Evaluation of four classification algorithms of Landsat-8 and Sentinel-2 satellite images to identify forest cover in highly fragmented regions in Costa Rica





Landsat 8, Sentinel-2, Maximum likelihood classification (MLC), Minimum distance classification (MDC), Support vector machine (SVM), Neural net classification (NNC), Huetar Norte Zone


Mapping of land use and forest cover and assessing their changes is essential in the design of strategies to manage and preserve the natural resources of a country, and remote sensing have been extensively used with this purpose. By comparing four classification algorithms and two types of satellite images, the objective of the research was to identify the type of algorithm and satellite image that allows higher global accuracy in the identification of forest cover in highly fragmented landscapes. The study included a treatment arrangement with three factors and six randomly selected blocks within the Huetar Norte Zone in Costa Rica. More accurate results were obtained for classifications based on Sentinel-2 images compared to Landsat-8 images. The best classification algorithms were Maximum Likelihood, Support Vector Machine or Neural Networks, and they yield better results than Minimum Distance Classification. There was no interaction among image type and classification methods, therefore, Sentinel-2 images can be used with any of the three best algorithms, but the best result was the combination of Sentinel-2 and Support Vector Machine. An additional factor included in the study was the image acquisition date. There were significant differences among months during which the image was acquired and an interaction between the classification algorithm and this factor was detected. The best results correspond to images obtained in April, and the lower to September, month that corresponds with the period of higher rainfall in the region studied. The higher global accuracy identifying forest cover is obtained with Sentinel-2 images from the dry season in combination with Maximum Likelihood, Support Vector Machine, and Neural Network image classification methods.


Download data is not yet available.

Author Biographies

I.D. Ávila-Pérez, Instituto Tecnológico de Costa Rica; Centro Nacional de Alta Tecnología de Costa Rica

Instituto Tecnológico de Costa Rica
Centro Nacional de Alta Tecnología de Costa Rica

E. Ortiz-Malavassi, Instituto Tecnológico de Costa Rica

Escuela de Ingeniería Forestal

C. Soto-Montoya, Instituto Tecnológico de Costa Rica

Escuela de Ingeniería Forestal

Y. Vargas-Solano, Centro Nacional de Alta Tecnología

Laboratorio PRIAS

H. Aguilar-Arias, Centro Nacional de Alta Tecnología

Laboratorio PRIAS

C. Miller-Granados, Centro Nacional de Alta Tecnología

Laboratorio PRIAS


Adankon, M., Cheriet, M. 2015. Support Vector Machine. En Encyclopedia of Biometrics, Editada por Stan Z. Li and Anil K. Jain, London: Springer. https://doi.org/10.1007/978-1-4899-7488-4_299

Barrientos, O., Chaves, G. 2008. Región Huetar Norte. Oferta exportada actual y oferta potencial de productos agropecuarios alternativos. Último acceso: 18 de marzo, 2020, de: https://web.archive.org/web/20140309040649/ http://www.procomer.com/contenido/descargables/investigaciones_economicas/2008/Region_Huetar_Norte_final.pdf

Berlanga, C., Cervantes, A., Murúa, E. 2018. Estacionalidad y tendencias del bosque tropical caducifolio de la cuenca Piaxtla-Elota- Quelite y el área protegida Meseta de Cacaxtla, México. Madera y bosques, 24(3), 1-16. https://doi.org/10.21829/myb.2018.2431576

Booth, D., Oldfield, R. 1989. A comparison of classification algorithms in terms of speed and accuracy after the application of a post-classification modal filter. International Journal of Remote Sensing, 10(7), 1271-1276. https://doi.org/10.1080/01431168908903965

CCT. 1993. Mapa Ecológico de Costa Rica, según el sistema de clasificación de Zonas de Vida del mundo de L. R. Holdridge. Bolaños, R; Watson; V. 1993 / Centro Científico Tropical (CCT) / esc: 1: 200 000). En Atlas Digital de Costa Rica 2014. Editado por E. Ortiz. ITCR, Cartago, Costa Rica.

Centro Nacional de Información Geoambiental (CENIGA). 2018. Sistema de Definición de Clases de los Usos y Coberturas de la Tierra de Costa Rica. San José, Costa Rica.

Chassot, O., Chaves, H., Finengan, B., Monge, G. 2010. Dinámica de paisaje en la Zona Norte de Costa Rica: implicaciones para la conservación del bosque tropical muy húmedo. Revista De Ciencias Ambientales, 39(1), 37-53. https://doi.org/10.15359/rca.39-1.5

Chazdon, R. 2014. Second growth: the promise of tropical forest regeneration in an age of deforestation. Chicago, University of Chicago Press. https://doi. org/10.7208/chicago/9780226118109.001.0001

Choodarathnakara, A., Ashok, T., Koliwad, S., Patil, C. 2012. Mixed pixels: a challenge in remote sensing data classification for improving performance. International Journal of Advanced Research in Computer Engineering and Technology (IJARCET), 1(9), 261-271.

Deilmai, B., Ahmad, B., Zabihi, H. 2014. Comparison of two classification methods (MLC and SVM) to extract land use and land cover in Johor Malaysia. En IOP Conference Series: Earth and Environmental Science, Volume 20, 7th IGRSM International Remote Sensing & GIS Conference and Exhibition. Kuala Lumpur, Malaysia, 22–23 de April. pp 1-7. https://doi.org/10.1088/1755-1315/20/1/012052

Del Toro, N., Gomariz, F., Cánovas, F., Alonso, F. 2015. Comparación de métodos de clasificación de imágenes de satélite en la cuenca del Río Argos (Región de Murcia). Boletín de la Asociación de Geógrafos Españoles, 67, 327-347.

European Space Agency (ESA). 2020. Sentinel Online, Level C-1. Último acceso: 15 de setiembre, 2020, de https://www.harrisgeospatial.com/docs/ SupportVectorMachine.html

Guo, J., Zhang, J., Zhang, Y., Cao, Y. 2008. Study on the comparison of the land cover classification for multitemporal MODIS images. Paper presented at the fifth International Workshop on Earth Observation and Remote Sensing Applications, Xi’an, China, 18-20 de Junio. pp 1-6. https://doi.org/10.1109/EORSA.2008.4620305

Harris Geospatial Solutions, Inc. 2020. Support Vector Machine. Último acceso: 9 de julio, 2020, de https://www.harrisgeospatial.com/docs/ SupportVectorMachine.html

Hermosilla, T., Wulder, M., White, J., Coops, N., Hobart, G. 2015. An integrated landsat time series protocol for change detection and generation of annual gap-free surface reflectance composites. Remote Sensing of Environment, 158, 220-234. https://doi.org/10.1016/j.rse.2014.11.005

Kristollari, V., Karathanassi, V. 2020. Artificial neural networks for cloud masking of Sentinel-2 ocean images with noise and sunglint. International Journal of Remote Sensing, 41(11), 4102-4135. https://doi.org/10.1080/01431161.2020.1714776

Kupková, L., Červená, L., Suchá, R., Jakešová, L., Zagajewski, B., Březina, S., Albrechtová, J. 2017. Classification of Tundra Vegetation in the Krkonoše Mts. National Park Using APEX, AISA Dual and Sentinel-2A Data. European Journal of Remote Sensing, 50(1), 29-46. https://doi.org/10.1080/2279 7254.2017.1274573

Li, J., Yang, X., Maffei, C., Tooth, S., Yao, G. 2018. Applying independent component analysis on Sentinel-2 imagery to characterize geomorphological responses to an extreme flood event near the non-vegetated Río Colorado terminus, Salar de Uyuni, Bolivia. Remote Sensing, 10(5), 725-743. https://doi.org/10.3390/rs10050725

Lu, D., Weng, Q. 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28(5), 823-870. https://doi.org/10.1080/01431160600746456

Madhura, M., Venkatachalam, S. 2015. Comparison of supervised classification methods on remote sensed satellite data: an application in Chennai, South India. International Journal of Science and Research (IJSR), 4(2), 1407-1411.

Mata, R., Rosales, A., Vásquez, A., Sandoval, D. 2010. Mapa digital de suelos, órdenes y subórdenes, escala 1:200 000. Centro de investigaciones Agronómicas (CIA), Faculta de Ciencias Agroalimentarias. UCR. En Atlas Digital de Costa Rica 2014. Editado por: E. Ortiz, ITCR, Cartago, Costa Rica.

Matthew, M., Adler-Golden, S., Berk, A., Richtsmeier, S., Levine, R., Bernstein L., Acharya, P., Anderson, G., Felde, G., Hoke, M., Ratkowski, A., Burke, H., Kaiser, R., Miller, D. 2000. Status of Atmospheric Correction Using a MODTRAN4-based Algorithm. SPIE Proceedings, Algorithms for Multispectral, Hyperspectral, and Ultraspectral Imagery VI, 4049: 199-207. https://doi.org/10.1117/12.410341

Mondal, A., Kundu, S., Kumar, S., Shukla, R., Mishra, P. 2012. Comparison of support vector machine and maximum likelihood classification technique using satellite imagery. International Journal of Remote Sensing and GIS, 1(2), 116-123.

Mountrakis, G., Im, J., Ogole, C. 2011. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3), 247-259. https://doi.org/10.1016/j. isprsjprs.2010.11.001

Mura, M., Bottalico, F., Giannetti, F., Bertani, R., Giannini, R., Mancini, M., Orlandini, S., Travaglini, D., Chirici, G. 2018. Exploiting the capabilities of the sentinel-2 multi spectral instrument for predicting growing stock volume in forest ecosystems. International Journal of Applied Earth Observation and Geoinformation, 66, 126-134. https://doi.org/10.1016/j.jag.2017.11.013

Murtaza, K., Romshoo, S. 2014. Determining the suitability and accuracy of various statistical algorithms for satellite data classification. International Journal of Geomatics and Geosciences, 4(4), 585-599.

Ndehedehe, C., Ekpa, A., Simeon, O., Nse, O. 2013. Understanding the Neural Network Technique for Classification of Remote Sensing Data Sets. New York Science Journal, 6(8), 26-33.

Nhamo, L., van Dijk, R., Magidi, J., Wiberg, D., Tshikolomo, K. 2018. Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV capability. Remote Sensing, 10(5), 712-723. https://doi.org/10.3390/rs10050712

Ningthoujam, R., Tansey, K., Balzter, H., Morrison, K., Johnson, S., Gerard, F., George, C., Burbidge, G., Doody, S., Veck, N., Llewellyn, G., Blythe, T. 2016. Mapping forest cover and forest cover change with airborne s-band radar. Remote Sensing, 8(7), 577- 597. https://doi.org/10.3390/rs8070577

Olofsson, P., Foody, G., Herold, M., Stehman, S., Woodcock, C., Wulder, M. 2014. Good practices for estimating area and assessing accuracy of land change. Remote Sensing of Environment, 148, 42- 57. https://doi.org/10.1016/j.rse.2014.02.015

Perumal, K., Bhaskaran, R. 2010. Supervised classification performance of multispectral images. Journal of computing, 2(2), 124-129.

Pimple, U., Sitthi, A., Simonetti, D., Pungkul, S., Leadprathom, K., Chidthaisong, A. 2017. Topographic correction of Landsat TM-5 And Landsat OLI-8 imagery to improve the performance of forest classification in the mountainous terrain of northeast Thailand. Sustainability, 9(2), 258-283. https://doi.org/10.3390/su9020258

Ponce, D., Donoso, P., Salas-Eljatib, C. 2017. Differentiating structural and compositional attributes across successional stages in chilean temperate rainforests. Forests, 8(9), 329-343. https://doi.org/10.3390/f8090329

Qiu, S., He, B., Zhu, Z., Liao, Z., Quan, X. 2017. Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images. Remote Sensing of Environment, 199, 107-119. https://doi.org/10.1016/j.rse.2017.07.002

Sader, S., Joyce. A 1988. Deforestation rates and trends in Costa Rica, 1940 to 1983. Biotropica, 20, 11-19. https://doi.org/10.2307/2388421

Sánchez, G., Rivard, B., Calvo, J., Moorthy, I. 2002. Dynamics of tropical deforestation around national parks: remote sensing of forest change on the Osa Peninsula of Costa Rica. Mountain Research and Development, 22(4), 352-358. https://doi.org/10.1659/0276-4741(2002)022[0352:DOTDAN ]2.0.CO;2

Shen, H., Lin, Y., Tian, Q., Xu, K., Jiao, J. 2018. A comparison of multiple classifier combinations using different voting-weights for remote sensing image classification. International Journal of Remote Sensing, 39(11), 3705-3722. https://doi.org /10.1080/01431161.2018.1446566

Shi, X., Xue, B. 2016. Parallelizing maximum likelihood classification on computer cluster and graphics processing unit for supervised image classification. International Journal of Digital Earth, 10(7), 737- 748. https://doi.org/10.1080/17538947.2016.1251502

Topaloğlu, R., Sertel, E., Musaoğlu, N., 2016. Assessment of classification accuracies of sentinel-2 and landsat-8 data for land cover/use mapping. International Archives of the Photogrammetry. Remote Sensing and Spatial Information Sciencies, XLI-B8, 1055-1059. https://doi.org/10.5194/ isprsarchives-XLI-B8-1055-2016

Vega, M., Alvarado, R. 2019. Análisis de las series de tiempo de variables biofísicas para cuatro ecorregiones de Guanacaste, Costa Rica. Revista de Ciencias Ambientales, 53(2), 60-96. https://doi. org/10.15359/rca.53-2.4

Vogeler, J., Braaten, J., Slesak, R., Falkowski, M. 2018. Extracting the full value of the landsat archive: Inter-sensor harmonization for the mapping of Minnesota forest canopy cover (1973-2015). Remote Sensing of Environment, 209, 363-374. https://doi.org/10.1016/j.rse.2018.02.046

Wacker, A., Langrebe, D. 1972. Minimum Distance Classification in Remote Sensing. En 1st Canadian Symposium for Remote Sensing. Montreal, Canada, 7-9 de febrero. spp.

Walton, A. 2015. Assessing the performance of different classification methods to detect inland surface water extent. Bachelor Thesis. Institute of Geodesy, Universidad de Stuttgart; Alemania.

Whyte, A., Ferentinos, K., Petropoulos, G. 2018. A new synergistic approach for monitoring wetlands using sentinels-1 and 2 data with object-based machine learning algorithms. Environmental Modelling and Software, 104, 40-54. https://doi.org/10.1016/j.envsoft.2018.01.023

Yang, H., Pan, B., Wu, W., Tai, J. 2018. Field-based rice classification in Wuhua county through integration of multi-temporal sentinel-1A and landsat-8 OLI data. International Journal of Applied Earth Observation and Geoinformation, 69, 226-236. https://doi.org/10.1016/j.jag.2018.02.019

Yang, X., Zhao, S., Qin, X., Zhao, N., Liang, L. 2017. Mapping of urban surface water bodies from Sentinel-2 MSI imagery at 10 m resolution via NDWI-based image sharpening. Remote Sensing, 9(6), 596-603. https://doi.org/10.3390/rs9060596

Yin, H., Pflugmacher, D., Li, A., Li, Z., Hostert, P. 2018. Land use and land cover change in inner Mongolia-understanding the effects of china’s re-vegetation programs. Remote Sensing of Environment, 204, 918-930. https://doi.org/10.1016/j.rse.2017.08.030

Zhao, F., Huang, C., Goward, S., Schleeweis, K., Rishmawi, K., Lindsey, M., Denning, E., Keddell, L., Cohen, W., Yang, Z., Dungan, J., Michaelis, A. 2018. Development of Landsat-based annual US forest disturbance history maps (1986-2010) in support of the North American Carbon Program (NACP). Remote Sensing of Environmen, 209, 312- 326. https://doi.org/10.1016/j.rse.2018.02.035

Zhu, Z., Woodcock, C. 2012. Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment, 118, 83-94. https://doi.org/10.1016/j.rse.2011.10.028





Research articles