Remote Sensing of Invasive Species in the Galapagos Islands: Comparison of Pixel-Based, Principal Component, and Object-Oriented Image Classification Approaches

  • Carolina Sampedro
  • Carlos F. Mena
Part of the Social and Ecological Interactions in the Galapagos Islands book series (SESGI)


The application of remote sensing techniques in threatened ecosystems such as the Galapagos Islands has shown to be a powerful tool for decision-making. Specifically in the case of San Cristobal Island, it will allow accurate mapping and modeling techniques at relatively low costs for battling invasive species such as guava and wax apple. This research evaluates the performance of three classification techniques for land cover mapping in the agricultural area of San Cristobal in the Galapagos: (a) pixel-based hybrid (supervised/unsupervised classification), (b) principal component pixel-based hybrid, and (c) object-oriented image hybrid classifications. An evaluation of three parametric classification algorithms (maximum likelihood, Mahalanobis distance, and minimum distances) for classification technique was also performed. The goal was to compare and identify the best approach for determining LULC with a focus on invasive species such as guava in the highland territory. The results for both pixel-based approaches are superior than the object-based approach. Nevertheless, it was evident that the principal component classifications tend to mix signature responses and did not show the same discrimination ability. Per-pixel/hybrid classification with maximum likelihood and Mahalanobis distance performs a superior kappa index of 0.8640 and 0.8610, respectively, proving to be more sensitive toward identifying invasive species such as guava and wax apple fields.


Galapagos LULC Remote sensing Sub-pixel classification Object-based classification 


  1. Aguirre-Gutiérrez J, Seijmonsbergen AC, Duivenvoorden JF (2012) Optimizing land cover classification accuracy for change detection, a combined pixel-based and object-based approach in a mountainous area in Mexico. Appl Geogr 34:29–37. CrossRefGoogle Scholar
  2. Aplin P, Atkinson PM (2001) Sub-pixel cover mapping for per-field classification. Int J Remote Sens 22(14):2853–2858CrossRefGoogle Scholar
  3. Ceballos JC, Bottino MJ (1997) The discrimination of scenes by principal components analysis of multi-spectral imagery. Int J Remote Sens 18(11):2437–2449. CrossRefGoogle Scholar
  4. Coello S, Saunders A (2011). Final project evaluation: control of invasive species in the Galapagos Archipelago, ECU/00/G31Google Scholar
  5. Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37(1):35–46CrossRefGoogle Scholar
  6. Cremers L (2002) Irrigated agriculture on the Galapagos Islands: fit for survival. Wageningen University, WageningenGoogle Scholar
  7. Desclée B, Bogaert P, Defourny P (2006) Forest change detection by statistical object-based method. Remote Sens Environ 102:1–11CrossRefGoogle Scholar
  8. Duro DC, Franklin SE, Dubé MG (2012) A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sens Environ 118:259–272. CrossRefGoogle Scholar
  9. ENVI EX (2009) ENVI EX user’s guide. ENVI EX tutorialGoogle Scholar
  10. Erdas Inc (1999) ERDAS field guide. Imagine, 5th edn. ERDAS, AtlantaGoogle Scholar
  11. Fleiss J (1971) Measuring nominal scale agreement among many raters. Psychol Bull 76:378–382CrossRefGoogle Scholar
  12. Foody GM (2002) Status of land cover classification accuracy assessment. Remote Sens Environ 80(1):185–201. CrossRefGoogle Scholar
  13. González JA, Montes C, Rodríguez J, Tapia W (2008) Rethinking the Galapagos Islands as a complex social-ecological system: implications for conservation and management. Ecol Soc 13(2):13CrossRefGoogle Scholar
  14. Grenier C (2000) Conservation contre nature: Les Iles Galápagos (IRD). Collection Latitudes 23, ParisCrossRefGoogle Scholar
  15. Huang C-Y, Asner GP (2009) Applications of remote sensing to alien invasive plant studies. Sensors (Basel, Switzerland) 9(6):4869–4889. CrossRefGoogle Scholar
  16. Im J, Jensen J, Tullis J (2008) Object-based change detection using correlation image analysis and image segmentation techniques. Int J Remote Sens 29:399–423CrossRefGoogle Scholar
  17. INEC (2010) Censo de Población y Vivienda. Ecuador.Google Scholar
  18. Joshi C (2006) Mapping cryptic invaders and invasibility of tropical forest ecosystems: Chromolaena odorata in Nepal. International Institute for Geo-information Science & Earth Observation (ITC), EnschedeGoogle Scholar
  19. Li X, Yeh AGO (1998) Principal component analysis of stacked multi-temporal images for the monitoring of rapid urban expansion in the Pearl River Delta. Int J Remote Sens 19(8):1501–1518. CrossRefGoogle Scholar
  20. Lloyd CD, Berberoglu S, Atkinson PM, Curran PJ (2004) A comparison of texture measures for the per-field classification of Mediterranean land cover. Int J Remote Sens 25:3943–3965CrossRefGoogle Scholar
  21. Lu D, Weng Q (2007) A survey of image classification methods and techniques for improving classification performance. Int J Remote Sens 28(5):823–870. CrossRefGoogle Scholar
  22. Magnani R (1999) Sampling guide: food security and nutrition monitoring. USAID, Washington, DCGoogle Scholar
  23. Messina J, Walsh S (2001) 2.5D morphogenesis: modeling landuse and landcover dynamics in the Ecuadorian Amazon. Plant Ecol 156(1):75–88CrossRefGoogle Scholar
  24. Messina JP, Crews-Meyer KA, Walsh SJ (2000) Scale dependent pattern metrics and panel data analysis as applied in a multiphase hybrid landcover classification scheme. In: Proc. 2000 ASPRS confGoogle Scholar
  25. Ministerio de Medio Ambiente, S.B (2010) Protocolo Metodológico para la generación del Mapa de Deforestación Histórica en el Ecuador continental. MAE, QuitoGoogle Scholar
  26. Ministerio del Ambiente (2013) Programa de control y erradicación de especies invasoras prioritarias para la reducción de la vulnerabilidad de especies endémicas y nativas de las islas Galápagos. San Cristobal, Parque Nacional GalápagosGoogle Scholar
  27. Myint SW, Giri CP, Wang L, Zhu Z, Gillette S (2008) Identifying mangrove species and their surrounding land use and land cover classes using an object oriented approach with a lacunarity spatial measure. GISci Remote Sens 45:188–208CrossRefGoogle Scholar
  28. Myint SW, Gober P, Brazel A, Grossman-Clarke S, Weng Q (2011) Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens Environ 115(5):1145–1161. CrossRefGoogle Scholar
  29. Pal M, Mather P (2003) An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sens Environ 86:554–565CrossRefGoogle Scholar
  30. Pal M, Mather P (2004) Assessment of the effectiveness of support vector machines for hyperspectral data. Futur Gener Comput Syst 20:1215–1225CrossRefGoogle Scholar
  31. Registro Oficial No. 520 (2015) Ley Orgánica de Régimen Especial de la Provincia de Galápagos. Asamblea Nacional del Ecuador, QuitoGoogle Scholar
  32. Rodriguez-Galiano VF, Ghimire B, Rogan J, Chica-Olmo M, Rigol-Sanchez JP (2012) An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS J Photogramm Remote Sens 67:93–104. CrossRefGoogle Scholar
  33. Rozenstein O, Karnieli A (2011) Comparison of methods for land-use classification incorporating remote sensing and GIS inputs. Appl Geogr 31(2):533–544. CrossRefGoogle Scholar
  34. Schott JR (1997) Remote sensing: the image chain approach. Oxford University Press, New YorkGoogle Scholar
  35. Smits PC, Dellepiane SG, Schowengerdt RA (1999) Quality assessment of image classification algorithms for land-cover mapping: a review and proposal for a cost-based approach. Int J Remote Sens 20:1461–1486CrossRefGoogle Scholar
  36. South S, Qi J, Lusch D (2004) Optimal classification methods for mapping agricultural tillage practices. Remote Sens Environ 91:90–97CrossRefGoogle Scholar
  37. Tayor PJ (1977) Quantitative methods in geography: an introduction to spatial analysis. Houghton Mifflin Company, BostonGoogle Scholar
  38. Taylor JE, Hardner J, Stewart M (2006) Ecotourism and economic growth in the Galapagos: an island economy-wide analysis. Environ Dev Econ 14:139–162CrossRefGoogle Scholar
  39. UICN (2007) Convention concerning the protection of the world cultural and natural heritage: thirty-fourth session (31 COM). Paris, FranceGoogle Scholar
  40. UICN (2010a) Convention concerning the protection of the world cultural and natural heritage: thirty-fourth session (34 COM). Understanding the politics of heritage. Paris, France.
  41. UICN (2010b) Decision: 34 COM 8C.3. Accessed 13 Sept 2016
  42. UICN (2016) Convention concerning the protection of the world cultural and natural heritage: thirty-fourth session (40 COM). Paris, FranceGoogle Scholar
  43. Van der Meer F, Scmidt KS, Bakker A, Bokler W (2002) Environmental modelling with GIS and RS. In: New environmental RS systems. Taylor and Francis, London, p 26–51Google Scholar
  44. Whiteside TG, Boggs GS, Maier SW (2011) Comparing object-based and pixel-based classifications for mapping savannas. Int J Appl Earth Observ Geoinform 13(6):884–893. CrossRefGoogle Scholar
  45. Wilkinson GG (2005) Results and implications of a study of fifteen years of satellite image classification experiments. Computer 43(3):433–440Google Scholar
  46. Xie Z, Roberts C, Johnson B (2008) Object-based target search using remotely sensed data: a case study in detecting invasive exotic Australian Pine in south Florida. J Photogramm Remote Sens 63(6):647–660CrossRefGoogle Scholar
  47. Yan G, Maathuis BHP, Xiangmin Z, Van Dijk PM (2006) Comparison of pixel based and object oriented image classification approaches—a case study in a coal fire area, Wuda, Inner Mongolia, China. Int J Remote Sens 27(18):4039–4055CrossRefGoogle Scholar
  48. Messina, J. P., Crews-Meyer, K. A. & Walsh, S. J (2000) Scale dependent pattern metrics and panel data analysis as applied in a multiphase hybrid landcover classification scheme. Proc. 2000 ASPRS ConfGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Universidad San Francisco de Quito—USFQ, Instituto de GeografíaQuitoEcuador
  2. 2.Colegio de Ciencias Biológicas y AmbientalesUniversidad San Francisco de QuitoQuitoEcuador
  3. 3.UNC-USFQ Galapagos Science Center, Universidad San Francisco de QuitoQuitoEcuador

Personalised recommendations