Hyperspectral satellite data analysis for pure pixels extraction and evaluation of advanced classifier algorithms for LULC classification


The study was carried out for Indian capital city Delhi using Hyperion sensor onboard EO-1 satellite of NASA. After MODTRAN-4 based atmospheric correction, MNF, PPI and n-D visualizer were applied and endmembers of 11 LCLU classes were derived which were employed in classification of LULC. To incur better classification accuracy, a comparative study was also carried out to evaluate the potential of three classifier algorithms namely Random Forest (RF), Support Vector Machines (SVM) and Spectral Angle Mapper (SAM). The results of this study reemphasize the utility of satellite borne hyperspectral data to extract endmembers and also to delineate the potential of random forest as expert classifier to assess land cover with higher classification accuracy that outperformed the SVM by 19% and SAM by 27% in overall accuracy. This research work contributes positively to the issue of land cover classification through exploration of hyperspectral endmembers. The comparison of classification algorithms’ performance is valuable for decision makers to choose better classifier for more accurate information extraction.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140

    Google Scholar 

  2. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  3. Breiman L and Cutler A (2004) Random forests Berkeley University article http://www.Stat.berkeley.Edu/~breiman/RandomForests. Accessed 16 May, 2015

  4. Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth International Group, Monterey

    Google Scholar 

  5. Carvalho De OA, Meneses PR (2000) Spectral correlation mapper (SCM): an improvement on the spectral angle mapper (SAM). Summaries of the 9th JPL airborne earth science workshop. JPL Publ 9:00–18

    Google Scholar 

  6. Chan JCW, Paelinckx D (2008) Evaluation of random Forest and Adaboost treebased ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery. Remote Sens Environ 112:2999–3011

    Article  Google Scholar 

  7. Chapelle O, Haffner P, Vapnik V (1999) SVMs for histogram-based image classification. IEEE Trans Neural Netw 10(5):1055–1064

    Article  Google Scholar 

  8. Colgan M, Baldeck C, Féret JB, Asner G (2012) Mapping savanna tree species at ecosystem scales using support vector machine classification and BRDF correction on airborne hyperspectral and LiDAR data. Remote Sens 4:3462–3480

    Article  Google Scholar 

  9. Congalton RG, Green K (1999) Assessing the accuracy of remotely sensed data principles and practices. Lewis Publishers, Boca Raton

    Google Scholar 

  10. Congalton RG, Oderwald RG, Mead RA (1983) Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. Photogramm Eng Remote Sens 49:1671–1678

    Google Scholar 

  11. Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297

    Google Scholar 

  12. Crosta AP, Sabine C, Taranik JV (1998) Hydrothermal Alteration Mapping at Bodie, California, using AVIRIS Hyperspectral Data. Remote Sens Environ 65:309–319

    Article  Google Scholar 

  13. Demir B, Ertürk S (2008) Phase correlation based redundancy removal in feature weighting band selection for hyperspectral images. Int J Remote Sens 29(6):1801–1807

    Article  Google Scholar 

  14. Dietterich TG (2000) An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn 40:139–157

    Article  Google Scholar 

  15. Dinsdale EA, Edwards RA, Bailey BA, Tuba I, Akhter S, McNair K, Schmieder R, Apkarian N, Creek M, Guan E, Hernandez M, Isaacs K, Peterson C, Regh T, Ponomarenko V (2013) Multivariate analysis of functional metagenomes. Front Genet 4:41

    Article  Google Scholar 

  16. Ellis JM (2001) Searching for oil seeps and oil-impacted soil with hyperspectral imagery. Earth Obs Mag 25–28

  17. ENVI help (2017) ENVI 5.0, Exelisvis Inc. USA. ENVI software user help

  18. Féret JB, Asner GP (2013) Tree species discrimination in tropical forests using airborne imaging spectroscopy. IEEE Trans Geosci Remote Sens 51(1):73-84

  19. FLAASH module user’s guide (2006) Version 4.3, ITT Visual Information Solutions. ftp://popo.jpl.nasa.gov/pub/ENVI_Installers/ENVI_Documentation/docs/FLAASH_Module.pdf. Accessed 13 Sept 2017

  20. Furey TS, Cristianini N, Duffy N, Bednarski DW, Schummer M, Haussler D (2000) Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 16(10):906–914

    Article  Google Scholar 

  21. Girouard G, Bannari A, Harti A, and Desrochers A (2004) Validated spectral angle mapper algorithm for geological mapping: comparative study between Quickbird and Landsat-TM. Proc. of 20th International Society for Photogrammetry and Remote Sensing Congress, Istanbul, Turkey 599–605

  22. Goodenough DG, Dyk A, Niemann O, Pearlman JS, Chen H, Han T, Murdoch M, West C (2003) Processing HYPERION and ALI for forest classification. IEEE Trans Geosci Remote Sens 41(2):1321–1331

    Article  Google Scholar 

  23. Gupta RP (2003) Remote sensing geology, 2nd edn. Springer Publication, New York

    Book  Google Scholar 

  24. Hall FG, Strebel DE, Nickeson JE, Goets SJ (1991) Radiometric rectification: towards a common radiometric response among multidate, multisensor images. Remote Sens Environ 35:11–27

    Article  Google Scholar 

  25. Han T, Goodenough DG, Dyk A, Love J (2002) Detection and correction of abnormal pixels in hyperion images. IGARSS Toronto, Ontario, Canada: IEEE 1327–1330

  26. Horning N (2010) RandomForests : an algorithm for image classification and generation of continuous fields data sets. International Conference on Geoinformatics for Spatial Infrastructure Development in Earth and Allied Sciences (GISIDEAS)

  27. Hunter EL, Power CH (2002) An Assessment of Two Classification Methods for Mapping Thames Estuary Intertidal Habitats Using CASI Data. Int J Remote Sens 23(15):2989–3008

    Article  Google Scholar 

  28. Jupp DLB, Datt B, Lovell J, Campbell S, King E (2002) Discussions around Hyperion data: background notes for the Hyperion data users workshop. CSIRO, CSIRO Office of Space Science & Applications Earth Observation Centre

    Google Scholar 

  29. Krishna G (2012) Spatiotemporal analysis of Noida, Greater Noida and surrounding areas (India) using remote sensing and GIS approaches. J Remote Sens GIS 3(3):42–51

    Google Scholar 

  30. Kruse FA, Boardman JW, Lefkoff AB, Heidebrecht KB, Shapiro AT, Barloon PJ, Goetz AFH (1993) The Spectral Image Processing System (SIPS) – Interactive Visualization and Analysis of Imaging Spectrometer Data. Remote Sens Environ 44:145–163

    Article  Google Scholar 

  31. Lacar FM, Lewis MM, Grierson IT (2001) Use of hyperspectral imagery for mapping grape varieties in the Barossa Valley, South Australia. Geosci Remote Sens Symp IGARSS 6:2875–2877

    Google Scholar 

  32. Liaw A, Wiener M (2002) Classification and regression by random forest. R News 2(3):18–22

    Google Scholar 

  33. Licciardi G, Pacifici F, Tuia D et al (2009) Decision fusion for the classification of hyperspectral data: outcome of the 2008 GRS-S data fusion contest. IEEE Trans Geosci Remote Sens 47(11):3857–3865

    Article  Google Scholar 

  34. Mountrakis G, Im J, Ogole C (2011) Support vector machines in remote sensing: a review. ISPRS J Photogramm Remote Sens 66:247–259

    Article  Google Scholar 

  35. Petropoulos GP, Vadrevu KP, Kalaitzidis C (2013) Spectral angle mapper and object-based classification combined with hyperspectral remote sensing imagery for obtaining land use/cover mapping in a Mediterranean region. Geocarto Int 28:114–129. https://doi.org/10.1080/10106049.2012.668950

    Article  Google Scholar 

  36. Rodriguez-Galiano VF, Chica-Olmo M, Abarca-Hernandez F, Atkinson PM, Jeganathan C (2012a) Random forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture. Remote Sens Environ 121:93–107

    Article  Google Scholar 

  37. Rodríguez-Galiano VF, Ghimire B, Pardo-Igúzquiza E, Chica-Olmo M, Congalton RG (2012b) Incorporating the downscaled landsat TM thermal band in landcover classification using random forest. Photogramm Eng Remote Sens 78:129–137

    Article  Google Scholar 

  38. Rosenfield GH, Fitzpatrick-Lins K (1986) A coefficient of agreement as a measure of thematic classification accuracy. Photogramm Eng Remote Sens 52:223–227

    Google Scholar 

  39. Rowan LC, Mars JC (2003) Lithologic mapping in the Mountain Pass, California area using Advanced Spaceborn Thermal Emission and Reflection Radiometer (ASTER) data. Remote Sens Environ 84:250–266

    Article  Google Scholar 

  40. Sahoo RN, Pargal S, Pradhan S, Krishna G, and Gupta VK (2013) Processing of Hyperspectral remote sensing data- a practical manual, ICAR publication

  41. Schwarz J, Staenz K (2001) Adaptive Threshold for Spectral Matching of Hyperspectral Data. Can J Remote Sens 27(3):216–224

    Article  Google Scholar 

  42. Statnikov A, Aliferis CF, Tsamardinos I, Hardin D, Levy S (2005) A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics 21(5):631–643

    Article  Google Scholar 

  43. Switzer P, Green AA (1984) Min / max autocorrelation factors for multivariate spatial imagery. Department of Statistics, Stanford University, Technical Report No. 6

  44. Thenkabail PS (2011) Hyperspectral remote sensing of vegetation. Landsat science team meeting, USA

  45. Van der Meer F, Vasquez-Torres M, Van Dijk PM (1997) Spectral Characterization of Ophiolite Lithologies in the Troodos Ophiolite Complex of Cyprus and its Potential in Prospecting for Massive Sulphide Deposits. Int J Remote Sens 18(6):1245–1257

    Article  Google Scholar 

  46. USGS EO-1 website (2015). http://eo1.usgs.gov. Accessed 12 May 2015

  47. Vapnik VN (1995) The nature of statistical learning theory, vol 8. Springer Verlag, New York

  48. Waske B, Benediktsson JA, Arnason K, Sveinsson JR (2009) Mapping of hyperspectral aviris data using machine learning algorithms. Can J Remote Sens 35:106–116

    Article  Google Scholar 

  49. Wen X, Yang X (2012) An unsupervised classification method for hyperspectral remote sensing image based on spectral data mining. In: Advances in data mining knowledge discovery and applications. InTechOpen, Croatia, pp 143–154

  50. Yuhas RH, Goetz AFH, Boardman JW (1992) Discrimination Among Semi-Arid Landscape Endmembers Using the Spectral Angle Mapper (SAM) Algorithm. Summaries of the 4th JPL Airborne Earth Science Workshop. JPL Publ 92(41):147–149

    Google Scholar 

  51. Zhang C, Xie Z (2013) Object-based vegetation mapping in the Kissimmee River watershed using HyMap data and machine learning techniques. Wetlands 33:233–244

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Gopal Krishna.

Ethics declarations

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Communicated by: H. A. Babaie

Electronic supplementary material


(PNG 461 kb)


(PNG 62 kb)


(PNG 20 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Krishna, G., Sahoo, R.N., Pradhan, S. et al. Hyperspectral satellite data analysis for pure pixels extraction and evaluation of advanced classifier algorithms for LULC classification. Earth Sci Inform 11, 159–170 (2018). https://doi.org/10.1007/s12145-017-0324-4

Download citation


  • Endmembers extraction
  • Hyperspectral image classification
  • Random forest - ensemble classifier
  • SVM
  • SAM