Classification of Australian native forest species using hyperspectral remote sensing and machine-learning classification algorithms

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

Volumn 7, Issue 6, 2014, Pages 2481-2489

  Shang, Xiao ^a   Chisholm, Laurie A ^a  

^a UNIVERSITY OF WOLLONGONG   (Australia)

Author keywords

Forestry; remote sensing

Indexed keywords

ADAPTIVE BOOSTING; DECISION TREES; FORESTRY; IMAGE RETRIEVAL; REMOTE SENSING; SUPPORT VECTOR MACHINES;

BIOPHYSICAL CHARACTERISTICS; CLASSIFICATION ACCURACY; CLASSIFICATION ALGORITHM; CLASSIFICATION RESULTS; HYPERSPECTRAL REMOTE SENSING; HYPERSPECTRAL REMOTE SENSING DATA; LINEAR DISCRIMINANT ANALYSIS; SPECTRAL REFLECTANCES;

ALGORITHMS;

ALGORITHM; FORESTRY; IMAGE CLASSIFICATION; NATIVE SPECIES; REMOTE SENSING; SPECTRAL ANALYSIS; SPECTRAL REFLECTANCE;

AUSTRALIA; BEECROFT PENINSULA; NEW SOUTH WALES;

EUCALYPTUS;

EID: 84905906990     PISSN: 19391404     EISSN: 21511535     Source Type: Journal    
DOI: 10.1109/JSTARS.2013.2282166     Document Type: Article

References (63)

1. A. Banskota et al., "Improving within-genus tree species discrimination using the discrete wavelet transform applied to airborne hyperspectral data," Int. J. Remote Sens., vol. 32, pp. 3551-3563, 2011.
2. K. Barry et al., "Characterizing eucalypt leaf phenology and stress with spectral analysis," in Innovations in Remote Sensing and Photogrammetry. Berlin, Heidelberg: Springer, 2009, pt. 3, pp. 193-209.
3. N. C. Coops et al., "Prediction of eucalypt foliage nitrogen content from satellite-derived hyperspectral data," IEEE Trans. Geosci. Remote Sens., vol. 41, pp. 1338-1346, Jun. 2003.
4. S. Delalieux et al., "Detection of biotic stress (Venturia inaequalis) in apple trees using hyperspectral data: Non-parametric statistical approaches and physiological implications," Eur. J. Agron., vol. 27, pp. 130-143, 2007. (Pubitemid 46795449)
5. S. M. Kochubey and T. A. Kazantsev, "Changes in the first derivatives of leaf reflectance spectra of various plants induced by variations of chlorophyll content," J. Plant Physiol., vol. 164, pp. 1648-1655, Dec. 2007. (Pubitemid 350087319)
6. I.Moorthy et al., "Estimating chlorophyll concentration in conifer needles with hyperspectral data: An assessment at the needle and canopy level," Remote Sens. Environ., vol. 112, pp. 2824-2838, 2008.
7. C. Wu et al., "Estimating chlorophyll content from hyperspectral vegetation indices: Modeling and validation," Agricult. Forest Meteorol., vol. 148, pp. 1230-1241, 2008.
8. I. Keramitsoglou et al., "Reliable, accurate and timely forest mapping for wildfire management using ASTER and Hyperion satellite imagery," Forest Ecol. Manag., vol. 255, pp. 3556-3562, 2008.
9. G. G. Wang, "Fire severity in relation to canopy composition within burned boreal mixedwood stands," Forest Ecol. Manag., vol. 163, pp. 85-92, 2002. (Pubitemid 34689011)
10. R. Lucas et al., "Classification of Australian forest communities using aerial photography, CASI and HyMap data," Remote Sens. Environ., vol. 112, pp. 2088-2103, 2008.
11. M. Kalacska et al., "Hyperspectral discrimination of tropical dry forest lianas and trees: Comparative data reduction approaches at the leaf and canopy levels," Remote Sens. Environ., vol. 109, pp. 406-415, 2007. (Pubitemid 47008921)
12. L.Wang andW. P. Sousa, "Distinguishing mangrove species with laboratory measurements of hyperspectral leaf reflectance," Int. J. Remote Sens., vol. 30, pp. 1267-1281, 2009.
13. N. Coops et al., "Assessment of crown condition in eucalypt vegetation by remotely sensed optical indices," J. Environm. Quality, vol. 33, pp. 956-964, 2004. (Pubitemid 38661586)
14. N. Goodwin et al., "Classifying eucalyptus forests with high spatial and spectral resolution imagery: An investigation of individual species and vegetation communities," Austr. J. Botany, vol. 53, pp. 337-345, 2005. (Pubitemid 41112798)
15. L. Kumar, "A comparison of reflectance characteristics of some Australian eucalyptus species based on high spectral resolution data-Discriminating using the visible and NIR regions," J. Spatial Sci., vol. 52, pp. 51-64, Dec. 2007.
16. L. Kumar et al., "Leaf level experiments to discriminate between eucalyptus species using high spectral resolution reflectance data: Use of derivatives, ratios and vegetation indices," Geocarto Int., pp. 1-18, 2010.
17. L. Kumar and A. K. Skidmore, "Use of derivative spectroscopy to identify regions of difference between some Australian eucalypt species," presented at the 9th Australasian Remote Sensing and Photogrammetry Conf., Sydney, Australia, 1998.
18. B. Datt, "Remote sensing of foliar biochemistry and biophysical properties in eucalyptus species: Application of high spectral resolution reflectance measurement," Ph.D. dissertation, Sch. Geography, Univ. New South Wales, Sydney, Australia, 1999.
19. B. Datt, "Recognition of eucalyptus forest species using hyperspectral reflectance data," in Proc. IEEE IGARSS, 2000, pp. 1405-1407. (Pubitemid 32019269)
20. E. Adam et al., "Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: A review,"Wetlands Ecol. Manag., vol. 18, pp. 281-296, 2010.
21. G. Mountrakis et al., "Support vector machines in remote sensing: A review," ISPRS J. Photogramm. Remote Sens., vol. 66, pp. 247-259, 2011.
22. B.W. Heumann, "Satellite remote sensing of mangrove forests: Recent advances and future opportunities," Progr. Phys. Geogr., vol. 35, pp. 87-108, Feb. 1, 2011.
23. J.Wu and D. L. Peng, "Advances in researches on hyperspectral remote sensing forestry information-extracting technology," Spectroscopy and Spectral Analysis, vol. 31, pp. 2305-2312, Sep. 2011
24. 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, pp. 2999-3011, 2008.
25. M. Pal, "Random forest classifier for remote sensing classification," Int. J. Remote Sens., vol. 26, pp. 217-222, 2005. (Pubitemid 40198661)
26. M. Pal and P. M. Mather, "Support vector machines for classification in remote sensing," Int. J. Remote Sens., vol. 26, pp. 1007-1011, 2005. (Pubitemid 40231241)
27. V. Heikkinen et al., "Simulated multispectral imagery for tree species classification using support vector machines," IEEE Trans. Geosci. Remote Sens., vol. 48, pp. 1355-1364, 2010.
28. L. Su et al., "Support vector machines for recognition of semi-arid vegetation types using MISR multi-angle imagery," Remote Sens. Environ., vol. 107, pp. 299-311, 2007. (Pubitemid 46241275)
29. S. E. Sesnie et al., "The multispectral separability of Costa Rican rainforest types with support vector machines and Random Forest decision trees," Int. J. Remote Sens., vol. 31, pp. 2885-2909, 2010.
30. A. C. Braun et al., "Support vector machines for vegetation classification-A revision," Photogrammetrie Fernerkundung Geoinformation, pp. 273-281, 2010.
31. M. D. Wilson et al., "Classification of contamination in salt marsh plants using hyperspectral reflectance," IEEE Trans. Geosci. Remote Sens., vol. 42, pp. 1088-1095, 2004.
32. E. M. Adam et al., "Discriminating the papyrus vegetation (Cyperus papyrus L.) and its co-existent species using random forest and hyperspectral data resampled to HYMAP," Int. J. Remote Sens., vol. 33, pp. 552-569, 2012.
33. N. Skelton and P. Adam, Beecroft Peninsula Vegetation Survey, For ANCA/ERIN and the Department of Defence, GIS Environmental Consultants, 1994.
34. Government of New South Wales, Plan of Management: Jervis Bay National Park and Woollamia Nature Reserve, Dept. Environment, Climate Change and Water. Sydney, Australia, 2011.
35. T. Cocks et al., "The Hymap(tm) airborne hyperspectral sensor: The system, calibration and performance," in Proc. 1st EARSEL Workshop on Imaging Spectroscopy, Zurich, Switzerland, 1998, pp. 37-42.
36. M. L. Clark et al., "Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales," Remote Sens. Environ., vol. 96, pp. 375-398, 2005. (Pubitemid 40912438)
37. Vapnik and V. Naumovich, The Nature of Statistical Learning Theory. New York, NY, USA: Springer, 1995.
38. Q. Ge et al., "High efficient classification on remote sensing images based on SVM," International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 37, pp. 1011-1014, 2008.
39. C. Huang et al., "An assessment of support vector machines for land cover classification," Int. J. Remote Sens., vol. 23, pp. 725-749, 2002. (Pubitemid 34119904)
40. Y. Freund and R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting," J. Comput. Syst. Sci., vol. 55, pp. 119-139, 1997. (Pubitemid 127433398)
41. T. Hastie et al., The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York, NY, USA: Springer, 2001.
42. Y. Freund and R. E. Schapire, "A short introduction to boosting," J. Jpn. Soc. Artificial Intell., vol. 14, pp. 771-780, Sep. 1999.
43. L. Breiman, "Random forests," Machine Learning, vol. 45, pp. 5-32, 2001. (Pubitemid 32933532)
44. R. Genuer et al., "Variable selection using random forests," Pattern Recognit. Lett., vol. 31, pp. 2225-2236, 2010.
45. P. O. Gislason et al., "Random forests for land cover classification," Pattern Recognit. Lett., vol. 27, pp. 294-300, 2006. (Pubitemid 43063112)
46. T. V. Bandos et al., "Classification of hyperspectral images with regularized linear discriminant analysis," IEEE Trans. Geosci. Remote Sens., vol. 47, pp. 862-873, 2009.
47. C. Vaiphasa et al., "Tropical mangrove species discrimination using hyperspectral data: A laboratory study," Estuarine, Coastal and Shelf Science, vol. 65, pp. 371-379, 2005. (Pubitemid 41338151)
48. M. J. Santos et al., "Using hyperspectral remote sensing to detect and quantify southeastern pine senescence effects in red-cockaded woodpecker (Picoides borealis) habitat," Remote Sens. Environ., vol. 114, pp. 1242-1250, 2010.
49. R. L. Pu, "Broadleaf species recognition with in situ hyperspectral data," Int. J. Remote Sens., vol. 30, pp. 2759-2779, 2009.
50. W. C. Driscoll, "Robustness of the ANOVA and Tukey-Kramer statistical tests," Comput. Ind. Eng., vol. 31, pp. 265-268, 1996. (Pubitemid 126380034)
51. R. Pu et al., "Invasive species change detection using artificial neural networks and CASI hyperspectral imagery," Environ. Monitor. Assess., vol. 140, pp. 15-32, 2008. (Pubitemid 351486302)
52. C.-C. Chang and C.-J. Lin, "LIBSVM: A library for support vector machines," 2001 [Online]. Available: http://www.csie.ntu.edu.tw/~cjlin/ papers/libsvm.pdf
53. H. Z. M. Shafri et al., "Hyperspectral remote sensing of vegetation using red edge position techniques," Amer. J. Appl. Sci., vol. 3, pp. 1864-1871, 2006.
54. M. A. Cho and A. K. Skidmore, "A new technique for extracting the red edge position from hyperspectral data: The linear extrapolation method," Remote Sens. Environ., vol. 101, pp. 181-193, Mar. 2006. (Pubitemid 43343901)
55. N. C. Coops et al., "Chlorophyll content in eucalypt vegetation at the leaf and canopy scales as derived from high resolution spectral data," Tree Physiol., vol. 23, pp. 23-31, Jan. 2003. (Pubitemid 36260800)
56. B. Datt, "Remote sensing of chlorophyll a, chlorophyll b, chlorophyll a+b, and total carotenoid content in Eucalyptus leaves," Remote Sens. Environ., vol. 66, pp. 111-121, 1998. (Pubitemid 29360721)
57. B. Datt, "A new reflectance index for remote sensing of chlorophyll content in higher plants: Tests using Eucalyptus leaves," J. Plant Physiol., vol. 154, pp. 30-36, 1999. (Pubitemid 29072956)
58. R. Pu and D. Liu, "Segmented canonical discriminant analysis of in situ hyperspectral data for identifying 13 urban tree species," Int. J. Remote Sens., vol. 32, pp. 2207-2226, 2011, 2012/02/21.
59. P. Bunting and R. Lucas, "Landscape classification of Australian forest communities using hyperspectral HyMap and CASI data," University of Bari, Bari, Italy, IUFRO 8.01.03 Landscape Ecology, 2006, pp. 457-469.
60. K. N. Youngentob et al., "Mapping two eucalyptus subgenera using multiple endmember spectral mixture analysis and continuum-removed imaging spectrometry data," Remote Sens. Environ., vol. 115, pp. 1115-1128, 2011.
61. R. A. Chastain, "Isolating and characterizing woodland and savanna communities on Fort Lewis, Washington, USA," presented at the ASPRS 2008 Annual Conf., Portland, OR, USA, 2008.
62. C. Dahinden, "An improved Random Forests approach with application to the performance prediction challenge datasets," in Hands-On Pattern Recognition, I. Guyon, Ed. Brookline,MA,USA:Microtome Publishing, 2009, vol. 1.
63. Q. Zhou et al., "Gene selection using random forest and proximity differences criterion on DNA microarray data," J. Converg. Inform. Technol., vol. 5, pp. 161-170, 2010.