Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

Journal of Applied Remote Sensing

Volumn 7, Issue 1, 2013, Pages

  Adelabu, Samuel ^a   Mutanga, Onisimo ^a   Adam, Elhadi ^a   Cho, Moses Azong ^b  

^a UNIVERSITY OF KWAZULU NATAL   (South Africa)

^b DSI CSIR Nanotechnology Innovation Centre   (South Africa)

Author keywords

Random forest; red edge; semiarid environment; support vector machines; tree species classification

Indexed keywords

DECISION TREES; FORESTRY; IMAGE CLASSIFICATION; LEARNING ALGORITHMS; MACHINE LEARNING; REMOTE SENSING; SOIL MOISTURE;

ADVANCED PROCESSING ALGORITHMS; OVERALL ACCURACIES; RANDOM FORESTS; RED EDGE; REMOTE SENSING CLASSIFICATION; SEMI-ARID ENVIRONMENTS; SPECIES CLASSIFICATION; TREE SPECIES;

SUPPORT VECTOR MACHINES;

ALGORITHMS; CLASSIFICATION; FORESTRY; INFORMATION RETRIEVAL; MOISTURE; SOIL; SPECIES IDENTIFICATION; TREES;

EID: 84890064392     PISSN: None     EISSN: 19313195     Source Type: Journal    
DOI: 10.1117/1.JRS.7.073480     Document Type: Article

References (47)

1. W. Mojeremane and T. Kgathi, Seed treatments for enhancing germination of Colophospermum mopane seeds: a multipurpose tree in Botswana, J. Biol. Sci. 5(3), 309 (2005), http://dx.doi.org/10.3923/jbs.2005.309.311.
2. R. J. Sebego et al., Mapping of Colophospermum mopane using Landsat TM in eastern Botswana, S. Afr. Geogr. J. 90(1), 41-53 (2008), http://dx.doi.org/10. 1080/03736245 .2008.9725310.
3. M. Ditlhogo et al., Interactions between the mopane caterpillar, Imbrasia belina, and its host, Colophospermum mopane in Botswana, in Management of mopane in Southern Africa, Ogongo Agricultural College, Namibia, C. Flower, G. Wardell-Johnson, and A. Jamieson, Eds., pp. 46-49 (1996).
4. S. Adelabu, O. Mutanga, and M. A. Cho, A review of remote sensing of insect defoliation and its implications for the detection and mapping of Imbrasia belina defoliation of Mopane Woodland, Afr. J. Plant Sci. Biotechnol. 6(1), 1-13 (2012).
5. L. J. Quackenbush and Y. Ke, Investigating new advances in forest species classification, presented at Proc. of 2007 ASPRS Annual Conf., 7-11 May 2007, Reno, Navada (2007).
6. S. E. Franklin, Remote Sensing for Sustainable Forest Management, Lewis Publishers, Boca Raton, Florida (2001).
7. M. Wulder and S. Franklin, Remote Sensing of Forest Environments: Concepts and Case Studies, Kluwer Academic, Boston (2003).
8. C. Schuster, M. Forster, and B. Kleinschmit, Testing the red edge channel for improving land-use classifications based on high-resolution multi-spectral satellite data, Int. J. Remote Sens. 33(17), 5583-5599 (2012), http://dx.doi.org/10.1080/01431161.2012.666812.
9. J. Tigges, T. Lakes, and P. Hostert, Urban vegetation classification: benefits of multitemporal RapidEye satellite data, Remote Sens. Environ. 136, 66-75 (2013), http://dx.doi.org/10.1016/j.rse.2013.05.001.
10. A. Carleer and E. Wolff, Exploitation of very high resolution satellite data for tree species identification, Photogramm. Eng. Remote Sens. 70(1), 135-140 (2004). (Pubitemid 38069989)
11. M. A. Cho et al., Improving discrimination of Savanna tree species through a multipleendmember spectral angle mapper approach: canopy-level analysis, IEEE Trans. Geosci. Remote Sens. 48(11), 4133-4142 (2010).
12. A. Lobo, Image segmentation and discriminant analysis for the identification of land cover units in ecology, IEEE Trans. Geosci. Remote Sens. 35(5), 1136-1145 (1997), http://dx.doi.org/10.1109/36.628781.
13. S. Ringrose et al., Nature of the darkening effect in drought affected savannah woodland environments relative to soil reflectance, Remote Sens. Environ. 25(25), 519-524 (1989).
14. 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. 112(6), 2999-3011 (2008), http://dx.doi.org/10.1016/j.rse.2008.02.011.
15. E. Adam and O. Mutanga, Spectral discrimination of papyrus vegetation (Cyperus papyrus L.) in swamp wetlands using field spectrometry, ISPRS J. Photogramm. Remote Sens. 64(6), 612-620 (2009), http://dx.doi.org/10.1016/j. isprsjprs.2009.04.004.
16. F. Melgani and L. Bruzzone, Classification of hyperspectral remote sensing images with support vector machines, IEEE Trans. Geosci. Remote Sens. 42(8), 1778-1790 (2004), http://dx.doi.org/10.1109/TGRS.2004.831865.
17. P. Krahwinkler and J. Rossman, Using decision tree based multiclass support vector machines for forest mapping, presented at IEEE Int. Geoscience and Remote Sensing Symp., Vancouver, Canada (2011).
18. Y. P. R. Bhalotra, Climate of Botswana, Part 2: Elements of climate, Department of Meteorological Services, Ministry of Works, Transport and Communications: Botswana, B. M. Services, Ed. Gaborone, p. 104 (1987).
19. F. Do et al., Stable annual pattern of water use by Acacia tortilis in Sahelian Africa, Tree Physiol. 28(1), 95-104 (2008), http://dx.doi.org/10.1093/ treephys/28.1.95. (Pubitemid 351344923)
20. I. Wessels, C. Waal, and W. D. Boer, Induced chemical defences in Colophospermum mopane trees, Afr. J. Range Forage Sci. 24(24), 141-147 (2007), http://dx.doi.org/10 .2989/AJRFS.2007.24.3.4.297. (Pubitemid 350164179)
21. R. J. Sebego and W. Arnberg, Interpretation of mopane woodlands using air photos with implication on satellite image classification, Int. J. Appl. Earth Obs. Geoinf. 4(2), 119-135 (2002), http://dx.doi.org/10.1016/S0303-2434(02) 00009-0. (Pubitemid 38242227)
22. ENVI, Environment for Visualising Images, ITT Industries Inc., Boulder, Colorado, ITT Industries Inc, USA (2006).
23. E. M. Adam et al., Discriminating the papyrus vegetation (Cyperus papyrus L.) and its coexistent species using random forest and hyperspectral data resampled to HYMAP, Int. J. Remote Sens. 33(2), 552-569 (2012), http://dx.doi.org/10.1080/01431161.2010.543182.
24. RapidEye, Satellite imagery product specifications, 2011, http://www.RapidEye.de/upload/-RE-Product-Specifications-ENG.pdf (01 November 2011).
25. D. Naughton et al., Absolute radiometric calibration of the RapidEye multispectral imager using the reflectance-based vicarious calibration method, J. Appl. Remote Sens. 5(1), 053544 (2011), http://dx.doi.org/10.1117/1.3613950.
26. L. Breiman, Random forests, Mach. Learn. 45(1), 5-32 (2001), http://dx.doi.org/10.1023/A:1010933404324. (Pubitemid 32933532)
27. R. L. Lawrence, S. D. Wood, and R. L. Sheley, Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (randomForest), Remote Sens. Environ. 100(3), 356-362 (2006), http://dx.doi.org/10.1016/j.rse. 2005.10.014. (Pubitemid 43145876)
28. J. A. Benediktsson and J. R. Sveinsson, Random forest classification of multisource remote sensing and geographic data, in 2004 IEEE Int. Geoscience and Remote Sensing Symp., Anchorage, Alaska, pp. 1049-1052 (2004). (Pubitemid 40438304)
29. A. Özçift, Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis, Comput. Biol. Med. 41(5), 265-271 (2011), http://dx.doi.org/10.1016/j.compbiomed.2011.03.001.
30. V. Vapnik, Statistical Learning Theory. Support Vector Machines for Pattern Recognition, John Wiley & Sons, New York (1998).
31. C. J. C. Burges, A tutorial on support vector machines for pattern recognition, Data Min. Knowl. Discov. 2(2), 121-167 (1998), http://dx.doi.org/ 10.1023/A:1009715923555. (Pubitemid 128695475)
32. C. W. Hsu, C. C. Chang, and C. J. Lin, A practical guide to support vector classification, 2009, http://www-personal.umich.edu/~yongjiaw/NLPproject/ guide.pdf (22 October 2013).
33. R. Pontius, Jr. and M. Millones, Death to kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment, Int. J. Remote Sens. 32(15), 4407-4429 (2011), http://dx.doi.org/10.1080/01431161.2011.552923.
34. R. Ismail et al., Determining the optimal resolution of remotely sensed data for the detection of Sirex noctilio infestations in Pinus patula plantations in KwaZulu-Natal, South Africa, S. Afr. Geogr. J. 90(1), 196-204 (2008), http://dx.doi.org/10.1080/03736245 .2008.9725308.
35. G. P. Petropoulos, C. Kalaitzidis, and K. P. Vadrevu, Support vector machines and objectbased classification for obtaining land-use/cover cartography from hyperion hyperspectral imagery, Comput. Geosci. 41, 99-107 (2012), http://dx.doi.org/10.1016/j.cageo.2011.08 .019.
36. R. Manandhar, I. O. A. Odeh, and T. Ancev, Improving the accuracy of land use and land cover classification of Landsat data using post-classification enhancement, Remote Sens. 1(3), 330-344 (2009), http://dx.doi.org/10.3390/ rs1030330.
37. I. Nitze, U. Schulthess, and H. Asche, Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification, presented at Proc. of the 4th GEOBIA, 7-9 May 2012, Rio De Janeiro, Brazil (2012).
38. A. Gitelson and M. Merzlyak, Quantitative estimation of chlorophyll-a using reflectance spectra: experiments with autumn chesnut and maple leaves, J. Photochem. Photobiol. B 22(3), 247-252 (1994), http://dx.doi.org/10.1016/1011- 1344(93)06963-4. (Pubitemid 24082925)
39. O. Mutanga and A. K. Skidmore, Red-edge shift and biochemical content in grass canopies, ISPRS J. Photogramm. Remote Sens. 62(1), 34-42 (2007), http://dx.doi.org/10 .1016/j.isprsjprs.2007.02.001. (Pubitemid 46654760)
40. V. Thomas et al., Canopy chlorophyll concentration estimation using hyperspectral and lidar data for a boreal mixedwood forest in northern Ontario, Canada, Int. J. Remote Sens. 29(4), 1029-1052 (2008), http://dx.doi.org/10.1080/ 01431160701281023.
41. B. Tapsall, P. Milenov, and K. Tasdemir, Analysis of RapidEye imagery for annual landcover mapping as an aid to European Union (EU) common agricultural policy, in ISPRS Technical Commission VII Symp.-100 Years, Vienna, Austria, pp. 568-573 (2010).
42. S. Sah, A multi-temporal fusion-based approach for land cover mapping in support of nuclear incident response, MS Thesis, Chester F. Carlson Center for Imaging Science of the College of Science Rochester Institute of Technology, Pune University (2013).
43. H. O. Kim, J. O. Yeom, and Y. S. Kim, Agricultural land cover classification using RapidEye satellite imagery in South Korea-first result, Proc. SPIE 8174, 817424 (2011), http://dx.doi.org/10.1117/12.897810.
44. R. Pouteau, A. Collin, and B. Stoll, A comparison of machine learning algorithms for classification of tropical ecosystems observed by multiple sensors at multiple scales, 2011, http://www.isprs.org/proceedings/2011/isrse- 34/211104015Final00913.pdf (22 October 2013).
45. D. J. Redo and A. C. Millington, A hybrid approach to mapping land-use modification and land-cover transition from MODIS time-series: a case study from the Bolivian seasonal tropics, Remote Sens. Environ. 115(2), 353-372 (2011), http://dx.doi.org/10.1016/j.rse .2010.09.007.
46. G. M. Foody and A. Mathur, The use of small training sets containing mixed pixels for accurate hard image classification: training on mixed spectral responses for classification by a SVM, Remote Sens. Environ. 103(2), 179-189 (2006), http://dx.doi.org/10.1016/j.rse .2006.04.001. (Pubitemid 44015803)
47. R. G. Pontius and M. Millones, Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment, Int. J. Remote Sens. 32(15), 4407-4429 (2011), http://dx.doi.org/10.1080/01431161.2011.552923.