Land cover classification with spatial resolution of 10 meters in forests of the Colombian Caribbean based on Sentinel 1 and 2 missions




Sentinel, bands selection, Google Earth Engine, classification accuracy, dry forest, Colombia


A Land cover map of the Colombian Caribbean were generated with data from the Sentinel-1 and Sentinel-2 missions for the year 2020. The main objective was to evaluate Sentinel 1 and 2 images to generate a classification for Caribbean forests. The images were processed using Google Earth Engine (GEE) and then classified using Random Forest. The Overall Accuracy, the Mean Decrease Accuracy and the Mean Decrease in Gini were calculated for the optical and radar bands, this allowed evaluating the importance of different regions of the electromagnetic spectrum in the classification of vegetation cover and the relative importance of the spectral bands. The accuracy of the land cover map was 76% using exclusively Sentinel-2 bands, with a slight increase when Sentinel-1 data was incorporated. The SWIR region was the most important of both Sentinel programs for increasing accuracy. We highlight the importance of coastal aerosol band 1 (442.7 nm) in the classification despite its low spatial resolution. The overall accuracy reached 83% when adding the Elevation data from the Shuttle Radar Topography Mission (SRTM) as auxiliary variable. These results indicate great potential for the generation of vegetation cover maps at the regional level while maintaining a pixel size of 10 m. This article highlights the relative importance of the different bands and its contribution to improve accuracy.


Download data is not yet available.

Author Biographies

Jesús A. Anaya, Universidad de Medellín

Facultad de ingeniería

Susana Rodríguez-Buriticá, Instituto de Investigaciones de Recursos Biológicos Alexander von Humboldt

Coordinator of the spatial ecology group/Biodiversity Sciences program

María C. Londoño, Instituto de Investigaciones de Recursos Biológicos Alexander von Humboldt

Coordinación del Laboratorio de Biogeografía Aplicada y Bioacústica


Achard, F., y Hansen, M.C. 2013. Global forest monitoring from earth observation (E. Chuvieco, Ed.; p. 316). CRC Press, Taylor y Francis Group.

Anaya, J.A., Colditz, R.R., y Valencia, G.M. 2015. Land cover mapping of a tropical region by integrating multi-year data into an annual time series. Remote Sensing, 7(12).

Anaya, J.A., Gutiérrez-Vélez, V.H., Pacheco-Pascagaza, A.M., Palomino-Ángel, S., Han, N., y Balzter, H. 2020. Drivers of Forest Loss in a Megadiverse Hotspot on the Pacific Coast of Colombia. Remote Sensing, 12(8), 1235.

Andrade, J., Cunha, J., Silva, J., Rufino, I., y Galvão, C. 2021. Evaluating single and multidate Landsat classifications of land-cover in a seasonally dry tropical forest. Remote Sensing Applications: Society and Environment, 22, 100515.

Arias, M., Campo-Bescós, M.Á., y Álvarez-Mozos, J. 2020. Crop Classification Based on Temporal Signatures of Sentinel-1 Observations over Navarre Province, Spain. In Remote Sensing, 12(2), 278.

Barlow, J., Lennox, G.D., Ferreira, J., Berenguer, E., Lees, A.C., Nally, R. mac, Thomson, J.R., Ferraz, S.F. de B., Louzada, J., Oliveira, V.H.F., Parry, L., Ribeiro de Castro Solar, R., Vieira, I.C.G., Aragão, L.E.O.C., Begotti, R.A., Braga, R.F., Cardoso, T.M., Jr, R.C. de O., Souza Jr, C.M., … Gardner, T.A. 2016. Anthropogenic disturbance in tropical forests can double biodiversity loss from deforestation. Nature, 535(7610), 144-147.

Bastin, J.-F., Berrahmouni, N., Grainger, A., Maniatis, D., Mollicone, D., Moore, R., Patriarca, C., Picard, N., Sparrow, B., Abraham, E.M., Aloui, K., Atesoglu, A., Attore, F., Bassüllü, Ç., Bey, A., Garzuglia, M., García-Montero, L.G., Groot, N., Guerin, G., … Castro, R. 2017. The extent of forest in dryland biomes. Science, 356(6338), 635 LP - 638.

Breiman, L. 2001. Random Forests. Machine Learning, 45(1), 5-32.

Campos-Taberner, M., García-Haro, F.J., Martínez, B., y Gilabert, M.A. 2020. Deep learning for agricultural land use classification from sentinel-2. Revista de Teledeteccion, 2020(56 Special issue), 35-48.

Cartus, O., Kellndorfer, J., Walker, W., Franco, C., Bishop, J., Santos, L., y Fuentes, J.M.M. 2014. A national, detailed map of forest aboveground carbon stocks in Mexico. Remote Sensing, 6, 5559-5588.

Cavalcante, R.B.L., Ferreira, D.B. da S., Pontes, P.R.M., Tedeschi, R.G., da Costa, C.P.W., y de Souza, E.B. 2020. Evaluation of extreme rainfall indices from CHIRPS precipitation estimates over the Brazilian Amazonia. Atmospheric Research, 238, 104879.

Chastain, R., Housman, I., Goldstein, J., Finco, M., y Tenneson, K. 2019. Empirical cross sensor comparison of Sentinel-2A and 2B MSI, Landsat-8 OLI, and Landsat-7 ETM+ top of atmosphere spectral characteristics over the conterminous United States. Remote Sensing of Environment, 221, 274-285.

Chazdon, R.L., Brancalion, P.H.S., Laestadius, L., Bennett-Curry, A., Buckingham, K., Kumar, C., Moll-Rocek, J., Vieira, I.C.G., y Wilson, S.J. 2016. When is a forest a forest? Forest concepts and definitions in the era of forest and landscape restoration. Ambio, 45(5), 538-550.

Chen, B., Li, X., Xiao, X., Zhao, B., Dong, J., Kou, W., Qin, Y., Yang, C., Wu, Z., Sun, R., Lan, G., y Xie, G. 2016. Mapping tropical forests and deciduous rubber plantations in Hainan Island, China by integrating PALSAR 25-m and multi-temporal Landsat images. International Journal of Applied Earth Observation and Geoinformation, 50, 117-130.

Congalton, R.G., y Green, Kass. 2009. Assessing the accuracy of remotely sensed data (2nd ed.). CRC Press.

Correa-Ayram, C.A., Etter, A., Díaz-Timoté, J., Rodríguez-Buriticá, S., Ramírez, W., y Corzo, G. 2020. Spatiotemporal evaluation of the human footprint in Colombia: Four decades of anthropic impact in highly biodiverse ecosystems. Ecological Indicators, 117, 106630.

Descals, A., Wich, S., Meijaard, E., Gaveau, D.L.A., Peedell, S., y Szantoi, Z. 2021. High-resolution global map of smallholder and industrial closedcanopy oil palm plantations. Earth Syst. Sci. Data, 13(3), 1211-1231.

Fagan, M.E. 2020. A lesson unlearned? Underestimating tree cover in drylands biases global restoration maps. Global Change Biology, 26(9), 4679-4690.

Hansen, M.C., Krylov, A., Tyukavina, A., Potapov, P. v, Turubanova, S., Zutta, B., Ifo, S., Margono, B., Stolle, F., y Moore, R. 2016. Humid tropical forest disturbance alerts using Landsat data. Environmental Research Letters, 11(3), 34008.

Himeur, Y., Rimal, B., Tiwary, A., y Amira, A. 2022. Using artificial intelligence and data fusion for environmental monitoring: A review and future perspectives. Information Fusion, 86-87, 44-75.

Hong, D., Hu, J., Yao, J., Chanussot, J., y Zhu, X.X. 2021. Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning model. ISPRS Journal of Photogrammetry and Remote Sensing, 178, 68-80.

IAvH, y MADS. 2014. Mapa de coberturas de bosque seco tropical en Colombia (escala 1:100.000, 2.0v). 1 hoja cartográfica.

IDEAM. 2010. Leyenda Nacional de Coberturas de la Tierra. Metodología CORINE Land Cover adaptada para Colombia Escala 1:100.000. (M. y E. Ambientales. Instituto de Hidrología, Ed.; p. 72).

IDEAM. 2016. Mapa de Bosque No Bosque Colombia Área Continental (p. Landsat).

Jin, H., y Mountrakis, G. 2022. Fusion of optical, radar and waveform LiDAR observations for land cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 187, 171-190.

Kellndorfer, J., Walker, W., Pierce, L., Dobson, C., Fites, J.A., Hunsaker, C., Vona, J., y Clutter, M. 2004. Vegetation height estimation from Shuttle Radar Topography Mission and National Elevation datasets. Remote Sensing of Environment, 93, 339-358.

Lapini, A., Fontanelli, G., Pettinato, S., Santi, E., Paloscia, S., Tapete, D., y Cigna, F. 2020. Application of deep learning to optical and SAR images for the classification of agricultural areas in Italy. IEEE Geoscience and Remote Sensing Letters, 4163-4166.

Lillesand, T.M., y Kiefer, R.W. 2000. Remote sensing and image interpretation (J.W. and Sons, Ed.; Fourth). Wiley.

Miles, L., Newton, A.C., DeFries, R.S., Ravilious, C., May, I., Blyth, S., Kapos, V., y Gordon, J.E. 2006. A global overview of the conservation status of tropical dry forests. Journal of Biogeography, 33(3), 491-505.

Mullissa, A., Vollrath, A., Odongo-Braun, C., Slagter, B., Balling, J., Gou, Y., Gorelick, N., y Reiche, J. 2021. Sentinel-1 SAR Backscatter Analysis Ready Data Preparation in Google Earth Engine. Remote Sensing, 13(10).

NASA JPL. 2020. NASADEM Merged DEM Global 1 arc second.

Ndikumana, E., Ho Tong Minh, D., Baghdadi, N., Courault, D., y Hossard, L. 2018. Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France. In Remote Sensing, 10(8), 1217.

Olofsson, P., Foody, G.M., Stehman, S.V., y Woodcock, C.E. 2013. Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation. Remote Sensing of Environment, 129(0), 122-131.

Olofsson, P., Foody, G.M., Herold, M., Stehman, S. v, Woodcock, C.E., y Wulder, M.A. 2014. Good practices for estimating area and assessing accuracy of land change. Remote Sensing of Environment, 148, 42-57.

Palomino-Ángel, S., Anaya-Acevedo, J.A., y Botero, B.A. 2019. Evaluation of 3B42V7 and IMERG dailyprecipitation products for a very high-precipitation region in northwestern South America. Atmospheric Research, 217, 37-48.

Pizano, C., y García, H. 2014. El bosque seco tropical en Colombia. Instituto de investigación de recursos biológicos Alexander von Humboldt.

Portillo-Quintero, C., Sanchez-Azofeifa, A., CalvoAlvarado, J., Quesada, M., y do Espirito Santo, M.M. 2015. The role of tropical dry forests for biodiversity, carbon and water conservation in the neotropics: lessons learned and opportunities for its sustainable management. Regional Environmental Change, 15(6), 1039-1049.

Soudani, K., Delpierre, N., Berveiller, D., Hmimina, G., Vincent, G., Morfin, A., y Dufrêne, É. 2021. Potential of C-band Synthetic Aperture Radar Sentinel-1 timeseries for the monitoring of phenological cycles in a deciduous forest. International Journal of Applied Earth Observation and Geoinformation, 104, 102505.

Vélez, D.A., y Álvarez-Mozos, J. 2020. Land use and land cover classification and change analysis in the area surrounding the manglares churute ecological reserve (Ecuador) using sentinel-1 time series. Revista de Teledeteccion, 2020(56), 131-146.

Vollrath, A., Mullissa, A., y Reiche, J. 2020. AngularBased Radiometric Slope Correction for Sentinel-1 on Google Earth Engine. Remote Sensing, 12(11).

Vuolo, F., Neuwirth, M., Immitzer, M., Atzberger, C., y Ng, W.-T. 2018. How much does multitemporal Sentinel-2 data improve crop type classification? International Journal of Applied Earth Observation and Geoinformation, 72, 122-130.

Whelen, T., y Siqueira, P. 2018. Time-series classification of Sentinel-1 agricultural data over North Dakota. Remote Sensing Letters, 9(5), 411-420.

Zhang, F., y Yang, X. 2020. Improving land cover classification in an urbanized coastal area by random forests: The role of variable selection. Remote Sensing of Environment, 251, 112105.

Zhang, H., Li, J., Wang, T., Lin, H., Zheng, Z., Li, Y., y Lu, Y. 2018. A manifold learning approach to urban land cover classification with optical and radar data. Landscape and Urban Planning, 172, 11-24.





Research articles

Funding data