Browse > Article
http://dx.doi.org/10.7780/kjrs.2019.35.6.2.2

The Development of Major Tree Species Classification Model using Different Satellite Images and Machine Learning in Gwangneung Area  

Lim, Joongbin (Division of Global Forestry, National Institute of Forest Science)
Kim, Kyoung-Min (Division of Global Forestry, National Institute of Forest Science)
Kim, Myung-Kil (Division of Global Forestry, National Institute of Forest Science)
Publication Information
Korean Journal of Remote Sensing / v.35, no.6_2, 2019 , pp. 1037-1052 More about this Journal
Abstract
We had developed in preceding study a classification model for the Korean pine and Larch with an accuracy of 98 percent using Hyperion and Sentinel-2 satellite images, texture information, and geometric information as the first step for tree species mapping in the inaccessible North Korea. Considering a share of major tree species in North Korea, the classification model needs to be expanded as it has a large share of Oak(29.5%), Pine (12.7%), Fir (8.2%), and as well as Larch (17.5%) and Korean pine (5.8%). In order to classify 5 major tree species, national forest type map of South Korea was used to build 11,039 training and 2,330 validation data. Sentinel-2 data was used to derive spectral information, and PlanetScope data was used to generate texture information. Geometric information was built from SRTM DEM data. As a machine learning algorithm, Random forest was used. As a result, the overall accuracy of classification was 80% with 0.80 kappa statistics. Based on the training data and the classification model constructed through this study, we will extend the application to Mt. Baekdu and North and South Goseong areas to confirm the applicability of tree species classification on the Korean Peninsula.
Keywords
Random forest; Spectroscopy; Sentinel-2; PlanetScope; SRTM;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Asner, G.P., 2008. Hyperspectral remote sensing of canopy chemistry, physiology, and biodiversity in tropical rainforests, In: Kalacska, M., Sanchez-Azofeifa, G. (Ed.), Hyperspectral remote sensing of tropical and sub-tropical forests, CRS press Taylor and Francis group, Boca Raton, FL, USA, pp. 261-296.
2 Bae, J.S. and E.S. Kim, 2019. Understanding Forest Status of the Korean Peninsula in 1910: A Focus on Digitization of Joseonimyabunpodo (The Korean Peninsula Forest Distribution Map), Journal of Korean Society of Forest Science, 108(3): 418-428.
3 Bae, S.W., J.S. Kim, G.W. Kwon, K.N. Hong, I.S. Kim, J.S. Kim, B.Y. Ji, H.S. Kim, M.S. Jo, K.H. Kim, I.S. Mun, Y.M. Son, C.H. Jeon, J.H. Park, H.J. Lee, W.C. Park, G.W. Kim, B.W. Park, J.H. Lim, and S.J. Kim, 2012a. Economic tree species 2 Oak, National Institute of Forest Science, Seoul, Korea (in Korean).
4 Bae, S.W., C.Y. Lee, G.W. Kim, B.W. Park, J.S. Lee, E.W. Nho, K.N. Hong, S.E. Hahn, K.J. Lee, J.H. Hwang, S.T. Lee, K.W. Seo, H.S. Kim, G.H. Jo, B.Y. Ji, K.H. Kim, I.S. Mun, S.K. Lee, Y.B. Park, Y.M. Son, S.D. Kwon, C.H. Jeon, J.H. Park, S.T. Jo, G.H. Ga, H.J. Lee, M.J. Park, J.H. Lim, and S.J. Kim, 2012b. Economic tree species 3 Korean pine, National Institute of Forest Science, Seoul, Korea (in Korean).
5 Bae, S.W., C.Y. Lee, B.W. Park, S.C. Hong, I.S. Kim, S.E. Hahn, K.N. Hong, S.W. Lee, G.H. Jo, J.H. Hwang, S.T. Lee, K.H. Kim, I.S. Mun, Y.M. Son, C.H. Jeon, J.H. Park, G.H. Ga, H.J. Lee, M.J. Park, C.Y. Kim, G.W. Kim, J.H. Lim, and S.J. Kim, 2012c. Economic tree species 1 Korean red pine, National Institute of Forest Science, Seoul, Korea (in Korean).
6 Bae, S.W., S.H. Ryu, C.Y. Lee, G.W. Kim, B.W. Park, S.C. Hong, E.W. Nho, K.N. Hong, S.E. Hahn, K.J. Lee, J.H. Hwang, S.T. Lee, K.W. Seo, H.S. Kim, G.H. Jo, B.Y. Ji, K.H. Kim, I.S. Mun, Y.B. Park, Y.M. Son, S.D. Kwon, C.H. Jeon, J.H. Park, S.T. Jo, G.H. Ga, H.J. Lee, M.J. Park, J.H. Lim, and S.J. Kim, 2012d. Economic tree species 4 Japanese larch, National Institute of Forest Science, Seoul, Korea (in Korean).
7 Belgiu, M. and L. Dragut, 2016. Random forest in remote sensing: A review of applications and future directions, ISPRS Journal of Photogrammetry and Remote Sensing, 114: 24-31.   DOI
8 Breiman, L., 2001. Random forests, Machine Learning, 45(1):5-32.   DOI
9 Breiman, L. and A. Cutler, 2014. Random Forests, https://www.stat.berkeley.edu/-breiman/RandomForests/cc_home.htm, Accessed on Oct. 30, 2019.
10 Chan, J.C.W. and D. Paelinckx, 2008. Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery, Remote Sensing of Environment, 112(6): 2999-3011.   DOI
11 Cho, H. and K.S. Lee, 2014. Comparison between Hyperspectral and Multispectral Images for the Classification of Coniferous Species, Korean Journal of Remote Sensing, 30(1): 25-36 (in Korean with English abstract).   DOI
12 Choung, Y. and K. Lee, 2019. Ecology of Common Plant Species in Central Korean Forests, Nature & Ecology, Seoul, Korea (in Korean).
13 Chung, S.Y., J.S. Yim, and M.Y. Shin, 2011. A comparison of pixel-and segment-based classification for tree species classification using QuickBird imagery, Journal of Korean Forest Society, 100(4): 540-547 (in Korean with English abstract).
14 Culbert, P.D., V.C. Radeloff, V. St-Louis, C.H. Flather, C.D. Rittenhouse, T.P. Albright, and A.M. Pidgeon, 2012. Modeling broad-scale patterns of avian species richness across the Midwestern United States with measures of satellite image texture, Remote Sensing of Environment, 118: 140-150.   DOI
15 Curran, P.J., J.L. Dungan, B.A. Macler, and S.E. Plummer, 1991. The effect of a red leaf pigment on the relationship between red edge and chlorophyll concentration, Remote Sensing of Environment, 35(1): 69-76.   DOI
16 Dennison, P.E. and D.A. Roberts, 2003. The effects of vegetation phenology on endmember selection and species mapping in southern California chaparral, Remote Sensing of Environment, 87(2): 295-309.   DOI
17 Dian, Y., Z. Li, and Y. Pang, 2015. Spectral and Texture Features Combined for Forest Tree species Classification with Airborne Hyperspectral Imagery, Journal of the Indian Society of Remote Sensing, 43(1): 101-107.   DOI
18 George, R., H. Padalia, and S.P.S. Kushwaha, 2014. Forest tree species discrimination in western Himalaya using EO-1 Hyperion, International Journal of Applied Earth Observation and Geoinformation, 28: 140-149.   DOI
19 Feng, Q., J. Liu, and J. Gong, 2015. UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis, Remote Sensing, 7(1): 1074-1094.   DOI
20 Filella, I. and J. Penuelas, 1994. The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status, International Journal of Remote Sensing, 15(7): 1459-1470.   DOI
21 Hall-Beyer, M., 2017. GLCM Texture: A Tutorial v.3.0 March 2017, https://prism.ucalgary.ca/handle/1880/51900, Accessed on Oct. 30, 2019.
22 Hayes, M.M., S.N. Miller, and M.A. Murphy, 2014. High-resolution landcover classification using Random Forest, Remote Sensing Letters, 5(2): 112-121.   DOI
23 Jang, S.S., 2018. Classification of Tree Species using Sentinel-2 Satellite Image, University of Seoul, Seoul, Korea (in Korean with English abstract).
24 Jensen, J.R., 2016. Introductory digital image processing: a remote sensing perspective (4th), Pearson Education, Glenview, IL, USA.
25 Jensen, J.R., J. Im, P. Hardin, and R.R. Jensen, 2009. Image classification, In: Warner, T. A., Nellis, M. D., Foody, G. M. (Ed.), The SAGE handbook of remote sensing, Sage Publications, London, UK, pp. 269-281.
26 Jung, I.C., 1999. An Evaluation of the Use the Texture in Land Cover Classification Accuracy from SPOT HRV Image of Pusan Metropolitan Area, Journal of the Korean Association of Geographic Information Studies, 2(1): 32-44 (in Korean with English abstract).
27 Lim, J., K.M. Kim, and R. Jin, 2019a. Tree Species Classification Using Hyperion and Sentinel-2 Data with Machine Learning in South Korea and China, ISPRS International Journal of Geo-Information, 8(3): 150.   DOI
28 Kent, M. and P. Coker, 1992. Vegetation description and analysis: a practical approach, British Library, London, UK.
29 KFS, 2018. Introduction: Korea National Arboretum, Korea Forest Service, https://www.forest.go.kr/newkfsweb/html/HtmlPage.do?pg=/intro/intro_05010202.html, Accessed on Oct. 30, 2019.
30 Lee, J.S., E.S. Kim, G.E. Park, and J.H. Lim, 2017. Aerial photograph three-dimensional interpretation manual for producing forest species distribution map, National Institute of Forest Science, Seoul, Korea (in Korean).
31 Lim, J.H., E.S. Kim, G.E. Park, Y.S. Kim, G.C. Jang, J.K. Hahn, S.C. Jeong, H.I. Lim, B.L. Lee, W.K. Song, N.H. Jo, and S.H. Yun, 2019b. Current Status and Conservation Plan of Endangered Subalpine Conifers, National Institute of Forest Science, Seoul, Korea (in Korean).
32 Louis, J., V. Debaecker, B. Pflug, M. Main-Korn, J. Bieniarz, U. Mueller-Wilm, E. Cadau, and F. Gascon, 2016. Sentinel-2 Sen2Cor: L2A Processor for Users, Proc. of Living Planet Symposium, Prague, Czech Republic, May 9-13, vol. 740, pp. 91-98.
33 Luo, L. and G. Mountrakis, 2010. Integrating intermediate inputs from partially classified images within a hybrid classification framework: An impervious surface estimation example, Remote Sensing of Environment, 114(6): 1220-1229.   DOI
34 Maillard, P., 2003. Comparing texture analysis methods through classification, Photogrammetric Engineering & Remote Sensing, 69(4): 357-367.   DOI
35 Rautiainen, M., P. Lukes, L. Homolova, A. Hovi, J. Pisek, and M. Mottus, 2018. Spectral Properties of Coniferous Forests: A Review of In Situ and Laboratory Measurements, Remote Sensing, 10(2): 207.   DOI
36 Naidoo, L., M.A. Cho, R. Mathieu, and G. Asner, 2012. Classification of savanna tree species, in the Greater Kruger National Park region, by integrating hyperspectral and LiDAR data in a Random Forest data mining environment, ISPRS Journal of Photogrammetry and Remote Sensing, 69: 167-179.   DOI
37 Pena-Barragan, J.M., M.K. Ngugi, R.E. Plant, and J. Six, 2011. Object-based crop identification using multiple vegetation indices, textural features and crop phenology, Remote Sensing of Environment, 115(6): 1301-1316.   DOI
38 Persson, M., E. Lindberg, and H. Reese, 2018. Tree Species Classification with Multi-Temporal Sentinel-2 Data, Remote Sensing, 10(11): 1794.   DOI
39 Rodriguez-Galiano, V.F., B. Ghimire, J. Rogan, M. Chica-Olmo, and J.P. Rigol-Sanchez, 2012. An assessment of the effectiveness of a random forest classifier for land-cover classification, ISPRS Journal of Photogrammetry and Remote Sensing, 67: 93-104.   DOI
40 Ryu, J.H., S.H. Kim, W.B. Shim, J.C. Kim, S.A. Seo, and B.O. Yu, 2010. 5th forest type map (1: 25,000) production manual using ortho-aerial photograph, National Institute of Forest Science, Seoul, Korea (in Korean).
41 Schowengerdt, R.A., 2007. Remote sensing: models and methods for image processing (3rd), Academic Press, San Diego, CA, USA.
42 Sobhan, I., 2007. Species discrimination from a hyperspectral perspective, Wageningen University, Wageningen, Netherlands.
43 Warner, T., 2011. Kernel-Based Texture in Remote Sensing Image Classification, Geography Compass, 5(10): 781-798.   DOI
44 Thenkabail, P.S., E.A. Enclona, M.S. Ashton, C. Legg, and M.J. De Dieu, 2004. Hyperion, IKONOS, ALI, and ETM+ sensors in the study of African rainforests, Remote Sensing of Environment, 90(1): 23-43.   DOI
45 Vyas, D., N.S.R. Krishnayya, K.R. Manjunath, S.S. Ray, and S. Panigrahy, 2011. Evaluation of classifiers for processing Hyperion (EO-1) data of tropical vegetation, International Journal of Applied Earth Observation and Geoinformation, 13(2): 228-235.   DOI
46 Wang, L. and S. Zhang, 2014. Incorporation of texture information in a SVM method for classifying salt cedar in western China, Remote Sensing Letters, 5(6): 501-510.   DOI
47 Kim, K.M., J.W. Park, E.H. Kim, and J. Lim, 2019. A Study on the Establishment of Forest Spatial Information on Korean Peninsula, National Institute of Forest Science, Seoul, Korea (in Korean).
48 KNA, 2014. Korea Biodiversity Information System, Korea National Arboretum, http://www.nature.go.kr/ekbi/SubIndex.do, Accessed on Oct. 30, 2019.
49 Korea Forestry Promotion Institute, 2013. Borderline forest type map production guide, Korea Forestry Promotion Institute, Seoul, Korea.
50 Korea Society of Remote Sensing. 2016. Design of spectral library of major forest species in inaccessible areas, National Institute of Forest Science, Seoul, Korea (in Korean).
51 Kim, K.M. and S.H. Lee, 2013. Distribution of major species in Korea (based on 1: 5000 forest type map), National Institute of Forest Science, Seoul, Korea (in Korean).
52 Lee, H.S. and K.S. Lee, 2017. Effect of Red-edge Band to Estimate Leaf Area Index in Close Canopy Forest, Korean Journal of Remote Sensing, 33(5): 571-585 (in Korean with English abstract).   DOI
53 Kim, J.S. and T.Y. Kim, 2013. Korean trees; All of the trees in our land, Dolbaegae, Seoul, Korea (in Korean).