Forest attribute imputation using machine-learning methods and ASTER data: Comparison of k-NN, SVR and random forest regression algorithms

International Journal of Remote Sensing

Volumn 33, Issue 19, 2012, Pages 6254-6280

  Shataee, Shaban ^a   Kalbi, Syavash ^b   Fallah, Asghar ^b   Pelz, Dieter ^c  

^a GORGAN UNIVERSITY OF AGRICULTURAL SCIENCES AND NATURAL RESOURCES   (Iran)

^b SARI AGRICULTURAL SCIENCES AND NATURAL RESOURCES UNIVERSITY   (Iran)

^c UNIVERSITY OF FREIBURG   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 84877298110     PISSN: 01431161     EISSN: 13665901     Source Type: Journal    
DOI: 10.1080/01431161.2012.682661     Document Type: Article

References (70)

1. Baret, F., and Guyot, G., 1991. Potential and limits of vegetation indices for LAI and AFAR assessment. Remote Sensing of Environment, 35:161–173.
2. Birth, G.S., and McVey, G., 1968. Measuring the color of growing turf with a reflectance spectrophotometer. Agronomy Journal, 60:640–643.
3. Breidenbach, J., Nothdurft, A., and Kandler, G., 2010. Comparison of nearest neighbor approaches for small area estimation of tree species-specific forest inventory attributes in central Europe using airborne laser scanner data. European Journal of Forest Research, 129:833–845.
4. Breiman, L., 2001. Random forests. Machine Learning, 45:5–32.
5. Cohen, W.B., Spies, T.A., and Fiorella, M., 1995. Estimating the age and structure of forests in a multi-ownership landscape of western Oregon, U.S.A. International Journal of Remote Sensing, 16:721–746.
6. Cortez, P., and Morais, A., A data mining approach to predict forest fires using meteorological data. Proceedings of the EPIA 2007–Portuguese Conference on Artificial Intelligence. December2007, Guimarães, Portugal. Edited by:Neves, J., Santos, M.F., and Machado, J.M., pp.512–523. Heidelberg:Springer.
7. Dalponte, M., Bruzzone, L., and Gianelle, D., 2008. “Estimation of tree biomass volume in alpine forest areas using multi return lidar data and support vector regression”. In Proceedings of the SPIE Vol. 7109, 71090C-1–71090C-12
8. Deering, D.W., Rose, J.W., Mass, R.H., and Schell, J.A., 6–10 October 1975 1975. “Measuring forage production of grazing units from Landsat MSS data”. In Proceedings of the 10th International Symposium on Remote Sensing of Environment 6–10 October 1975, 1169–1178. Ann Arbor, MI
9. Durbha, S.S., King, R.L., and Younan, N.H., 2007. Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer. Remote Sensing of Environment, 107:348–361.
10. Eskelson, B.N.I., Hailemariam, T., and Barrett, T.M., 2009. Estimating current forest attributes from paneled inventory data using plot-level imputation:a study from the pacific northwest. Forest Science, 55:64–71.
11. Falkowski, M.J., Gessler, P., Morgan, P., Hudak, A.T., and Smith, A.M.S., April 2004 2004. “Evaluating the ASTER sensor for mapping and characterizing forest fire fuels in Northern Idaho”. In Proceedings of Tenth Biennial USDA Forest Service Remote Sensing Applications Conference April 2004, 11Salt Lake City, UT
12. FAO, 2002, Forests and the forestry sector. www.fao.org/forestry/site/23747/en/iran (http://www.fao.org/forestry/site/23747/en/iran) (Accessed:21 December 2009).
13. Finley, A.O., McRobert, R.E., and Ek, A.R., 2006. Applying an efficient k-nearest neighbor search to forest attribute imputation. Forest Science, 52:130–135.
14. Franco-Lopez, H., Ek, A.R., and Bauer, M.E., 2001. Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method. Remote Sensing of Environment, 77:251–274.
15. Fuchs, H., Magdon, P., Kleinn, C., and Flessa, H., 2009. Estimating aboveground carbon in a catchment of the Siberian forest tundra:combining satellite imagery and field inventory. Remote Sensing of Environment, 113:518–531.
16. Gebreslasie, M.T., Ahmed, F.B., and Aardt, J., 2008. Estimating plot-level forest structural attributes using high spectral resolution ASTER satellite data in even-aged Eucalyptus plantations in southern KwaZulu-Natal, South Africa. Southern Forests, 70:1–10.
17. Gjertsen, A.K., 2007. Accuracy of forest mapping based on Landsat TM data and a kNN-based method. Remote Sensing of Environment, 110:420–430.
18. Gong, G., 1986. Cross-validation, the jackknife, and the bootstrap:excess error estimation in forward logistic regression. Journal of American Statistics Association, 81:108–113.
19. Hagner, O., Nilsson, M., Joyce, S., and Olsson, H., 2002. K-nearest neighbor methods and artificial neural networks for estimation of forest parameters from satellite imagery
20. Hall, R.J., Skakun, R.S., Arsenault, E.J., and Case, B.S., 2006. Modeling forest stand structure attributes using Landsat ETM + data:application to mapping of aboveground biomass and stand volume. Forest Ecology and Management, 225:378–390.
21. Heiskanen, J., 20–24 June 2005 2005. “Remote sensing of mountain birch forest biomass and leaf area index using ASTER data”. In Proceedings of the 31st International Symposium on Remote Sensing of Environment 20–24 June 2005, St. Petersburg, Russia
22. Holmström, H., 2002. Estimation of single tree characteristics using kNN method and plot wise aerial photograph interpretations. Forest Ecology and Management, 167:303–314.
23. Hsu, C.W., Chang, C.C. and Lin, C.J., 2010, A Practical Guide to Support Vector Classification (Taipei:Department of Computer Science, National Taiwan University). http://www.csie.ntu.edu.tw/~cjlin (http://www.csie.ntu.edu.tw/~cjlin)
24. Hudak, A.T., Crookston, N.L., Evans, J.S., Hall, D.E., and Falkowski, M.J., 2008. Nearest neighbor imputation of species-level, plot-scale forest structure attributes from LiDAR data. Remote Sensing of Environment, 112:289–290.
25. Huiyan, G., Limin, D., Gang, W., Dong, X., Shunzhong, W., and Hui, W., 2006. Estimation of forest volumes by integrating Landsat TM imagery and forest inventory data. Science in China, Series E:Technological Sciences, 49:54–62.
26. Hyvönen, P., 2007. “The updating of forest resource data for management planning for privately owned forests in Finland”. In Academic dissertation, Faculty of Forestry, 40University of Joensuu, Joensuu, Finland.
27. Kajisa, T., Murakami, T., Mizoue, N., Kitahara, F., and Yoshida, S., 2008. Estimation of stand volumes using the k-nearest neighbors method in Kyushu, Japan. Journal of Forest Research, 13:249–254.
28. Katila, M., and Tomppo, E., 2001. Selecting estimation parameters for the Finnish multi-source national forest inventory. Remote Sensing of Environment, 76:16–32.
29. Keller, F., 2010, Evaluation, connectionist and statistical language processing. Online lecture, Computerlinguistik, Universit¨at des Saarlandes. http://www.coli.uni-saarland.de/~crocker/Teaching/Connectionist/lecture11_4up.pdf (http://www.coli.uni-saarland.de/~crocker/Teaching/Connectionist/lecture11_4up.pdf) (Accessed:April 2010).
30. Khorrami, K.R., 2004. “Investigation of the potential of Landsat ETM + Data in volume estimating of beech forest stands (case study:Sangdeh area in north of Iran)”. In MSc thesis, Faculty of Natural Resources, University of Tehran, Tehran, Iran, 80 p. [in Persian].
31. Kozma, L., 2008, k Nearest neighbor algorithm (kNN). Helsinki University of Technology, Special course in computer and information science. www.lkozma.net/knn2.pdf (http://www.lkozma.net/knn2.pdf)
32. Kutzer, C., 2008. “Potential of the kNN method for estimation and monitoring off-reserve forest resources in Ghana”. In PhD thesis, Faculty of Forest and Environmental Sciences, 145Freiburg im Breisgau, Germany:Albert-Ludwigs-Universität.
33. Latifi, H., Nothdurfet, A., and Koch, B., 2010. Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest:optimization of variable selection on optical/Lidar-derived predictors. Forestry Journal, 83:395–407.
34. Lemay, V., and Temesgen, H., 2005. Comparison of nearest neighbor methods for estimating basal area and stems per hectare using aerial auxiliary variables. Forest Science, 51:109–199.
35. Lister, A., Hoppus, M., and Czaplewski, R.L., 5–9 April 2004 2004. “K-nearest neighbor imputation of forest inventory variables in New Hampshire”. In Remote Sensing for Field Users, Proceedings of the Tenth Forest Service Remote Sensing Applications Conference 5–9 April 2004, Salt Lake City, UT
36. Makela, H., and Pekkarinen, A., 2004. Estimation of forest stands volumes by Landsat TM imagery and stand-level field-inventory data. Forest Ecology and Management, 196:245–255.
37. Mattera, D., and Haykin, S., 1999. “Support vector machines for dynamic reconstruction of a chaotic system”. In Advances in Kernel Methods:Support Vector Learning, Edited by:Schölkopf, B., Burges, C.J.C., and Smola, A.J., 211–242. Cambridge, MA:MIT Press.
38. Mayer, R.R., and Scribner, D.A., 8 July 2002 2002. “Extending the normalized difference vegetation index (NDVI) to short-wave infrared radiation (SWIR) (1- to 2.5-μm)”. In Proceedings of the Imaging Spectrometry VIII Conference 8 July 2002, Seattle, WA
39. McInerney, D.O., and Nieuwenhuis, M., 2009. A comparative analysis of kNN and decision tree methods for the Irish National Forest Inventory. International Journal of Remote Sensing, 30:4937–4955.
40. McRobert, R., Tomppo, E., Finley, A., and Heikkinen, J., 2007. Estimating aerial means and variances of forest attributes using the k-nearest neighbors technique and satellite imagery. Remote Sensing of Environment, 111:466–480.
41. McRobert, R.E., 2009. Diagnostic tools for nearest neighbors techniques when used with satellite imagery. Remote Sensing of Environment, 113:489–499.
42. Mohammadi, J., Sh, Shataee, Yaghmaee, F., and Mahiny, A., 2010. Modeling forest stand volume and tree density using Landsat ETM + data. International Journal of Remote Sensing, 31:2959–2975.
43. Muukkonen, P., and Heiskanen, J., 2005. Estimating biomass for boreal forests using ASTER satellite data combined with stand wise forest inventory data. Remote Sensing of Environment, 99:434–447.
44. Nilsson, M. 1997. “Estimation of forest variables using satellite image data and airborne lidar”. In PhD thesis, Acta Universitatis Agriculturae Suecia, Silvestria 17. Department of Forest Resource Management and Geomatics, Swedish University of Agricultural Sciences, Umeå, Sweden
45. Ohmann, J.L., and Gregory, M.J., 2002. Predictive mapping of forest composition and structure with direct gradient analysis and nearest neighbor imputation in coastal Oregon, U.S.A. Canadian Journal of Forest Research, 32:725–741.
46. Ostapowicz, K., Lakes, T., and Kozak, J., 10–14 May 2010 2010. “Modeling of land cover change using support vector machine”. In 13th AGILE International Conference on Geographic Information Science 10–14 May 2010, Guimarães, Portugal
47. Perry, C.R., and Lautenschlagei, L.F., 1984. Functional equivalence of vegetation indices. Remote Sensing and Environment, 14:169–182.
48. Reese, H., Nilsson, M., Sandström, P., and Olsson, H., 2002. Applications using estimates of forest parameters derived from satellite and forest inventory data. Computers and Electronics in Agriculture, 37:37–55.
49. Richardson, A.J., and Wiegand, C.L., 1977. Distinguishing vegetation from soil background information. Photogrammetric Engineering and Remote Sensing, 43:1541–1552.
50. Rose, J.W., Mass, R.H., Schell, J.A., and Deering, D.W., 10–14 December 1973 1973. “Monitoring vegetation systems in the Great Plains with ERTS”. In Earth Resource Technology Satellite-1 Symposium, 10–14 December 1973, 309–317. Washington, DC:Goddard Space Flight Center.
51. Roujean, J.L., and Breon, F.M., 1995. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements. Remote Sensing of Environment, 51:375–384.
52. Schölkopf, B., Smola, A., and Müller, K.R., 1998. Nonlinear component analysis as a kernel eigen value problem. Neural Computation, 10:1299–1319.
53. Shafri, H.Z.M., and Ramle, F.S.H., 2009. A comparison of support vector machine and decision tree classifications using satellite data of Langkawi islands. Information Technology Journal, 8:64–70.
54. Sironen, S., Kangas, A., and Maltamo, M., 2010. Comparison of different non-parametric growth imputation methods in the presence of correlated observations. Forestry, 83:39–51.
55. Sironen, S., Kangas, A., Maltamo, M., and Kangas, J., 2001. Estimating individual tree growth with the k-nearest neighbor and k-most similar neighbor methods. Silva Fenninica, 35:453–467.
56. Sivanpillai, R., Smith, C.T., Srinivasan, R., Messina, M.G., and Ben Wu, X., 2006. Estimation of managed loblolly pine stands age and density with Landsat ETM + data. Forest Ecology and Management, 223:247–254.
57. Statistica, 2010, Electronic text book, Stat Soft Inc. www.Statsoft.com (http://www.Statsoft.com)
58. Tatjana, K., Suppan, F., and Schneider, W., 2007. The impact of relative radiometric calibration on the accuracy of kNN-predictions of forest attributes. Remote Sensing of Environment, 110:431–437.
59. Thiam, A.K., 1997. “Geographic information system and remote sensing methods for assessing and monitoring land degradation in the shale:the case of Southern Mauritania”. In Doctoral dissertation, Darks University.
60. Tomppo, E., 2006. “The Finnish multi-source national forest inventory, small area estimation and map production”. In Forest Inventory–Methodology and Applications, Edited by:Kangas, A., and Maltamo, M., 195–224. The Netherlands:Springer.
61. Tucker, F., 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8:127–150.
62. Tuominen, S., 2007. “Estimation of local forest attributes, utilizing two-phase sampling and auxiliary data”. In Academic dissertation, Finnish Forest Research Institute, 45University of Helsinki, Helsinki, Finland.
63. Vapnik, V., 1998. Statistical Learning Theory, New York:John Wiley & Sons.
64. Vauhkonen, J., Korpela, I., Maltamo, M., and Tokola, T., 2010. Imputation of single-tree attributes using airborne laser scanning-based height, intensity, and alpha shape metrics. Remote Sensing of Environment, 114:1263–1276.
65. Walton, J.T., 2008. Sub pixel urban land cover estimation:comparing cubist, random forests, and support vector regression. Photogrammetric Engineering & Remote Sensing, 74:1213–1222.
66. Wang, X., Yang, C., Qin, B., and Gui, W., 2005. Parameter selection of support vector regression based on hybrid optimization algorithm and its application. Journal of Control Theory and Applications, 4:371–376.
67. Wang, Y., Wang, J., Du, W., Wang, C., Liang, Y., Zhou, C., and Huang, L., 2009. “Immune particle swarm optimization for support vector regression on forest fire prediction”. In Advances in Neural Networks, Edited by:Yu, W., He, H., and Zhang, N., 382–390. Berlin:Springer. ISNN 2009, Part II, LNCS 5552
68. Wang, Z., and Brenner, A., 16–19 November 2009 2009. “An integrated method for forest canopy cover mapping using Landsat ETM + imagery”. In ASPRS/MAPPS Fall Conference 16–19 November 2009, San Antonio, TX
69. Yarbrough, L.D., Easson, G., and Kuszmaul, J.S., 16–18 May 2005 2005. “Using at-sensor radiance and reflectance tasseled cap transforms applied to change detection for the ASTER sensor”. In IEEE Third International Workshop on the Analysis of Multi-temporal Remote Sensing Images 16–18 May 2005, Biloxi, MS
70. Zhang, R., and Ma, J., 2008. An improved SVM method P-SVM for classification of remotely sensed data. International Journal of Remote Sensing, 29:6029–6036.