Journal of Korean Society of Forest Science (한국산림과학회지)

Korean Society of Forest Science (한국산림과학회)
권호 표지

Forest Thematic Maps and Forest Statistics Using the k-Nearest Neighbor Technique for Pyeongchang-Gun, Gangwon-Do

kNN 기법을 이용한 강원도 평창군의 산림 주제도 작성과 산림통계량 추정

  • Yim, Jong-Su (Institute of Forest Management, Gottinggen University) ;
  • Kong, Gee Su (Division of Forest Resource Information, Korea Forest Research Institute) ;
  • Kim, Sung Ho (Division of Forest Resource Information, Korea Forest Research Institute) ;
  • Shin, Man Yong (Department of Forest Resources, Kookmin University)
  • 임종수 (독일 괴팅엔 대학 임학과) ;
  • 공지수 (국립산림과학원 산림자원정보과) ;
  • 김성호 (국립산림과학원 산림자원정보과) ;
  • 신만용 (국민대학교 산림자원학과)
  • Received : 2007.02.06
  • Accepted : 2007.04.19
  • Published : 2007.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study was conducted to produce forest thematic maps and estimate forest statistics for Pyeongchang Gun using the kNN technique, which has been applied to produce thematic maps of variables of interest including unobserved plots by combining field plot data, remotely sensed data and other digital map data in forest inventories. The estimation errors for three horizontal reference areas (HRAs), whose radii are 20, 40 and 60 km respectively, were compared. Although the precision for the 40 km radius was lower compared to that for the 60 km radius, the 40 km radius was found to be an efficient HRA because their difference in precision was modest. At a value of k=5 nearest neighbors for the selected HRA, the overall accuracy was high. As a result, using the k=5 neighbors within the HRA of 40 km radius, thematic maps of number of trees, basal area, and growing stock per hectare were generated. As compared to the forest statistics based on field sample plots, the estimated means of each parameter from the produced maps were underestimated.

본 연구는 야외조사 자료와 원격탐사 자료를 연계하여 야외조사가 이루어지지 않은 미 관측지점의 산림정보를 추정하고 산림 주제도를 작성할 수 있는 kNN 기법을 이용하여 강원도 평창군을 대상으로 산림정보별 주제도를 작성하고, 산림통계량을 산출하였다. 수평참조범위 반경을 20, 40, 60 km로 구분한 후, 각 반경별 추정치의 오차를 비교하였다. 반경 60 km일 때, 최소 오차를 갖는 것으로 분석되었지만, 반경 40 km와 비교하면 차이가 없는 것으로 파악되어, 반경이 작은 반경 40 km을 효율적인 참조범위로 선정하였다. 선정된 수평참조범위에서 최적의 참조 표본점의 개수를 선정하기 위하여 오차행렬을 분석한 결과, k=5가 최적의 참조 표본점개수로 관측되었다. 따라서 최소 수평반경 40 km와 k=5의 참조표본점수를 이용하여 평창군 산림의 ha당 재적, 흉고단면적, 그리고 본수에 대한 주제도를 작성하였다. 작성된 주제도에 의해 추정된 산림통계량은 야외조사에 의한 추정치보다 과소추정치를 나타내었다.

Keywords

Acknowledgement

Grant : 우리나라의 지속가능한 산림경영에 필요한 효율적인 표본조사 방법의 개발

Supported by : 한국과학재단

References

  1. 산림청. 2004a. 임업통계요람. 434p
  2. 산림청. 2004b. 국내외 여건변화에 다른 산림자원조사체계 개편연구(III). 284p
  3. 산림청. 2005. 국내외 여건변화에 따른 산림자원조사체계 개편연구(IV). 290p
  4. 이승호, 김철민, 원현규, 김경민, 조현국. 2004. Landsat TM 위성영상을 위한 산림자원량 산정. 한국임학회 정기학술발표 논문집, pp 250-252
  5. 임업연구원. 1996. 전국산림자원조사요령. 49p
  6. Altman, N.S. 1992. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician 46(3): 175-184 https://doi.org/10.2307/2685209
  7. Cho, H.K. 2002. Untersuchungen ber die Erfassung von Waldflchen und deren Vernderungen mit Hilfe der Satel-litenfemerkundung und segmentbasierter Klassifikation. Dissertation zur Georg-August-Universitt Gttingen. 120p
  8. Franco-Lopez, H., A.R. Ek, and M.E. Bauer. 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 https://doi.org/10.1016/S0034-4257(01)00209-7
  9. Halme, M. and E. Tomppo. 2001. Improving the accuracy of multi-source forest inventory estimates by reducing plot location error a multi-criteria approach. Remote Sensing of Environment 78: 321-327 https://doi.org/10.1016/S0034-4257(01)00227-9
  10. Holmgren, P. and T. Thuresson. 1998. Satellite remote sensing for forestry planning a review. Scandinavian Journal of Forest Research 13:90-110 https://doi.org/10.1080/02827589809382966
  11. Katila, M. and E. Tomppo. 2001. Selecting estimation parameters for the Finnish multi source national forest inventory. Remote Sensing of Environment 76: 16-32 https://doi.org/10.1016/S0034-4257(00)00188-7
  12. Katila, M. and E. Tomppo. 2002. Stratification by ancillary data in multisource forest inventories employing k-nearest-neighbour estimation. Canadian Journal of Forest Research 32(9): 1548-1561 https://doi.org/10.1139/x02-047
  13. Kleinn, C. 2002. New technologies and methodogies for national forest inventories. Unasylva 210(53): 10-18
  14. Lee, K.S. and J.S. Yoon. 1997. Radiometric correction of terrain effects for SPOT and Landsat Thematic mapper imagery in mountainous forest area. Journal of the Korean society of Remote sensing 13(3): 277-292
  15. McRoberts, R.E., M.D. Nelson, and D.G. Wndet. 2002. Stratified estimation of forest area using satellite imagery, inventoy data, and the k-neatest neighbors technique. Remote sensing of Environment 82: 457-468 https://doi.org/10.1016/S0034-4257(02)00064-0
  16. Reese, H., M. Nilsson, P. Sandstrm, and H. Olsson. 2002. Applications using estimates of forest parameters derived from satellite and forest inventory data. Computers and Electronics in Agriculture 37(1): 37-55 https://doi.org/10.1016/S0168-1699(02)00118-7
  17. Reese, H., T. Granqvist-Pahlen, M. Egberth, M. Nilsson, and H. Olsson, 2005. Automated estimation of forest parameters for Sweden using Landsat data and kNN algorithm. The 31 sl International symposium on Remote sensing Environment June 20-24 2005, Saint Petersburg, Russia
  18. Tokola, T., J. Pitknen, S. Partinen, and E. Muinonen. 1996. Point accuracy of a non-parametric method in estimation of forest characteristics with different satellite materials. International Journal of Remote Sensing 17(12): 2333-2351 https://doi.org/10.1080/01431169608948776
  19. Tokola, T. and J. Heikkila. 1997. Improving satellite image based forest inventory by using a priori site quality information. Silva Fennica 31(1): 67-78
  20. Tokola, T. 2000. The influence of field sample data location on growing stock volume estimation in Landsat TM-based forest inventory in eastern Finland. Remote sensing of environment 74(3): 422-431 https://doi.org/10.1016/S0034-4257(00)00135-8
  21. Tomppo, E. 1990. Satellite image-based national forest inventory of Finland. International Archives of Photogrammetry and Remote Sensing 28: 419-424. Proceedings of the Symposium on Global and Environmental Monitoring, Techniques and Impacts, 17-21 Sept. 1990. Victoria, British Columbia, Canada
  22. Tomppo, E., and M. Halme. 2004. Using coarse scale forest variables as ancillary information and weighting of variables in k-NN estimation: a genetic algorithm approach. Remote Sensing of Environment 92: 1-20 https://doi.org/10.1016/j.rse.2004.04.003