A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales

International Journal of Applied Earth Observation and Geoinformation

Volumn 26, Issue 1, 2014, Pages 49-63

  Ghosh, Aniruddha ^a   Fassnacht, Fabian Ewald ^b   Joshi, P K ^a   Kochb, Barbara ^a  

^a TERI UNIVERSITY   (India)

^b UNIVERSITY OF FREIBURG   (Germany)

Author keywords

Hyperspectral; nDSM; Random forest (RF); Scale; Support vector machines (SVM); Tree species classificationa

Indexed keywords

IMAGE ANALYSIS; IMAGE CLASSIFICATION; LIDAR; MAPPING; PIXEL; RANDOM WALK METHOD; REMOTE SENSING; SATELLITE SENSOR; SENSOR; SPATIAL ANALYSIS; SPATIAL DATA; SPATIAL RESOLUTION; SPECTRAL ANALYSIS; TREE; VEGETATION INDEX;

EUROPE;

EID: 84897585667     PISSN: 15698432     EISSN: 1872826X     Source Type: Journal    
DOI: 10.1016/j.jag.2013.05.017     Document Type: Article

References (71)

1. Anderson, J.E., Plourde, L.C., Martin, M.E., Braswell, B.H., Smith, M.-L., Dubayah, R.O.,Hofton, M.A., Blair, J.B., 2008. Integrating waveform lidar with hyperspectral imagery for inventory of a northern temperate forest. Remote Sensing of Environment 112 (4), 1856-1870.
2. Angelo, J.J., Duncan, B.W., Weishampel, J.F., 2010. Using Lidar-derived vegetationprofiles to predict time since fire in an oak scrub landscape in East-CentralFlorida. Remote Sensing 2, 514-525.
3. Asner, G.P., Knapp, D.E., Kennedy-Bowdoin, T., Jones, M.O., Martin, R.E., Boardman,J., Hughes, R.F., 2008. Invasive species detection in Hawaiian rainforests usingairborne imaging spectroscopy and LiDAR. Remote Sensing of Environment 112(5), 1942-1955.
4. Belluco, E., Camuffo, M., Ferrari, S., Modenese, L., Silvestri, S., Marani, A., 2006. Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing.Remote Sensing of Environment 105, 54-67.
5. Bian, L., 2005. Multiscale nature of spatial data in scaling up environmental models.In: Quattrochi, D.A., Goodchild, M.F. (Eds.), Scale in Remote Sensing and GIS.Lewis Publishers/CRC Press.
6. Braga-Neto, U.M., Dougherty, E.R., 2004. Is cross-validation valid for small samplemicroarray classification? Bioinformatics 20, 374-380.
7. Breiman, L., 2001. Random forest. Machine Learning 45 (1), 5-32.
8. Breiman, L., Cutler, A., 2004. Random Forests. Available on http://statwww.berkeley.edu/users/breiman/RandomForests/cc home.htm
9. Camps-Valls, G., Bruzzone, L. (Eds.), 2009. Kernel Methods for Remote Sensing DataAnalysis. Wiley & Sons.
10. Castillo, M., Rivard, B., Sánchez-Azofeifa, A., Calvo-Alvarado, J., Dubayah, R., 2012. LiDAR remote sensing for secondary tropical dry forest identification. RemoteSensing of Environment 121, 132-143.
11. Cao, C., Lam, N.S.-N., 2005. Understanding the scale and resolution effects in remotesensing and GIS. In: Quattrochi, D.A., Goodchild, M.F. (Eds.), Scale in RemoteSensing and GIS. Lewis Publishers/CRC Press.
12. Chen, C.H., Ho, P.G.P., 2008. Statistical pattern recognition in remote sensing. PatternRecognition 41, 2731-2741.
13. Cho, M.A., Debba, P., Mathieu, R., Naidoo, L., Van Aardt, J., Asner, G.P., 2010. Improvingdiscrimination of savanna tree species through a multiple-endmember spectralangle mapper approach: canopy-level analysis. IEEE Transactions on Geoscienceand Remote Sensing 48 (2), 4133-4142.
14. Cho, M.A., Mathieu, R., Asner, G.P., Naidoo, L., Van Aardt, J.A., Ramoelo, A., Debba,P., Wessels, K., Main, R., Smit, I.P., Erasmus, B.F., 2012. Mapping tree speciescomposition in South African savannas using an integrated airborne spectraland LiDAR system. Remote Sensing of Environment 125, 214-226.
15. Clark, M.L., Roberts, D.A., Clark, D.B., 2005. Hyperspectral discrimination of tropicalrain forest tree species at leaf to crown scales. Remote Sensing of Environment96, 375-398.
16. Congalton, R.G., Green, K., 1999. Assessing the Accuracy of Remotely Sensed Data:Principles and Practices. Lewis Publishers, Boca Raton, FL, pp. 137.
17. Colgan, M.S., Baldeck, C.A., Féret, J-B., Asner, G.P., 2012. Mapping savanna treespecies at ecosystem scales using support vector machine classification andBRDF correction on airborne hyperspectral and LiDAR data. Remote Sensing 4, 3462-3480.
18. Cortes, C., Vapnik, V., 1995. Support vector networks. Machine Learning 20 (3),273-297.
19. Dalponte, M., Bruzzone, L., Gianelle, D., 2008. Fusion of hyperspectral and LIDARremote sensing data for the classification of complex forest areas. IEEE Transactions on Geoscience and Remote Sensing 46 (5), 1416-1427.
20. Dalponte, M., Bruzzone, L., Vescovo, L., Gianelle, D., 2009. The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forestareas. Remote Sensing of Environment 115, 2345-2355.
21. Dalponte, M., Bruzzone, L., Gianelle, D., 2012. Tree species classification in theSouthern Alps based on the fusion of very high geometrical resolution multi-spectral/hyperspectral images and LiDAR data. Remote Sensing of Environment123, 258-270.
22. Datt, B., 2000. Recognition of eucalyptus forest species using hyperspectralreflectance. In: Proceedings of the IGARSS Geoscience and Remote Sensing Symposium, IEEE International, vol. 4, pp. 1405-1407.
23. Donoghue, D.N.M., Watt, P.J., Cox, N.J., Wilson, J., 2007. Remote sensing of speciesmixtures in conifer plantations using LiDAR height and intensity data. RemoteSensing of Environment 110 (4), 509-522.
24. Efron, B., Tibshirani, R.J., 1994. An Introduction to the Bootstrap. Chapman & Hall/CRCMonographs on Statistics & Applied Probability.
25. ENVI (The Environment for Visualizing Images), 2010. V.4.7. Exelis Visual Information Solutions. ENVI, Boulder, Colorado.
26. Fassnacht, F.E., Weinacker, H., Koch, B., 2011. Automatic forest area extraction fromimaging spectroscopy data using an extended NDVI. In: 7th EARSeL Workshopon Imaging Spectroscopy, Edinburgh, Scotland.
27. Fassnacht, F.E., Latifi, H., Koch, B., 2012. An angular vegetation index for imagingspectroscopy data-preliminary results on forest damage detection in the Bavarian National Park, Germany. International Journal of Applied Earth Observationand Geoinformation 19, 308-321.
28. Franklin, S.E., 2001. Remote Sensing for Sustainable Forest Management. CRC Press.
29. Foody, G.M., 2004. Thematic map comparisons: evaluating the statistical significance of differences in classification accuracy. Photogrammetric Engineeringand Remote Sensing 70 (5), 627-633.
30. Goodenough, D.G., Duk, A., Niemann, K.O., Jay, P.S., Hao, C., Tian, H., Murdock, M.,West, C., 2003. Processing hyperion and ALI for forest classification. IEEE Transactions on Geoscience and Remote Sensing 41, 1321-1331.
31. Green, A.A., Berman, M., Switzer, P., Craig, M.D., 1988. A transformation for orderingmultispectral data in terms of image quality with implications for noise removal.IEEE Transactions on Geoscience and Remote Sensing 26 (1), 65-74.
32. Ham, J.S., Chen, Y., Crawford, M.M., Ghosh, J., 2005. Investigation of the randomforest framework for classification of hyperspectral data. IEEE Transactions onGeoscience and Remote Sensing 43 (3).
33. Heinzel, J., Koch, B., 2012. Investigating multiple data sources for tree speciesclassification in temperate forest and use for single tree delineation. International Journal of Applied Earth Observation and Geoinformation 18,101-110.
34. Hijmans, R.J., Etten, J.v., 2012. Raster: Geographic Data Analysis and Modeling. Rpackage version 2. 0-41, Available on http://CRAN.R-project.org/package=raster
35. Holmgren, P., Thuresson, T., 1998. Satellite remote sensing for forestry planning - areview. Scandinavian Journal of Forest Research 13 (1-4).
36. Huang, C., Davis, L.S., Townshend, J.R., 2002. An assessment of support vectormachines for land cover classification. International Journal of Remote Sensing23, 725-749.
37. Hughes, G.F., 1968. On the mean accuracy of statistical pattern recognizers. IEEETransactions on Information Theory 14 (1), 55-63.
38. Jones, T., Coops, N.C., Sharma, T., 2010. Assessing the utility of airborne hyperspectraland LiDAR data for species distribution mapping in the coastal Pacific Northwest,Canada. Remote Sensing of Environment 114, 2841-2852.
39. Karatzoglou, A., Smola, A., Hornik, K., Zeileis, A., 2004. Kernlab - An S4 Package forKernel Methods in R. Journal of statistical software 11, 1-20.
40. Kuhn, M., 2008. Building predictive models in r using the caret package. Journal ofStatistical Software 28 (5), 1-26.
41. Kuhn, M., 2012. Caret: Classification and Regression Training. R package version5. 15-052, Available on http://CRAN.R-project.org/package=caret (contributionsfrom Jed Wing, Steve Weston, Andre Williams, Chris Keefer, Allan Engelhardtand Tony Cooper).
42. Kohavi, R., 1995. A study of cross-validation and bootstrap for accuracy estimationand model selection. In: International Joint Conference on Artificial Intelligence(IJCAI).
43. Leckie, D.G., Tinis, S., Nelson, T., Burnett, C., Gaugeon, F.A., Cloney, E., Paradine,D., 2005. Issues in species classification of trees in old growth conifer stands.Canadian Journal of Remote Sensing 31 (2), 175-190.
44. Liaw, A., Wiener, M., 2002. Classification and regression by random forest. R News2, 18-22.
45. Lim, K., Treitz, P., Wulder, M., St-Onge, B., Flood, M., 2003. LiDAR remote sensing offorest structure. Progress in Physical Geography 27 (1), 88-106.
46. Linke, J., Matthew, G.B., Michael, B.L., Franklin, S.E., 2006. Introduction: structure,function, and change of forest landscapes. In: Franklin, S.E., Wulder, M.M. (Eds.),Understanding Forest Disturbance and Spatial Pattern: Remote Sensing and GISApproaches. CRC Press/Taylor & Francis Group.
47. Mairs, J.W., 1976. The use of remote sensing techniques to identify potential naturalareas in Oregon. Biological Conservation 9 (4), 259-266.
48. Marceau, D.J., Howarth, P.J., Gratton, D.J., 1994a. Remote sensing and the measurement of geographical entities in a forested environment. 1.The scale and spatialaggregation problem. Remote Sensing of Environment 49 (103-114).
49. Marceau, D.J., Gratton, D.J., Fournier, R.A., Fortin, J.-P., 1994b. Remote sensing and themeasurement of geographical entities in a forested environment. 2. The optimalspatial resolution. Remote Sensing of Environment 49, 105-117.
50. Martin, M.E., Newman, S.D., Aber, J.D., Congalton, R.G., 1998. Determining forestspecies composition using high spectral resolution remote sensing data. RemoteSensing of Environment 65, 249-254.
51. Mcnemar, Q., 1947. Note on the sampling error of the difference between correlatedproportions or percentages. Psychometrika, 153-157.
52. Melgani, F., Bruzzone, L., 2004. Classification of hyperspectral remote sensing imageswith support vector machines. IEEE Transactions on Geoscience and RemoteSensing 42 (8), 1778-1790.
53. Mountrakis, G., Im, J., Ogole, C., 2011. Support vector machines in remote sensing: Areview. ISPRS Journal of Photogrammetry and Remote Sensing 66 (3), 247-259.
54. Naidoo, L., Cho, M.A., Mathieu, R., Asner, G., 2012. Classification of savanna treespecies, in the Greater Kruger National Park region, by integrating hyperspectraland LiDAR data in a random forest data mining environment. ISPRS Journal ofPhotogrammetry and Remote Sensing 69, 167-179.
55. Onojeghuo, A.O., Blackburn, G.A., 2011. Optimising the use of hyperspectral andLiDAR data for mapping reedbed habitats. Remote Sensing of Environment 115, 2025-2034.
56. Pal, M., 2005. Random forest classifier for remote sensing classification. InternationalJournal of Remote Sensing 26 (1).
57. Pal, M., Mather, M., 2005. Support vector machines for classification in remotesensing. International Journal of Remote Sensing 26 (5), 1007-1011.
58. R Core Team, 2012. R: A Language and Environment for Statistical Computing.R Foundation for Statistical Computing, Vienna, Austria, ISBN 3-900051-07-0,http://www.R-project.org/
59. Richter, R., Schläpfer, D., 2011. Atmospheric/Topographic Correction for AirborneImagery. DLR report DLR-IB 565-02/11, Wessling, Germany.
60. Rogaß, C., Spengler, D., Bochow, M., Segl, K., Lausch, A., Doktor, D., Roessner, S., Behling, R., Wetzel, H.-U., Kaufmann, H., 2011. Reduction ofradiometric miscalibration-applications to pushbroom sensors. Sensors 11, 6370-6395.
61. Sarrazin, D., Van Aardt, J.A., Asner, G.P., Mcglinchy, J., Messinger, D.W., Wu, J., 2011.Fusing small-footprint waveform LiDAR and hyperspectral data for canopy-levelspecies classification and herbaceous biomass modeling in savanna ecosystems.Canadian Journal of Remote Sensing 37 (6), 653-665.
62. Thenkabail, P.S., Enclona, E.A., Ashton, M.S., Legg, C., Jean, M.D.D., 2004. Hyperion, IKONOS, ALI, and ETM+ sensors in the study of African rainforests. RemoteSensing of Environment 90, 23-43.
63. Ustin, S.L., Roberts, D.A., Gamon, J.A., Asner, G.P., Green, R.O., 2004. Using imagespectroscopy to study ecosystem processes and properties. Bioscience 54,523-534.
64. vanAardt, J.A., Wynne, R.H., 2007. Examining pine spectral separability using hyper-spectral data from an airborne sensor: an extension of field-based results.International Journal of Remote Sensing 28 (2), 431-436.
65. van der Meer, F.D., van der Werff, H.M.A., van Ruitenbeek, F.J.A., Hecker, C.A., Bakker,W.H., Noomen, M.F., van der Meijde, M., Carranza, E.J.M., Smeth J.B. d. Woldai, T.,2012. Multi- and hyperspectral geologic remote sensing: a review. InternationalJournal of Applied Earth Observation and Geoinformation 14, 112-128.
66. Vapnik, V.N., 1995. The Nature of Statistical Learning Theory. Springer.
67. Waske, B., Benediktsson, J.A., Sveinsson, J.R., 2012. Random Forest classificationof Remote Sensing data. In: Chen, C.H. (Ed.), Signal and Image Processing forRemote Sensing. CRC Press, pp. 365-374.
68. Weinacker, H., Koch, B., Weinacker, R., 2004a. Treevis - a software system for simultaneous 3D real time visualization of DTM, laser raw data,multispectral data, simple tree and building models. In: Proceedings ofthe ISPRS Working Group VIII/2 Laser-Scanners for Forest and LandscapeAssessment, Freiburg, Germany, vol. 90.
69. Weinacker, H., Koch, B., Heyder, U., Weiancker, R., 2004b. Development of filtering, segmentation and modelling modules for lidar and multispectral dataas a fundament of an automatic forest inventory system. In: Proceedings ofthe International Conference. Laser-Scanners for Forest and Landscape Assessment - Instruments, Processing Methods and Applications, Freiburg imBreisgau,Germany.
70. Yang, C., Everitt, J.H., Fletcher, R.S., Jensen, R.R., Mausel, P.W., 2009. EvaluatingAISA + hyperspectral Imagery for mapping black mangrove along the SouthTexas Gulf Coast. Photogrammetric Engineering and Remote Sensing 75 (4),425-435.
71. Zhang, C., Xie, Z., 2012. Combining object-based texture measures with a neuralnetwork for vegetation mapping in the everglades from hyperspectral imagery.Remote Sensing of Environment 124, 310-320.