Random Forests Unsupervised Classification: The Detection and Mapping of Solanum mauritianum Infestations in Plantation Forestry Using Hyperspectral Data

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

Volumn 8, Issue 6, 2015, Pages 3107-3122

  Peerbhay, Kabir Yunus ^a   Mutanga, Onisimo ^a   Ismail, Riyad ^a  

^a UNIVERSITY OF KWAZULU NATAL   (South Africa)

Author keywords

Anselin local Moran's I; principal component analysis (PCA); proximity matrix; Random forest (RF)

Indexed keywords

DAMAGE DETECTION; DECISION TREES; ECOLOGY; ECOSYSTEMS; FORESTRY; MAPPING; MATRIX ALGEBRA; REMOTE SENSING; TIMBER;

COMMERCIAL FORESTRY; FALSE POSITIVE RATES; HYPERSPECTRAL REMOTE SENSING; LOCAL MORAN'S I; PLANTATION FORESTRY; PROXIMITY MATRIX; RANDOM FORESTS; UNSUPERVISED CLASSIFICATION;

PRINCIPAL COMPONENT ANALYSIS;

DETECTION METHOD; FOREST ECOSYSTEM; INTRODUCED SPECIES; INVASIVE SPECIES; MAPPING; PLANTATION FORESTRY; PRINCIPAL COMPONENT ANALYSIS; REMOTE SENSING; SPECTRAL ANALYSIS;

CLASSIFICATION; DECAY; ECONOMIC ANALYSIS; FORESTS; MAPPING; PLANTS; REMOTE SENSING;

SOLANUM MAURITIANUM;

EID: 85027926869     PISSN: 19391404     EISSN: 21511535     Source Type: Journal    
DOI: 10.1109/JSTARS.2015.2396577     Document Type: Article

References (74)

1. T. Olckers and C. Borea, "Assessing the risks of releasing a sapsucking lace bug, Gargaphia decoris, against the invasive tree Solanum mauritianum in New Zealand," BioControl, vol. 54, pp. 143-154, 2009.
2. T. Olckers and H. G. Zimmermann, "Biological control of silverleaf nightshade, Solanum elaegnifolium, and bugweed, Solanum mauritianum, (Solanaceae) in South Africa," Agric. Ecosyst. Environ., vol. 37, pp. 137-155, 1991.
3. T. Olckers, "Biological Control of Solanum mauritianum Scop. (Solanaceae) in South Africa:Will Perseverance Pay off?," Afr. Entomol., vol. 19, pp. 416-426, 2011.
4. L. Henderson, "Invasive, naturalized and casual alien plants in southern Africa: a summary based on the Southern African Plant Invaders Atlas (SAPIA)," Bothalia, vol. 37, p. 215, 2007.
5. L. A. Jordaan and C. T. Downs, "Comparison of germination rates and fruit traits of indigenous Solanum giganteum and invasive Solanum mauritianum in South Africa," South Afr. J. Bot., vol. 80, pp. 13-20, 2012.
6. E. T. F.Witkowski and R. D. Garner, "Seed production, seed bank dynamics, resprouting and long-term response to clearing of the alien invasive Solanum mauritianum in a temperate to subtropical riparian ecosystem," South Afr. J. Bot., vol. 74, pp. 476-484, 2008.
7. R. S. Copeland and R. A. Wharton, "Year-round production of pest Ceratitis species (Diptera: Tephritidae) in fruit of the invasive species Solanum mauritianum in Kenya," Ann. Entomol. Soc. Amr., vol. 99, pp. 530-535, 2006.
8. J. T. Atkinson, R. Ismail, and M. Robertson, "Mapping bugweed (Solanum mauritianum) infestations in pinus patula plantations using hyperspectral imagery and support vector machines," IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 7, no. 1, pp. 17-28, Jan. 2014.
9. C. Y. Huang and G. Asner, "Applications of remote sensing to alien invasive plant studies," Sensors, vol. 9, pp. 4869-4889, 2009.
10. D. C. Le Maitre, D. M. Richardson, and R. A. Chapman, "Alien plant invasions in South Africa: Driving forces and the human dimension," South Afr. J. Sci., vol. 100, pp. 103-112, 2004.
11. DAFF, "Report on commercial timber resources and primary roundwood processing in South Africa," Dept. Agriculture, Forestry, and Fisheries, Pretoria, South Africa, Tech. Rep. 1, 2009.
12. R. N. Pallett, "Precision forestry for pulpwood re-establishment silviculture," South. Afr. For. J., vol. 203, pp. 33-40, 2005.
13. J. Müllerová, J. Pergl, and P. Pyšek, "Remote sensing as a tool for monitoring plant invasions: Testing the effects of data resolution and image classification approach on the detection of a model plant species Heracleum mantegazzianum (giant hogweed)," Int. J. Appl. Earth Observ. Geoinf., vol. 25, pp. 55-65, 2013.
14. M. Masocha and A. K. Skidmore, "Integrating conventional classifiers with a GIS expert system to increase the accuracy of invasive species mapping," Int. J. Appl. Earth Observ. Geoinf., vol. 13, pp. 487-494, 2011.
15. X. Miao et al., "Estimation of yellow starthistle abundance through CASI-2 hyperspectral imagery using linear spectral mixture models," Remote Sens. Environ., vol. 101, pp. 329-341, 2006.
16. S. L. Ustin, D. DiPietro, K. Olmstead, E. Underwood, and G. J. Scheer, "Hyperspectral remote sensing for invasive species detection and mapping," in Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), 2002, vol. 3, pp. 1658-1660.
17. C. Joshi et al., "Indirect remote sensing of a cryptic forest understorey invasive species," For. Ecol. Manage., vol. 225, pp. 245-256, 2006.
18. R. L. Lawrence, S. D. Wood, and R. L. Sheley, "Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest)," Remote Sens. Environ., vol. 100, pp. 356-362, 2006.
19. G. P. Asner, M. O. Jones, R. E. Martin, D. E. Knapp, and R. F. Hughes, "Remote sensing of native and invasive species in Hawaiian forests," Remote Sens. Environ., vol. 112, pp. 1912-1926, 2008.
20. I. Somodi, A. C? arni, D. Ribeiro, and T. Podobnikar, "Recognition of the invasive species Robinia pseudacacia from combined remote sensing and GIS sources," Biol. Conserv., vol. 150, pp. 59-67, 2012.
21. B. A. Bradley and J. F. Mustard, "Characterizing the landscape dynamics of an invasive plant and risk of invasion using remote sensing," Ecol. Appl., vol. 16, pp. 1132-1147, 2006.
22. J. Resasco, A. N. Hale, M. C. Henry, and D. L. Gorchov, "Detecting an invasive shrub in a deciduous forest understory using late-fall Landsat sensor imagery," Int. J. Remote Sens., vol. 28, pp. 3739-3745, 2007.
23. C. Joshi et al., "Indirect remote sensing of a cryptic forest understorey invasive species," For. Ecol. Manage., vol. 225, pp. 245-256, 2006.
24. G. Anderson, J. Everitt, D. Escobar, N. Spencer, and R. Andrascik, "Mapping leafy spurge (Euphorbia esula) infestations using aerial photography and geographic information systems," Geocarto Int., vol. 11, pp. 81-89, 1996.
25. J. Mullerova, P. PyŠEk, V. JaroŠÍK, and J. A. N. Pergl, "Aerial photographs as a tool for assessing the regional dynamics of the invasive plant species Heracleum mantegazzianum," J. Appl. Ecol., vol. 42, pp. 1042-1053, 2005.
26. L. W. Lass et al., "A review of remote sensing of invasive weeds and example of the early detection of spotted knapweed (Centaurea maculosa) and babysbreath (Gypsophila paniculata) with a hyperspectral sensor," Weed Sci., vol. 53, pp. 242-251, 2005.
27. J. T. Mundt et al., "Discrimination of hoary cress and determination of its detection limits via hyperspectral image processing and accuracy assessment techniques," Remote Sens. Environ., vol. 96, pp. 509-517, 2005.
28. J. Everitt, C. Yang, B. Racher, C. Britton, andM. Davis, "Remote sensing of redberry juniper in the Texas rolling plains," J. RangeManage., vol. 54, pp. 254-259, 2001.
29. L. W. Lass, B. Shafii, W. J. Price, and D. C. Thill, "Assessing agreement in multispectral images of Yellow Starthistle (Centaurea solstitialis) with ground truth data using a Bayesian methodology1," Weed Technol., vol. 14, pp. 539-544, 2000.
30. D. O. Fuller, "Remote detection of invasive Melaleuca trees (Melaleuca quinquenervia) in South Florida with multispectral IKONOS imagery," Int. J. Remote Sens., vol. 26, pp. 1057-1063, 2005.
31. D. P. Groeneveld and R. P.Watson, "Near-infrared discrimination of leafless saltcedar in wintertime Landsat TM," Int. J. Remote Sens., vol. 29, pp. 3577-3588, 2008.
32. H. W. Carson, L. W. Lass, and R. H. Callihan, "Detection of yellow hawkweed (Hieracium pratense) with high resolutionmultispectral digital imagery," Weed Technol., vol. 10, pp. 477-483, 1995.
33. M. E. Andrew and S. L. Ustin, "The role of environmental context in mapping invasive plants with hyperspectral image data," Remote Sens. Environ., vol. 112, pp. 4301-4317, 2008.
34. G. P. Asner, R. E. Martin, A. J. Ford, D. J. Metcalfe, and M. J. Liddell, "Leaf chemical and spectral diversity in Australian tropical forests," Ecol. Appl., vol. 19, pp. 236-253, 2009.
35. P. R. Eddy et al., "Comparison of neural network and maximum likelihood high resolution image classification for weed detection in crops: Applications in precision agriculture," in Proc. IEEE Int. conf. Geosci. Remote Sens. Symp. (IGARSS'06), 2006, pp. 116-119.
36. C. Yang, Q. Du, J. H. Everitt, J. A. Goolsby, and N. H. Younan, "Spectral unmixing of airborne hyperspectral imagery for mapping giant reed infestations," in Proc. 2nd Workshop Hyperspectral Image Signal Process. Evol. Remote Sens. (WHISPERS'10), 2010, pp. 1-4.
37. C. Yang, J. A. Goolsby, J. H. Everitt, and Q. Du, "Applying spectral unmixing and support vector machine to airborne hyperspectral imagery for detecting giant reed," in Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), 2011, pp. 3664-3667.
38. F. Tsai, E. K. Lin, and K. Yoshino, "Spectrally segmented principal component analysis of hyperspectral imagery for mapping invasive plant species," Int. J. Remote Sens., vol. 28, pp. 1023-1039, 2007.
39. E. Adam, O. Mutanga, D. Rugege, and R. Ismail, "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.
40. J. H. Everitt, D. E. Escobar, M. A. Alaniz, M. R. Davis, and J. V. Richerson, "Using spatial information technologies to map Chinese tamarisk (Tamarix chinensis) infestations," Weed Sci., vol. 44, pp. 194-201, 1996.
41. L. Breiman, "Random forests," Mach. Learn., vol. 45, pp. 5-32, 2001.
42. R. Genuer, J.-M. Poggi, and C. Tuleau-Malot, "Variable selection using random forests," Pattern Recog. Lett., vol. 31, pp. 2225-2236, 2010.
43. M. Pal, "Random forest classifier for remote sensing classification," Int. J. Remote Sens., vol. 26, pp. 217-222, 2005.
44. M. Robnik-Šikonja, "Improving random forests," in Machine Learning: ECML 2004. New York, NY, USA: Springer, 2004, pp. 359-370.
45. R. Ismail and O. Mutanga, "Discriminating the early stages of Sirex noctilio infestation using classification tree ensembles and shortwave infrared bands," Int. J. Remote Sens., vol. 32, pp. 4249-4266, 2011.
46. M. Dye, O. Mutanga, and R. Ismail, "Examining the utility of random forest and AISA Eagle hyperspectral image data to predict Pinus patula age in KwaZulu-Natal, South Africa," Geocarto Int., vol. 26, pp. 275-289, 2011.
47. 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.
48. L. Breiman and A. Cutler, "Random forests manual v4.0," UC Berkeley, CA, USA, Tech. Rep., 2003, vol. 4.
49. T. Shi and S. Horvath, "Unsupervised learning with random forest predictors," J. Comput. Graph. Stat., vol. 15, pp. 118-138, 2006.
50. L. Auret and C. Aldrich, "Change point detection in time series data with random forests," Control Eng. Pract., vol. 18, pp. 990-1002, 2010.
51. A. L. Tarca, V. J. Carey, X.-W. Chen, R. Romero, and S. Draghici, "Machine learning and its applications to biology," PLoS Comput. Biol., vol. 3, p. 116, 2007.
52. L. Hegarat-Mascle, I. Bloch, and D. Vidal-Madjar, "Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing," IEEE Trans. Geosci. Remote Sens., vol. 35, no. 4, pp. 1018-1031, Jul. 1997.
53. J. Zhang and M. Zulkernine, "Anomaly based network intrusion detection with unsupervised outlier detection," in Proc. IEEE Int. Conf. Commun. (ICC'06), 2006a, pp. 2388-2393.
54. J. Zhang, M. Zulkernine, and A. Haque, "Random-forests-based network intrusion detection systems," IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., vol. 38, no. 5, pp. 649-659, Sep. 2008.
55. L. Mucina and M. C. Rutherford, The Vegetation of South Africa, Lesotho and Swaziland. Pretoria, South Africa: South African National Biodiversity Institute, 2006.
56. D. Roberts, Y. Yamaguchi, and R. Lyon, "Comparison of various techniques for calibration of AIS data," NASA STI/Recon Tech. Rep. SEE N87-12968 04-43, p. 12970, 1986, vol. 87.
57. ENVI, Environment for Visualizing Images: Version 4.7. White Plains, NY, USA: Exelis Visual Information Solutions, ITT Industries, 2009.
58. F. T. Liu, K. M. Ting, and Z.-H. Zhou, "Isolation forest," in Proc. 8th IEEE Int. Conf. Data Min. (ICDM'08), 2008, pp. 413-422.
59. R Development Core Team, R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing, 2008.
60. S. H. Wu, B. N. Lee, L. Wang, and M. S. Abadir, "Statistical analysis and optimization of parametric delay test," in Proc. IEEE Int. Test Conf. (ITC'07), 2007, pp. 1-10.
61. V. Rodriguez-Galiano, B. Ghimire, J. Rogan, M. Chica-Olmo, and J. 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.
62. A. Liaw andM.Wiener, "Classification and regression by random forest," R News, vol. 2, pp. 18-22, 2002.
63. R. Diáz-Uriarte and S. A. De Andres, "Gene selection and classification of microarray data using random forest," BMC Bioinf., vol. 7, p. 3, 2006.
64. Y. Xiao andM. R. Segal, "Identification of yeast transcriptional regulation networks using multivariate random forests," PLoS Comput. Biol., vol. 5, p. 1000414, 2009.
65. C. C. Aggarwal, A. Hinneburg, and D. A. Keim, On the Surprising Behavior of Distance Metrics in High Dimensional Space. New York, NY, USA: Springer, 2001.
66. J. Zhang and M. Zulkernine, "A hybrid network intrusion detection technique using random forests," in Proc. 1st Int. Conf. Availability Reliab. Secur. (ARES'06), 2006b, p. 8.
67. G. L. Scott and H. C. Longuet-Higgins, "Feature grouping by 'relocalisation' of eigenvectors of the proximity matrix," in Proc. BMVC, 1990, pp. 1-6.
68. E. Triantaphyllou and S. H. Mann, "An evaluation of the eigenvalue approach for determining the membership values in fuzzy sets," Fuzzy Sets Syst., vol. 35, pp. 295-301, 1990.
69. L. Anselin, "Local indicators of spatial association-LISA," Geog. Anal., vol. 27, pp. 93-115, 1995.
70. S. Spitalnic, "Test properties 2: Likelihood ratios, Bayes' formula, and receiver operating characteristic curves," Hosp. Physician, vol. 40, pp. 53-58, 2004.
71. D. Bamber, "The area above the ordinal dominance graph and the area below the receiver operating characteristic graph," J. Math. Psychol., vol. 12, pp. 387-415, 1975.
72. I. S. Reed and X. Yu, "Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution," IEEE Trans. Acoust. Speech Signal Process., vol. 38, no. 10, pp. 1760-1770, Oct. 1990.
73. R. Ismail, O. Mutanga, and L. Kumar, "Modeling the potential distribution of pine forests susceptible to Sirex noctilio infestations in Mpumalanga, South Africa," Trans. GIS, vol. 14, pp. 709-726, 2010.
74. N. F. Glenn et al., "Hyperspectral data processing for repeat detection of small infestations of leafy spurge," Remote Sens. Environ., vol. 95, pp. 399-412, 2005.