), pp. 27-35,2008.

Perea, A.J., Meroño, J.E. and Aguilera, M.J., Object-based classification in aereal digital photography for land-use discrimination. Interciencia, 34(9), pp. 612-616, 2009.

Rodríguez, A., Metodología para detectar cambios en el uso de la tierra utilizando los principios de la clasificación orientada a objetos, estudio de caso piedemonte de Villavicencio, Meta, Tesis de Maestría. Facultad de Ingeniería Agronómica. Universidad Nacional de Colombia, Bogotá D.C., Colombia, 2011.

Breiman, L., Random forests. Machine learning, 45(1), pp. 5-32, 2001. DOI: 10.1023/A:1010933404324

Pal, M., Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), pp. 217-222, 2005. DOI: 10.1080/01431160412331269698

Prasad, A.M., Iverson, L.R. and Liaw, A., Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems, 9, pp. 181-199, 2006. DOI: 10.1007/s10021-005-0054-1

Urrea-Gales, V., Detección de interacciones genéticas asociadas a enfermedades complejas. Aplicación al cáncer de vejiga. Tesis de Maestría. Departamento de Estadística en Investigación Operativa Universidad Politécnica de Cataluña, Barcelona, España, 2009.

Liaw, A. and Wiener, M., Classification and regression by Random Forest. R news, 2(3), pp. 18-22, 2002.

Lawrence, R.L., Wood, S.D. and Sheley, R.L., Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest). Remote Sensing of Environment, 100(3), pp. 356-362, 2006. DOI: 10.1016/j.rse.2005.10.014

Van der Meer, F.D., Van der Werff, H.M.A. and Van Ruitenbeek, F.J.A., Potential of ESA's Sentinel-2 for geological applications. Remote Sensing of Environment, 148, pp. 124-133, 2014. DOI: 10.1016/j.rse.2014.03.022

Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez, V., Gascon, F. and Meygret, A., Sentinel-2: ESA's optical high-resolution mission for GMES operational services. Remote Sensing of Environment, 120, pp. 25-36, 2012. DOI: 10.1016/j.rse.2011.11.026

ESA. Sentinel-1 User Handbook, September 2013: ESA User Guide, GMES-S1OP-EOPG-TN-13-0001. European Space Agency, Paris, France, 2013, 80 P.

Mbulisi, S, Mutanga, O. and Rouget M., Examining the potential of Sentinel-2 MSI spectral resolution in quantifying above ground biomass across different fertilizer treatments. ISPRS Journal of Photogrammetry and Remote Sensing 110, pp. 55-65, 2015. DOI: 10.1016/j.isprsjprs.2015.10.005

Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D. and Moore, R., Google Earth Engine: planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, pp. 18-27, 2017. DOI: 10.1016/j.rse.2017.06.031

Rouse, J.W. Jr., Haas, R.H., Deering, D.W., Schell, J.A., and Harlan, J.C., Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation. NASA/GSFC Type III Final Report, Greenbelt, MD., 1974, 371 P.

Huete, A., Didan, K., Miura, T., Rodriguez, E.P., Gao, X. and Ferreira, L.G., Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, 83(1-2), pp. 195-213, 2002. DOI: 10.1016/S0034-4257(02)00096-2

Huete, A., Justice, C. and Liu, H., Development of vegetation and soil indices for MODIS-EOS. Remote Sensing of Environment, 49(3), pp. 224-234, 1994. DOI: 10.1016/0034-4257(94)90018-3

Huete, A.R., Liu, H.Q., Batchily, K.V. and Van Leeuwen, W.J.D.A., A comparison of vegetation indices over a global set of TM images for EOS-MODIS. Remote Sensing of Environment, 59(3), pp. 440-451, 1997. DOI: 10.1016/S0034-4257(96)00112-5

Cánovas-García, F., Análisis de imágenes basado en objetos (OBIA) y aprendizaje automático para la obtención de mapas de coberturas del suelo a partir de imágenes de muy alta resolución espacial: aplicación en la Unidad de Demanda Agraria nº 28, cabecera del Argos. Tesis Dr. Departamento de Geografía. Universidad de Murcia. Murcia, España. 2012.

Breiman, L., Random Forest: Breiman and Cutler’s Random Forests for classification and regression. R package version 4.6-12, 2006. Software available at URL: https://cran. rproject. org/web/packages/randomForest [40] Gounaridis, D. and Koukoulas, S., Urban land cover thematic disaggregation, employing datasets from multiple sources and Random Forests modeling. International Journal of Applied Earth Observation and Geoinformation, 51, pp. 1-10, 2016. DOI: 10.1016/j.jag.2016.04.002

Lizarazo, I. and Elsner, P., Segmentation of remotely sensed imagery: moving from sharp objects to fuzzy regions. Image Segmentation, 2011. DOI: 10.5772/15421

Blaschke, T., Burnett, C. and Pekkarinen, A., Image segmentation methods for object-based analysis and classification, in: de Jong, S. and van derMeer, F. (eds), Remote sensing image analysis: including the spatial domain, Springer, 2006, pp. 211-236. DOI: 10.1007/1-4020-2560-2_12

Lang, S., Albretch, F. and Blaschke, T., Tutorial: introduction to object-based image analysis, Centre for Geoinformatics - Z-GIS, 2006.

Platt, R.V. and Rapoza, L., An evaluation of an object-oriented paradigm for land use/land cover classification, The Professional Geographer 60(1), pp. 87-100, 2008. DOI: 10.1080/00330120701724152

Vargas-Ulate, G., Cartografía fitogeográfica de la Reserva Biológica de Carara, San José, Costa Rica. Editorial de la Universidad de Costa Rica, 1992, 49 P.

Cerda, J. y Villarroel, L., Evaluación de la concordancia inter-observador en investigación pediátrica: coeficiente de Kappa. Revista Chilena de Pediatría, 79(1), pp. 54-58, 2008. DOI: 10.4067/S0370-41062008000100008

Cómo citar

IEEE

[1]
J. R. Mancera Florez y I. A. Lizarazo Salcedo, «Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia)», DYNA, vol. 87, n.º 215, pp. 136–145, nov. 2020.

ACM

[1]
Mancera Florez, J.R. y Lizarazo Salcedo, I.A. 2020. Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia). DYNA. 87, 215 (nov. 2020), 136–145. DOI:https://doi.org/10.15446/dyna.v87n215.84915.

ACS

(1)
Mancera Florez, J. R.; Lizarazo Salcedo, I. A. Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia). DYNA 2020, 87, 136-145.

APA

Mancera Florez, J. R. & Lizarazo Salcedo, I. A. (2020). Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia). DYNA, 87(215), 136–145. https://doi.org/10.15446/dyna.v87n215.84915

ABNT

MANCERA FLOREZ, J. R.; LIZARAZO SALCEDO, I. A. Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia). DYNA, [S. l.], v. 87, n. 215, p. 136–145, 2020. DOI: 10.15446/dyna.v87n215.84915. Disponível em: https://revistas.unal.edu.co/index.php/dyna/article/view/84915. Acesso em: 14 mar. 2026.

Chicago

Mancera Florez, Juan Ricardo, y Ivan Alberto Lizarazo Salcedo. 2020. «Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia)». DYNA 87 (215):136-45. https://doi.org/10.15446/dyna.v87n215.84915.

Harvard

Mancera Florez, J. R. y Lizarazo Salcedo, I. A. (2020) «Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia)», DYNA, 87(215), pp. 136–145. doi: 10.15446/dyna.v87n215.84915.

MLA

Mancera Florez, J. R., y I. A. Lizarazo Salcedo. «Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia)». DYNA, vol. 87, n.º 215, noviembre de 2020, pp. 136-45, doi:10.15446/dyna.v87n215.84915.

Turabian

Mancera Florez, Juan Ricardo, y Ivan Alberto Lizarazo Salcedo. «Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia)». DYNA 87, no. 215 (noviembre 5, 2020): 136–145. Accedido marzo 14, 2026. https://revistas.unal.edu.co/index.php/dyna/article/view/84915.

Vancouver

1.
Mancera Florez JR, Lizarazo Salcedo IA. Land cover classification at three different levels of detail from optical and radar Sentinel SAR data: a case study in Cundinamarca (Colombia). DYNA [Internet]. 5 de noviembre de 2020 [citado 14 de marzo de 2026];87(215):136-45. Disponible en: https://revistas.unal.edu.co/index.php/dyna/article/view/84915

Descargar cita

CrossRef Cited-by

CrossRef citations3

1. Ying Li, Guolong Shi. (2021). Monitoring and Mathematical Model Analysis of Dynamic Changes in Land Resources Based on SAR Sensor Image. Journal of Sensors, 2021(1) https://doi.org/10.1155/2021/1661825.

2. Mohammed Abdulmajeed Moharram, Divya Meena Sundaram. (2023). Land use and land cover classification with hyperspectral data: A comprehensive review of methods, challenges and future directions. Neurocomputing, 536, p.90. https://doi.org/10.1016/j.neucom.2023.03.025.

3. William Martínez, Ivan Lizarazo, André Große-Stoltenberg. (2025). Integration of InSAR coherence and SAR backscatter increases accuracy of LULC mapping in tropical high-mountain ecosystems. Geocarto International, 40(1) https://doi.org/10.1080/10106049.2025.2451174.

Dimensions

PlumX

Visitas a la página del resumen del artículo

1939

Descargas

Los datos de descargas todavía no están disponibles.