Land use classification from Sentinel-2 imagery


  • J. Borràs Universitat de València
  • J. Delegido Universitat de València
  • A. Pezzola Instituto Nacional de Tecnología Agropecuaria
  • M. Pereira-Sandoval Universitat de València
  • G. Morassi Universitat de València
  • G. Camps-Valls Universitat de València



classification, remote sensing, land use, Kappa Index, Sentinel-2


Sentinel-2 (S2), a new ESA satellite for Earth observation, accounts with 13 bands which provide high-quality radiometric images with an excellent spatial resolution (10 and 20 m) ideal for classification purposes. In this paper, two objectives have been addressed: to determine the best classification method for S2, and to quantify its improvement with respect to the SPOT operational mission. To do so, four classifiers (LDA, RF, Decision Trees, K-NN) have been selected and applied to two different agricultural areas located in Valencia (Spain) and Buenos Aires (Argentina). All classifiers were tested using, on the one hand, all the S2 bands and, on the other hand, only selecting those bands from S2 closer to the four bands from SPOT. In all the cases, between 10%-50% of samples were used to train the classifier while remaining the rest for validation. As a result, a land use map was generated from the best classifier, according to the Kappa index, providing scientifically relevant information such as the area of each land use class.


Download data is not yet available.

Author Biographies

J. Borràs, Universitat de València

Laboratorio de Procesado de Imágenes

J. Delegido, Universitat de València

Laboratorio de Procesado de Imágenes

A. Pezzola, Instituto Nacional de Tecnología Agropecuaria

Estación Experimental Hilario Ascasubi. Laboratorio de Teledetección y SIG

M. Pereira-Sandoval, Universitat de València

Laboratorio de Procesado de Imágenes

G. Morassi, Universitat de València

Laboratorio de Procesado de Imágenes

G. Camps-Valls, Universitat de València

Laboratorio de Procesado de Imágenes


Abraira, V. 2001. El índice kappa. Semergen, 27(5), 247-249. 3593(01)73955-X

Breiman, L. 1984. Classification and regression trees. Chapman & Hall/CRC. Breiman, L. 2001. Random forests. Machine Learning, 45(1), 5-32. https://doi. org/10.1023/A:1010933404324

Camps-Valls, G., Gómez Chova, L., Muñoz Marí, J., Rojo Álvarez, J.L., Martínez-Ramón, M. 2008. Kernel based framework for muli-temporal and multi-source remote sensing data classification and change detection. IEEE Trans. Geosc. Rem. Sens., 46(6), 1822-1835. TGRS.2008.916201

Camps-Valls, G., Tuia, D., Gómez-Chova, L., Jiménez, S., Malo, J. 2011. Remote Sensing Image Processing. Synthesis Lectures on Image, Video, and Multimedia Processing, 5(1), 1-192. S00392ED1V01Y201107IVM012

Cohen J. A. 1960. Coefficient of agreement for nominal scales. Educ. Psychol. Meas., 20(1), 37-46. https://

Comber, A., Fisher, P., Wadsworth, R. 2005. You know what land cover is but does anyone else? ... an investigation into semantic and ontological confusion. International Journal of Remote Sensing, 26(1), 223- 228.

Del Bosque, I., Arozarena, A., Villa, G., Valcárcel, N., Porcuna, A. 2005. Creación de un sistema de información geográfico de ocupación del suelo en España."Proyecto SIOSE". Actas del XI Congreso Nacional de Teledetección, 21-23 Septiembre, Puerto de la Cruz, España, 255-262.

Delegido, J., Verrelst, J., Alonso, L., Moreno, J. 2011. Evaluation of Sentinel-2 Red-Edge Bands for Empirical Estimation of Green LAI and Chlorophyll Content. Sensors, 11, 7063-7081. https://doi. org/10.3390/s110707063

Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernández, V., Gascón, F., Hoersch, B., Isola, C., Laberinti, P., Martimort, P., Meygret, A., Spoto, F., Sy, O., Marchese, F., Bargellini, P. 2012. Sentinel-2:ESA’s Optical High-Resolution Mission for GMES Operational Services. Remote sensing of Environment, 120, 25-36. rse.2011.11.026

ESA. 2016. Consultado el 10 de julio de 2016.

Gislason, P.O., Benediktsson, J.A., Sveinsson, J.R. 2006. Random Forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300. https://

Hastie, T., Tibshirani, R., Friedman, J. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed.; Springer: New York, NY, USA. 84858-7

James, G., Witten, D., Hastie, T., Tibshiram, R. 2015. An Introduction to Statistical Learning with Applications in R. In Springer Texts in Statistics. Volume 103. 7138-7

Immitzer, M., Atzberger, C., Koukal, T. 2012. Tree species classification with Random Forest using very high spatial resolution 8-band WorldView-2 satellite data. Remote Sensing, 4, 2661-2693. https://

Landis, J.R., Koch, G.G. 1977. The measurement of observer agreement for categorical data. Biometrics, 33, 159-174.

López González, F.J., Crecente Maseda, R., Álvarez López, C.J. 2002. Los usos del suelo analizados mediante S.I.G. XIV Congreso de Ingeniería Gráfica. 5-7 Junio, Santander, España.

Manual de usuario de Sentinel 2-ESA. Julio 2015.

Martimort, P., Berger, M., Carnicero, B., Del Bello, U., Fernández, V., Gascón, F., et al. 2007. Sentinel-2: Optical high-resolution mission for GMES operational services. Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International, 131, 18-23. igarss.2007.4423394

Mena, A.J. 2014. Procesamiento de imágenes satelitales multiespectrales. Proyecto final de carrera, Facultad de Informática, Universidad del País Vasco.

Pezzola, A. 2014. Transformaciones territoriales producto del riego en el Valle Bonaerense del Río Colorado. Departamento de geografía y turismo, UNS, provincia de Buenos Aires.

Quinlan, J.R. 1993. Programs for Machine Learning. 1st ed. San Mateo, CA, Morgan.

Rees, G. 2005. The Remote Sensing Data Book. Cambridge University Press, 262 pp.

Rodríguez-Galiano, V., Chica-Rivas, M. 2012. Clasificación de imágenes de satélite mediante software libre: Nuevas tendencias en algoritmos de Inteligencia artificial. Departamento de Geodinámica, Universidad de Granada.





Research articles