PCA and SVM as geo-computational methods for geological mapping in the southern of Tunisia, using ASTER remote sensing data set

  • Anis Gasmi
  • Cécile Gomez
  • Hédi Zouari
  • Antoine Masse
  • Danielle Ducrot
Original Paper


The purpose of this study was to examine the efficiency of Advanced Space Borne Thermal Emission and Reflection Radiometer (ASTER) data in the discrimination of geological formations and the generation of geological map in the northern margin of the Tunisian desert. The nine ASTER bands covering the visible (VIS), near-infrared (NIR) and short-wave infrared (SWIR) spectral regions (wavelength range of 400–2500 nm) have been treated and analyzed. As a first step of data processing, crosstalk correction, resampling, orthorectification, atmospheric correction, and radiometric normalization have been applied to the ASTER radiance data. Then, to decrease the redundancy information in highly correlated bands, the principal component analysis (PCA) has been applied on the nine ASTER bands. The results of PCA allow the validation and the rectification of the lithological boundaries already published on the geologic map, and gives a new information for identifying new lithological units corresponding to superficial formations previously undiscovered. The application of a supervised classification on the principal components image using a support vector machine (SVM) algorithm shows good correlation with the reference geologic map. The overall classification accuracy is 73 % and the kappa coefficient equals to 0.71. The processing of ASTER remote sensing data set by PCA and SVM can be employed as an effective tool for geological mapping in arid regions.


PCA SVM ASTER Geological mapping Tunisia 



We thank the CERTE (Centre de Recherche et des Technologies des Eaux, Tunisie), the ONM (Office National des Mines, Tunisie), the CESBIO (Centre d’Etudes Spatiales de la Biosphère, France), and LISAH (Laboratoire d’étude des Interactions Sol Agrosystème Hydrosystème, France) for material assistance and guidance that provided for the completion of this work. We thank the editor and the reviewers for valuable comments and suggestions.


  1. Adler-Golden SM, Berk A, Bernstein LS, Richtsmeier SC, Acharya PK, Matthew MW, Anderson GP, Allred C, Jeong L, Chetwynd J (1998) FLAASH, a MODTRAN4 atmospheric correction package for hyperspectral data retrievals and simulations. AVIRIS Geoscience Workshop, Pasadena. Jet Propulsion Laboratory, CA, USAGoogle Scholar
  2. Bishop JL, Pietres CM, Dyar MD, Hamilton VE, Harloff J (2002) A spectral, chemical and mineralogical study of Mars analogue rocks. Lunar and Planetary Science XXXIII, LPI, Houston, TXGoogle Scholar
  3. Brandmeier M, Erasmi S, Hansen C, Höweling A, Nitzsche K, Ohlendorf T, Mamani M (2013) Mapping patterns of mineral alteration in volcanic terrains using ASTER data and field spectrometry in southern Peru. J S Am Earth Sci 48:296–314. doi: 10.1016/j.jsames.2013.09.011 CrossRefGoogle Scholar
  4. ERSDAC (2003) Earth remote sensing data analysis center. Crosstalk correction software User’s guide. Mitsubichi Space Software Co. Ltd., Tokyo, pp. 1–17Google Scholar
  5. Fujisada H (1995) Design and performance of ASTER instrument. Proc SPIE Int Soc Opt Eng 2583:16–25. doi: 10.1117/12.228565 Google Scholar
  6. Fujisada H, Ono A (1994) Observational performance of ASTER instrument on EOS AM1 spacecraft. Adv Space Res 14:147–150. doi: 10.1016/0273-1177(94)90207-0 CrossRefGoogle Scholar
  7. Gomez C, Delacourt C, Allemand P, Ledru P, Wackerle R (2005) Using ASTER remote sensing data set for geological mapping, in Namibia. Phys Chem Earth 30:97–108. doi: 10.1016/j.pce.2004.08.042 CrossRefGoogle Scholar
  8. Hewson RD, Cudahy TJ, Huntington JF (2001) Geologic and alteration mapping at Mt Fitton, South Australia, using ASTER satellite-borne data. International Geosciences and Remote Sensing Symposium 2:724–726. doi: 10.1109/IGARSS.2001.976615 Google Scholar
  9. Hsu CW, Chang CC, Lin CJ (2016) A practical guide to support vector classification. National Taiwan University. Accessed 19 May 2016
  10. Hunt GR (1977) Spectral signatures of particulate minerals in the visible and near infrared. Geophysics 42:501–513. doi: 10.1190/1.1440721 CrossRefGoogle Scholar
  11. Hunt GR (1979) Near infrared (1.3-2.4 μm) spectra of alteration minerals-potential for use in remote sensing. Geophysics 44:1974–1986. doi: 10.1190/1.1440951 CrossRefGoogle Scholar
  12. Iwasaki A, Tonooka H (2005) Validation of a crosstalk correction algorithm for ASTER/SWIR. IEEE Trans Geosci Remote Sens 43:2747–2751. doi: 10.1109/TGRS.2005.855066 CrossRefGoogle Scholar
  13. Japan Space Systems (2012) Available from: Accessed 30 Mar 2012
  14. Kahle AB (1976) Thermal inertia imaging: a new geologic mapping tool. Geophys Res Lett 3:419–421. doi: 10.1029/GL003i001p00026 CrossRefGoogle Scholar
  15. Kavzoglu T, Colkesen I (2009) A kernel functions analysis for support vector machines for land cover classification. Int J Appl Earth Obs Geoinf 11:352–359. doi: 10.1016/j.jag.2009.06.002 CrossRefGoogle Scholar
  16. Khan SD, Mahmood K, Casey JF (2007) Mapping of Muslim Baghophiolite complex (Pakistan) using new remote sensing, and field data. J Asian Earth Sci 30:333–343. doi: 10.1016/j.jseaes.2006.11.001 CrossRefGoogle Scholar
  17. Leverington DW (2010) Discrimination of sedimentary lithologies using Hyperion and Landsat thematic mapper data: a case study at Melville Island, Canadian high Arctic. Int J Remote Sens 31(1):233–260. doi: 10.1080/01431160902882637 CrossRefGoogle Scholar
  18. Li PJ, Long XY, Liu L (2007) Ophiolite mapping using ASTER data: a case study of Derni ophiolite complex. Acta Petrol Sin 23(5):1175–1180Google Scholar
  19. Lyon RJP (1972) Infrared spectral emittance in geological mapping: airborne spectrometer data from Pisgah crater. Science 7:983–986. doi: 10.1126/science.175.4025.983 CrossRefGoogle Scholar
  20. Mustard JF, Hays JE (1997) Effects of hyperfine particles on reflectance spectra from 0.3 to 25 μm. Icarus 125:145–163 CrossRefGoogle Scholar
  21. Okada K, Ishii M (1993) Mineral and lithological mapping using thermal infrared remotely sensed data from ASTER simulator. International Geosciences and Remote Sensing Symposium “Better Understanding of Earth Environment” 93:126–128. doi: 10.1109/IGARSS.1993.322501
  22. Oommen T, Misra D, Twarakavi NKC, Prakash A, Sahoo B, Bandopadhyay S (2008) An objective analysis of support vector machine based classification for remote sensing. Math Geosci 40:409–424. doi: 10.1007/s11004-008-9156-6 CrossRefGoogle Scholar
  23. Pour AB, Hashim M (2011) Spectral transformation of ASTER data and the discrimination of hydrothermal alteration minerals in a semi-arid region, SE Iran. International Journal of the Physical Sciences 6(8):2037–2059Google Scholar
  24. Pournamdari M, Pour AB, Hashim M (2014) Spectral transformation of ASTER and Landsat TM bands for lithological mapping of Soghan ophiolite complex, South Iran. Adv Space Res 54:694–709. doi: 10.1016/j.asr.2014.04.022 CrossRefGoogle Scholar
  25. Richards JA, Xiuping J (1998) Remote Sensing Digital Image Analysis, 3rd edn. Springer, Berlin, p. 363Google Scholar
  26. Rowan L, Hook SJ, Abrams MJ, Mars JC (2003) Mapping hydrothermally altered rocks at cuprite, Nevada, using the advanced Spaceborne thermal emission and reflection radiometer (ASTER), a new satellite-imaging system. Econ Geol Bull Soc Econ Geol 98(5):1019–1027CrossRefGoogle Scholar
  27. Salisbury JW, Walter LS, Verge N (1987) Mid-infrared (2.1–25 μm) spectra of minerals, 1st ed. United States Geological Survey, Open File Report, USGS, Washington, DC, p 87–263Google Scholar
  28. Watson K (1975) Geological applications of thermal infrared images. Proc IEEE 63:128–137. doi: 10.1109/PROC.1975.9712 CrossRefGoogle Scholar
  29. Yamaguchi Y, Kahle AB, Kawakami T, Kawakami T, Pniel M (1998) Overview of the Advanced Spaceborne Thermal Emission And Reflection Radiometer (ASTER). IEEE Transaction on Geoscience and Remote Sensing 36(4):1062–1071. doi: 10.1109/36.700991 CrossRefGoogle Scholar
  30. Younis MT, Gilabert MA, Melia J, Bastida J (1997) Weathering process on spectral reflectance of rocks in a semi-arid environment. Int J Remote Sens 18(16):3361–3377. doi: 10.1080/014311697216928 CrossRefGoogle Scholar
  31. Yu L, Porwal A, Holden EJ, Dentith MC (2012) Towards automatic lithological classification from remote sensing data using support vector machines. Comput Geosci 45:229–239. doi: 10.1016/j.cageo.2011.11.019 CrossRefGoogle Scholar
  32. Zouari H, Ouled Ghrib A, Ben Ouezdou H, Zargouni F (1989) Geological map of El Ayacha, scale 1:100000 Geological Series, Sheet 67. National Office of Mines (ONM) Geological Survey of TunisiaGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2016

Authors and Affiliations

  • Anis Gasmi
    • 1
    • 2
  • Cécile Gomez
    • 3
  • Hédi Zouari
    • 2
  • Antoine Masse
    • 4
  • Danielle Ducrot
    • 4
  1. 1.Université de Tunis El ManarFaculté des Sciences de Tunis (FST)El ManarTunisie
  2. 2.Laboratoire de Traitement des Eaux Naturelles (LabTEN)Centre de Recherches et Technologies des Eaux (CERTE), Technopole de Borj CedriaSolimanTunisie
  3. 3.IRD, Laboratoire d’Etude des Interactions Sols-Agrosystèmes-Hydrosystèmes, UMR LISAH (INRA-IRD-SupAgro)MontpellierFrance
  4. 4.Centre d’Etudes Spatiales de la Biosphère (CESBIO)Toulouse cedex 9France

Personalised recommendations