Journal of Korean Society of Forest Science (한국산림과학회지)

Korean Society of Forest Science (한국산림과학회)
권호 표지

Comparison of Forest Growing Stock Estimates by Distance-Weighting and Stratification in k-Nearest Neighbor Technique

거리 가중치와 층화를 이용한 최근린기반 임목축적 추정치의 정확도 비교

  • Yim, Jong Su (Department of Forest Environment System, College of Forest Sciences, Kookmin University) ;
  • Yoo, Byung Oh (Southern Forest Resources Research Center, Korea Forest Research Institute) ;
  • Shin, Man Yong (Department of Forest Environment System, College of Forest Sciences, Kookmin University)
  • 임종수 (국민대학교 산림환경시스템학과) ;
  • 유병오 (국립산림과학원 남부산림자원연구소) ;
  • 신만용 (국민대학교 산림환경시스템학과)
  • Published : 2012.09.30
⟨ Previous Next ⟩

Abstract

The k-Nearest Neighbor (kNN) technique is popularly applied to assess forest resources at the county level and to provide its spatial information by combining large area forest inventory data and remote sensing data. In this study, two approaches such as distance-weighting and stratification of training dataset, were compared to improve kNN-based forest growing stock estimates. When compared with five distance weights (0 to 2 by 0.5), the accuracy of kNN-based estimates was very similar ranged ${\pm}0.6m^3/ha$ in mean deviation. The training dataset were stratified by horizontal reference area (HRA) and forest cover type, which were applied by separately and combined. Even though the accuracy of estimates by combining forest cover type and HRA- 100 km was slightly improved, that by forest cover type was more efficient with sufficient number of training data. The mean of forest growing stock based kNN with HRA-100 and stratification by forest cover type when k=7 were somewhat underestimated ($5m^3/ha$) compared to statistical yearbook of forestry at 2011.

본 연구는 최근린 기법에서 거리가중치와 훈련자료의 층화에 의한 추정치의 정확도를 비교하여 효율적인 방법을 모색하기 위하여 수행하였다. 거리가중치의 경우, 유사성이 높은 훈련자료에 가중치를 부여하는 방법으로 일반적으로 적용되는 5가지의 계수(0, 0.5, 1, 1.5, 그리고 2)를 비교한 결과, 평균 편차에서 최대 ${\pm}0.6m^3/ha$로 정확도는 유사한 것으로 나타났다. 훈련자료의 층화에서는 임상구분을 적용하였을 때 추정치의 정확도가 가장 높은 것으로 나타났으며, 임상구분과 참조수평거리(반경=100 km)를 통합하여 적용하였을 경우에는 임상구분에 의한 추정치와 유사한 정확도를 나타내었다. 연구대상지의 2010년 기준 평균임목축적과 비교한 결과 최근린 기반 추정치가 약 $5m^3/ha$ 정도 과소 추정되었지만, 조사시점을 고려하였을 때 상당한 정확도를 나타낸 것으로 평가된다.

Keywords

References

  1. 국립산림과학원. 2004. 임목자원평가.예측 프로그램.
  2. 국립산림과학원. 2009. 제5차 국가산림자원조사 현지조사지침서-ver.1.3-.
  3. 성주군. 2009. 성주군 통계요람.
  4. 산림청. 2011. 임업통계연보
  5. 임종수, 김성호, 공지수와 신만용. 2007. k-Nearest Neighbor 기법을 이용한 강원도 평창군의 산림주제도 작성과 산림 통계량 추정. 한국임학회지 96(3): 259-268.
  6. 임종수, 한원성, 정일빈, 김성호, 신만용. 2010a. 소면적 산림축적량 추정을 위한 합성추정법의 적용. 한국임학회지 99(3): 311-320.
  7. 임종수, 정상영, 정일빈, 조현국, 신만용. 2010b. 위성영상 변수를 이용한 최근린 기반 추정치의 정확도 향상. 한국임학회 정기총회 및 정기학술논문 발표논문집 (CD). 443-446.
  8. 정상영, 임종수, 조현국, 정진현, 김성호, 신만용. 2009. 산림 바이오매스 변환표와 위성영상을 이용한 무주군의 산림 바이오매스 추정. 한국임학회지 98(4): 409-416.
  9. 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. https://doi.org/10.1016/S0034-4257(01)00209-7
  10. Hans, F., 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. https://doi.org/10.1016/j.rse.2008.07.017
  11. Katila, M. and Tomppo, E. 2002. Stratification by ancillary data in multisource forest inventories employing knearest- neighbor estimation. Canadian Journal of Forest Research 32(9): 1548-1561. https://doi.org/10.1139/x02-047
  12. Lappi, J. and Kanagas, A. 2006. Use of additional information. pp. 107-117. In: A. Kangas and M. Maltamo, ed. Forest Inventory-Methodology & Application. Springer.
  13. McRoberts, R.E. and Tomppo, E. 2007. Remote sensing support for national forest inventories. Remote Sensing of Environment 110: 412-419. https://doi.org/10.1016/j.rse.2006.09.034
  14. Nilsson, M. 1997. Estimation of forest variables using satellite image data and airborne lidar. Doctoral thesis. Acta Univ. Agric. Suec. 17.
  15. Reese, H., Nilsson, M., Granqvist Pahlen, T., Hagner, O., Joyce, S., Tingelöf, U., Egberth, M., and Olsson, H. 2003. Countrywide estimates of forest variables using satellite data and field data from the National Forest Inventory. Ambio 32: 542-548.
  16. Tokola, T., Pitkanen, J., Partinen, S. and Muinonen, E. 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
  17. Tomppo, E. and Halme, M. 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
  18. Tomppo, E., Olsson, H. Stahl, G., Nilsson, M., Hngner, O. and Katila, M. 2008. Combining national forest inventory field plots and remote sensing data for forest database. Remote Sensing of Environment 112: 1982-1999. https://doi.org/10.1016/j.rse.2007.03.032
  19. Yim, J.S., Kim, Y.H., Kim, S.H., Jeong, J.H. and Shin, M.Y. 2011. Comparison of k-nearest neighbor technique with geographical calibration for estimating forest growing stock volume. Canadian Journal of Forest Research 44(1): 73-82.