Comparison of feature reduction algorithms for classifying tree species with hyperspectral data on three central european test sites

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Volumn 7, Issue 6, 2014, Pages 2547-2561

  Fassnacht, Fabian E ^a,b   Neumann, Carsten ^c   Forster, Michael ^d   Buddenbaum, Henning ^e   Ghosh, Aniruddha ^f,g   Clasen, Anne ^d   Joshi, Pawan Kumar ^f   Koch, Barbara ^a  

^a UNIVERSITY OF FREIBURG   (Germany)

^b KARLSRUHE INSTITUTE OF TECHNOLOGY   (Germany)

^c GFZ GERMAN RESEARCH CENTRE FOR GEOSCIENCES   (Germany)

^d TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

^e UNIVERSITY OF TRIER   (Germany)

^f TERI UNIVERSITY   (India)

^g Department of Environmental and Radiological Health Sciences   (United States)

Author keywords

Feature reduction; feature selection; forestry; hyperspectral remote sensing; random forest; support vector machines (SVM); tree species classification

Indexed keywords

ALGORITHMS; BIODIVERSITY; CLASSIFICATION (OF INFORMATION); DECISION TREES; FEATURE EXTRACTION; FORESTRY; GENETIC ALGORITHMS; LEAST SQUARES APPROXIMATIONS; WATER ABSORPTION;

AIRBORNE HYPERSPECTRAL DATA; CLASSIFICATION PERFORMANCE; FEATURE REDUCTION; FEATURE SELECTION ALGORITHM; HYPERSPECTRAL REMOTE SENSING; PARTIAL LEAST SQUARE (PLS); RANDOM FORESTS; TREE SPECIES;

SUPPORT VECTOR MACHINES;

ABSORPTION; BIODIVERSITY; BIOMASS; COMMUNITY COMPOSITION; FORESTRY; GENETIC ALGORITHM; HABITAT QUALITY; IMAGE CLASSIFICATION; MAPPING; REMOTE SENSING; SPECTRAL ANALYSIS; TREE;

CENTRAL EUROPE;

EID: 84905918062     PISSN: 19391404     EISSN: 21511535     Source Type: Journal    
DOI: 10.1109/JSTARS.2014.2329390     Document Type: Article

References (89)

1. P. Gong, R. Pu, and B. Zu, "Conifer species recognition: An exploratory analysis of in situ hyperspectal data," Remote Sens. Environ., vol. 62, no. 2, pp. 189-200, 1997. (Pubitemid 28091206)
2. T. Jones, N. C. Coops, and T. Sharma, "Assessing the utility of airborne hyperspectral and LiDAR data for species distribution mapping in the coastal Pacific Northwest, Canada," Remote Sens. Environ., vol. 114, no. 12, pp. 2841-2852, 2010.
3. L. C. Plourde, S. V. Ollinger, M. Smith, and M. E. Martin, "Estimating species abundance in northern temperate forest using spectral mixture analysis," Photogramm. Eng. Remote Sens., vol. 73, no. 7, pp. 829-840, 2007. (Pubitemid 47025751)
4. M. Dalponte, L. Bruzzone, and D. Gianelle, "Tree species classification in the southern Alps with very high geometrical resolution multispectral and hyperspectral data," in Proc. IEEE GRSS Workshop Hyperspectral Image Signal Process. Conf. (WHISPERS'11), Lisbon, Portugal, Jun. 6-9, 2011, pp. 1-4.
5. M. Förster, A. Frick, H. Walentowski, and B. Kleinschmit, "Approaches to utilising Quickbird-data for the monitoring of NATURA 2000 habitats," Commun. Ecol., vol. 9, pp. 155-168, 2008.
6. E. Adam, O. Mutanga, and D. Rugege, "Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: A review," Wetlands Ecol. Manag., vol. 18, no. 3, pp. 281-296, 2010.
7. E. Belluco et al., "Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing," Remote Sens. Environ., vol. 105, no. 1, pp. 54-67, 2006. (Pubitemid 44585025)
8. S. L. Ustin, D. A. Roberts, J. A.Gamon, G. P. Asner, and R. O. Green, "Using image spectroscopy to study ecosystem processes and properties," Bioscience, vol. 54, no. 6, pp. 523-534, 2004. (Pubitemid 38751838)
9. H. Buddenbaum, M. Schlerf, and J. Hill, "Classification of coniferous tree species and age classes using hyperspectral data and geostatistical methods," Int. J. Remote Sens., vol. 26, no. 24, pp. 5453-5465, 2005. (Pubitemid 43878391)
10. M. Pal and G. M. Foody, "Feature selection for classification of hyperspectral data by SVM," IEEE Trans. Geosci. Remote Sens., vol. 48, no. 5, pp. 2297-2307, May 2010.
11. G. F. Hughes, "On the mean accuracy of statistical pattern recognizers," IEEE Trans. Inf. Theory, vol. 14, no. 1, pp. 55-63, Jan. 1968.
12. T. Key, T. A. Warner, J. B. McGraw, and M. A. Fajvan, "A comparison of multispectral and multitemporal information in high spatial resolution imagery for classification of individual tree species in a temperate hardwood forest," Remote Sens. Environ., vol. 75, no. 1, pp. 100-112, 2001. (Pubitemid 32139670)
13. M. L. Clark, D. A. Roberts, and D. B. Clark, "Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales," Remote Sens. Environ., vol. 96, no. 3-4, pp. 375-398, 2005. (Pubitemid 40912438)
14. L. Wang and P. Sousa, "Distinguishing mangrove species with laboratory measurements of hyperspectral leaf reflectance," Int. J. Remote Sens., vol. 30, no. 5, pp. 1267-1281, 2009.
15. M. Boschetti, L. Boschetti, S. Oliveri, L. Casati, and I. Canova, "Tree species mapping with airborne hyper-spectral MIVIS data: The Ticino Park study case," Int. J. Remote Sens., vol. 28, no. 6, pp. 1251-1261, 2007. (Pubitemid 46455018)
16. C. Yang, J. H. Everitt, R. S. Fletcher, R. R. Jensen, and P. W. Mausel, "Evaluating hyperspectral imagery for mapping black mangrove along the south Texas Gulf Coast," Photogramm. Eng. Remote Sens., vol. 75, no. 4, pp. 425-435, 2009.
17. A. R. Webb and K. D. Copsey, Statistical Pattern Recognition, 3rd ed. Hoboken, NJ, USA: Wiley, 2011, 666p, ISBN: 978-0-470-68227-2.
18. B. Datt, "Recognition of eucalyptus forest species using hyperspectral reflectance data," in T. I. Stein (Ed.), Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), Honolulu, HI, USA, Jul. 24-28, 2000, vol. 4, pp. 1405-1407. (Pubitemid 32019269)
19. T. Fung, H. F. Y. Ma, and W. L. Siu, "Band selection using hyperspectral data of subtropical tree species," Geocarto Int., vol. 18, no. 4, pp. 3-11, 2003.
20. J. C.-W. Chan and D. Paelinckx. "Evaluation of random forest, and Adaboost tree-based ensemble classification, and spectral band selection for ecotope mapping using airborne hyperspectral imagery," Remote Sens. Environ., vol. 112, no. 6, pp. 2999-3011, 2008.
21. A. Ghosh, F. E. Fassnacht, P. K. Joshi, and B. Koch, "A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales," Int. J. Appl. Earth Observ. Geoinf., vol. 26, pp. 49-63, 2014.
22. L. Liu, Y. Pang, W. Fan, Z. Li, and M. Li, "Fusion of airborne hyperspectral and LiDAR data for tree species classification in the temperate forest of Northeast China," in Proc. 19th Int. Conf. Geoinformat., Shanghai, China, Jun. 24-26, 2011, pp. 1-5.
23. R. Sugumaran and M. Voss, "Object-oriented classification of LiDARfused hyperspectral imagery for tree species identification in an Urban Environment," in Proc. Urban Remote Sens. Joint Event, Paris, France, Apr. 11-13, 2007, pp. 1-6.
24. M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, "The role of spectral resolution, and classifier complexity in the analysis of hyperspectral images of forest areas," Remote Sens. Environ., vol. 113, no. 11, pp. 2345-2355, 2009.
25. K. Y. Peerbhay, O. Mutanga, and R. Ismail, "Commercial tree species discrimination using airborneAISA Eagle hyperspectral imagery and partial least squared discriminant analysis (PLS-DA) in KwaZulu-Natal, South Africa," ISPRS J. Photogramm. Remote Sens., vol. 79, pp. 19-28, 2013.
26. F. E. Fassnacht, H. Latifi, and B. Koch, "An angular vegetation index for imaging spectroscopy data-Preliminary results on forest damage detection in the Bavarian National Park, Germany," Int. J. Appl. Earth Observ. Geoinf., vol. 19, pp. 308-321, 2012.
27. H. Latifi, A. Nothdurft, and B. Koch, "Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest: Application of multiple optical/LiDAR-derived predictors," Forestry, vol. 83, no. 4, pp. 395-407, 2010.
28. H. Latifi, F. Fassnacht, and B. Koch, "Airborne hyperspectral and LiDAR data fusion to describe forest structure," Remote Sens. Environ., vol. 121, pp. 10-25, 2012.
29. L. Naidoo, M. A. Cho, R. Mathieu, and G. Asner, "Classification of savanna tree species, in the Greater Kruger National Park region, by integrating hyperspectral and LiDAR data in a Random Forest data mining environment," ISPRS J. Photogramm. Remote Sens., vol. 69, pp. 167-179, 2012.
30. L. Breimann. (2003). Manual on Setting Up, Using, and Understanding Random Forests v4.0 [Online]. Available: http://oz.berkeley.edu/users/breiman/ Using-random-forests-v4.0.pdf, accessed on Apr. 16, 2014.
31. M. Dalponte, H. O. ∅rka, L. T. Ene, T. Gobakken, and E. Næsset, "Tree crown delineation and tree species classification in boreal forests using hyperspectral and ALS data," Remote Sens. Environ., vol. 140, pp. 306-317, 2014.
32. A. Ghiyamat, H. Z. M. Shafri, G. A. Mahdiraji, A. R. M. Shariff, and S. Mansor, "Hyperspectral discrimination of tree species with different classifications using single-and multiple-endmember," Int. J. Appl. Earth Observ. Geoinf., vol. 23, pp. 177-191, 2013.
33. A. Tillack, A. Clasen, B. Kleinschmit, and M. Förster, "Estimation of seasonal leaf area index in an alluvial forest using high resolution satellitebased vegetation indices," Remote Sens. Environ., vol. 141, pp. 52-63, 2014.
34. H. Buddenbaum, P. Pueschel, M. Stellmes, W. Werner, and J. Hill, "Measuring water and chlorophyll content on the leaf and canopy scale," EARSeL eProc., vol. 10, no. 1, pp. 66-72, 2011.
35. R. F. Kokaly and R. N. Clark, "Spectroscopic determination of leaf biochemistry using band-depths analysis of absorption features and stepwise linear regression," Remote Sens. Environ., vol. 67, no. 3, pp. 267-287, 1999. (Pubitemid 29360732)
36. G. A. Blackburn, "Hyperspectral remote sensing of plant pigments," J. Exp. Bot., vol. 58, no. 4, pp. 855-886, 2007.
37. R. L. King, C. Ruffin, F. E. LaMastus, and D. R. Shaw, "The analysis of hyperspectral data using Savitzky-Golay filtering-Practical issues 2," in Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), Hamburg, Germany, Jun. 28-Jul. 2, 1999, vol. 2, pp. 398-400. (Pubitemid 30538854)
38. A. Savitzky and M. J. E. Golay, "Smoothing and differentiation of data by simplified least-square procedures," Anal. Chem., vol. 36, no. 8, pp. 1627-1639, 1964.
39. S. Huber, M. Kneubühler, A. Psomas, K. Itten, and N. E. Zimmermann, "Estimating foliar biochemistry from hyperspectral data in mixed forest canopy," Forest Ecol. Mange., vol. 256, no. 3, pp. 491-501, 2008.
40. L. Ladha and T. Deepa, "Feature selection methods and algorithms," Int. J. Comput. Sci. Eng., vol. 3, no. 5, pp. 1787-1797, 2011.
41. M. Kuhn and K. Johnson, "Filter methods," in Applied Predictive Modeling. New York, NY, USA: Springer, 2013, pp. 499-500.
42. I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," J. Mach. Learn. Res., vol. 3, pp. 1157-1182, 2003.
43. L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees. Belmont, CA, USA: Wadsworth/Brooks, 1984.
44. J. H. Holland, Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. Ann Arbor, MI, USA: Univ. of Michigan Press, 1975.
45. C. Vaiphasa, A. K. Skidmore, W. F. de Boer, and T. Vaiphasa, "A hyperspectral band selector for plant species discrimination," ISPRS J. Photogramm. Remote Sens., vol. 62, no. 3, pp. 225-235, 2007. (Pubitemid 47043387)
46. V. Trevino and F. Falciani, "GALGO: An R package for multivariate variable selection using genetic algorithms," Bioinformatics, vol. 22, pp. 1154-1156, 2006.
47. R Core Team, R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing, 2012 [Online]. Available: http://www.R-project.org/, ISBN: 3-900051-07-0.
48. S. van der Linden and P. Hostert, "The influence of urban structures on impervious surface maps from airborne hyperspectral data," Remote Sens. Environ., vol. 113, no. 11, pp. 2298-2305, 2009.
49. R. Kohavi and G. H. John, "Wrappers for feature subset selection," Artif. Intell., vol. 97, pp. 273-324, 1997. (Pubitemid 127401107)
50. H. Wold, Estimation of Principal Components and Related Models by Iterative Least Squares. New York, NY, USA: Academic, 1966.
51. T. Mehmood, K. H. Liland, L. Snipen, and S. Sæbø, "A review of variable selection methods in partial least squares regression," Chemom. Intell. Lab. Syst., vol. 118, pp. 62-69, 2012.
52. M. Barker and W. Rayens, "Partial least squares for discrimination," J. Chemom., vol. 17, no. 3, pp. 166-173, 2003.
53. D. Nguyen and D. Rocke, "Multi-class cancer classification via partial least squares with gene expression profiles," Bioinformatics, vol. 18, no. 9, pp. 1216-1226, 2002.
54. D. Chung and S. Keles, "Sparse partial least squares classification for high dimensionaldata,"Stat. Appl. Genet. Mol. Biol.,vol.9, no.1, 2010, Article no. 17.
55. R. Tibshirani, "Regression shrinkage and selection via the lasso," J. Roy. Stat. Soc. B, vol. 58, no. 1, pp. 267-288, 1996.
56. A.-L. Boulesteix, "PLS dimension reduction for classification with microarray data," Stat. Appl. Genet. Mol. Biol., vol. 3, 2004, Article no. 33.
57. H. Chun and S. Kele\+, "Sparse partial least squares regression for simultaneous dimension reduction and variable selection," J. Roy. Stat. Soc. B (Stat. Methodol.), vol. 72, no. 1, pp. 3-25, 2010.
58. D. Chung, H. Chun, and S. Keles. (2012). "SPLS: Sparse partial least squares (SPLS) regression and classification," R Package Version 2.1-2 [Online]. Available: http://CRAN.R-project.org/package=spls
59. A. Frenich et al., "Wavelength selection method for multicomponent spectrophotometric determinations using partial least squares," Analyst, vol. 120, pp. 2787-2792, 1995.
60. R. O. Green, M. L. Eastwood, and O. Williams, "A transformation for ordering multispectral data in terms of image quality with implications for noise removal," IEEE Trans. Geosci. Remote Sens., vol. 26, no. 1, pp. 65-74, Jan. 1988.
61. F. E. Fassnacht, H. Weinacker, and B. Koch, "Automatic forest area extraction from imaging spectroscopy data using an extended NDVI," in Proc. 7th EARSeL Workshop Imaging Spectrosc., Edinburgh, Scotland, Apr. 11-13, 2011, pp. 1-13.
62. R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Proc. 14th Int. joint Conf. Artif. Intell., Montreal, Canada, Aug. 20-25, 1995, vol. 2, pp. 1137-1143.
63. M. Kuhn. (2012). The Caret Package [Online]. Available: http://cran.r-project.org/web/packages/caret/caret.pdf
64. P. S. Thenkabail, E. A. Enclona, M. S. Ashton, C. Legg, and M. J. De Dieu, "Hyperion, IKONOS, ALI, and sensors in the study of African reinorests," Remote Sens. Environ., vol. 90, pp. 23-43, 2004. (Pubitemid 38225344)
65. S. Sawilowsky, "Mann-Whitney U test (Wilcoxon Rank-Sum test)," in Encyclopedia of Measurement and Statistics, N. Salkind, Ed. Newbury Park, CA, USA: SAGE, 2007, pp. 566-568.
66. A. Liaw and M. Wiener, "Classification and regression by random forest," R News, vol. 2, no. 3, pp. 18-22, 2002.
67. A. Karatzoglou, A. Smola, K. Hornik, and A. Zeileis, "Kernlab-An S4 package for Kernel methods in R," J. Stat. Software, vol. 11, pp. 1-20, 2004.
68. R. J. Hijmans and J. van Etten. (2012). "Raster: Geographic analysis and modeling with raster data," R Package Version 2.0-12 [Online]. Available: http://CRAN.R-project.org/package=raster
69. T. H. Keitt, R. Bivand, E. Pebesma, and B. Rowlingson. (2012). RGDAL: Bindings for the geospatial data abstraction library, R Package Version 0.7-20 [Online]. Available: http://CRAN.R-project.org/package=rgdal
70. M. Kuhn, "Building predictive models in R using caret package," J. Stat. Software, vol. 28, no. 5, pp. 1-26, 2008.
71. F. Melgani and L. Bruzzone, "Classification of hyperspectral remote sensing images with support vector machines," IEEE Trans. Geosci. Remote Sens., vol. 42, no. 8, pp. 1778-1790, Aug. 2004.
72. C. Huang, L. S. Davis, and J. R. Townshend, "An assessment of support vector machines for land cover classification," Int. J. Remote Sens., vol. 23, no. 4, pp. 725-749, 2002. (Pubitemid 34119904)
73. C. Schuster, M. Förster,and B. Kleinschmit," Testing therededge channel for improving land-use classifications based on high-resolution multi-spectral satellite data," Int. J. Remote Sens., vol. 33, no. 17, pp. 5583-5599, 2012.
74. C. H. Chen and P. G. P. Ho, "Statistical pattern recognition in remote sensing," Pattern Recognit., vol. 41, no. 9, pp. 2731-2741, 2008.
75. J. Heinzel and B. Koch, "Investigating multiple data sources for tree species classification in temperate forest and use for single tree delineation," Int. J. Appl. Earth Observ. Geoinf., vol. 18, pp. 101-110, 2012.
76. B. Waske, S. Van der Linden, J. A. Benediktsson, A. Rabe, and P. Hostert, "Sensitivity of support vector machines to random feature selection in classification of hyperspectral data," IEEE Trans. Geosci. Remote Sens., vol. 48, no. 7, pp. 2880-2889, Jul. 2010.
77. C. J. C. Burges, "A tutorial on support vector machines for pattern recognition," Data Min. Knowl. Discovery, vol. 2, pp. 121-167, 1998. (Pubitemid 128695475)
78. D. C. Duro, S. E. Franklin, and M. G. Dube, "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., vol. 118, pp. 259-272, 2012.
79. E. Alpaydin, Introduction to Machine Learning. Cambridge, MA, USA: MIT Press, 2004.
80. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5-32, 2001. (Pubitemid 32933532)
81. V. F. Rodriguez-Galiano, B. Ghimire, J. Rogan, M. Chica-Olmo, and J. P. Rigol-Sanchez, "An assessment of the effectiveness of a random forest classifier for land-cover-classification," ISPRS J. Photogramm. Remote Sens., vol. 67, pp. 93-104, 2012.
82. A. Ghosh and P. K. Joshi, "A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high resolution WorldView 2 imagery," Int. J. Appl. Earth Observ. Geoinf., vol. 26, pp. 298-311, 2014.
83. D. R. Cutler et al., "Random forests for classification in ecology," Ecology, vol. 88, pp. 2783-2792, 2007. (Pubitemid 351345081)
84. B. Waske, J. A. Benediktsson, and J. R. Sveinsson, "Random Forest classification of remote sensing data," in Signal and Image Processing for Remote Sensing, C. H. Chen, Ed. Boca Raton, FL, USA: CRC Press, 2012, pp. 365-374.
85. L. Breiman and A. Cutler. (2007). Random forests-Classification Description [Online]. Available: http://www.stat.berkeley.edu/~breiman/ RandomForests/cc-home.htm, accessed on Oct. 21, 2013.
86. V. Heikkinen, T. Tokola, J. Parkkinen, I. Korpela, and T. Jääskelainen, "Simulated multispectral imagery for tree species classification using support vector machines," IEEE Trans. Geosci. Remote Sens., vol. 48, pp. 1355-1364, 2010.
87. P. Pant et al., "Evaluation of simulated bands in airborne optical sensors for tree species identification," Remote Sens. Environ., vol.138, pp.27-37, 2013.
88. A. Pope and W. G. Rees, "Impact of spatial, spectral, and radiometric properties of multispectral imagery on glacier surface classification," Remote Sens. Environ., vol. 141, pp. 1-13, 2014.
89. S. Zacharias et al., "A network of terrestrial environmental observatories in Germany," Vadose Zone J., vol. 10, pp. 955-973, 2011.