Journal of the Korean Association of Geographic Information Studies (한국지리정보학회지)

The Korean Association of Geographic Information Studies (한국지리정보학회)
권호 표지
DOI QR코드

DOI QR Code

Change Analysis of Aboveground Forest Carbon Stocks According to the Land Cover Change Using Multi-Temporal Landsat TM Images and Machine Learning Algorithms

다시기 Landsat TM 영상과 기계학습을 이용한 토지피복변화에 따른 산림탄소저장량 변화 분석

  • LEE, Jung-Hee (School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology) ;
  • IM, Jung-Ho (School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology) ;
  • KIM, Kyoung-Min (Global Forest Resources Division, Korea Forest Research Institute) ;
  • HEO, Joon (School of Civil and Environmental Engineering, Yonsei University)
  • 이정희 (울산과학기술대학교 도시환경공학부) ;
  • 임정호 (울산과학기술대학교 도시환경공학부) ;
  • 김경민 (국립산림과학원 국제산림연구과) ;
  • 허준 (연세대학교 사회환경시스템공학부)
  • Received : 2015.09.25
  • Accepted : 2015.12.21
  • Published : 2015.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The acceleration of global warming has required better understanding of carbon cycles over local and regional areas such as the Korean peninsula. Since forests serve as a carbon sink, which stores a large amount of terrestrial carbon, there has been a demand to accurately estimate such forest carbon sequestration. In Korea, the National Forest Inventory(NFI) has been used to estimate the forest carbon stocks based on the amount of growing stocks per hectare measured at sampled location. However, as such data are based on point(i.e., plot) measurements, it is difficult to identify spatial distribution of forest carbon stocks. This study focuses on urban areas, which have limited number of NFI samples and have shown rapid land cover change, to estimate grid-based forest carbon stocks based on UNFCCC Approach 3 and Tier 3. Land cover change and forest carbon stocks were estimated using Landsat 5 TM data acquired in 1991, 1992, 2010, and 2011, high resolution airborne images, and the 3rd, 5th~6th NFI data. Machine learning techniques(i.e., random forest and support vector machines/regression) were used for land cover change classification and forest carbon stock estimation. Forest carbon stocks were estimated using reflectance, band ratios, vegetation indices, and topographical indices. Results showed that 33.23tonC/ha of carbon was sequestrated on the unchanged forest areas between 1991 and 2010, while 36.83 tonC/ha of carbon was sequestrated on the areas changed from other land-use types to forests. A total of 7.35 tonC/ha of carbon was released on the areas changed from forests to other land-use types. This study was a good chance to understand the quantitative forest carbon stock change according to the land cover change. Moreover the result of this study can contribute to the effective forest management.

가속되는 지구온난화로 인해 한반도 주변의 탄소순환에 대한 명확한 이해의 필요성이 제기되고 있다. 산림은 이산화탄소의 주요 흡수원으로 지상 탄소량의 대부분을 저장하고 있어 이에 대한 추정이 필요하다. 우리나라에서는 국가산림자원조사의 표본점에서 측정되는 헥타르당 임목축적량을 활용하여 산림 탄소저장량을 추정한다. 하지만 탄소저장량은 요약된 수치 형태로 발표하고 있어 탄소저장량의 공간적 분포를 파악하는 것이 어렵다. 본 연구에서는 토지피복변화가 빠르고 국가산림자원조사 표본점 배치가 부족한 도시지역을 대상으로 UNFCCC의 Approach 3와 Tier 3를 충족하는 격자 기반 산림탄소저장량을 추정하였다. 토지피복변화 및 산림탄소저장량은 1991, 1992, 2010, 2011년에 취득된 Landsat 5 TM 영상과 고해상도 항공사진, 제 3차 및 제 5, 6차 국가산림자원조사 자료를 이용하여 추정하였다. 토지피복변화는 기계학습을 이용하여 변화된 토지피복과 변화되지 않은 토지피복 항목을 한 번에 분류하여 추정하였으며, 산림탄소저장량은 반사도, 밴드비율, 식생지수, 지형변수를 입력변수로 하여 기계학습을 통해 추정하였다. 연구 결과, 산림이 그대로 산림으로 유지되는 지역의 경우 33.23tonC/ha의 흡수를 하였으며 비산림이 산림으로 변한 지역의 경우 이보다 큰 36.83tonC/ha의 흡수가 진행된 것으로 추정되었다. 산림이 비산림으로 바뀐 경우에는 -7.35tonC/ha로, 배출이 일어난 것으로 추정되었다. 본 연구를 통하여 토지피복변화에 따른 산림탄소저장량 변화를 정량적으로 이해할 수 있었으며, 향후 효율적인 산림관리에 기여할 수 있을 것으로 판단된다.

Keywords

References

  1. Ahmed, O.S., S.E. Franklin, M.A. Wulder and J.C. White. 2015. Characterizing stand-level forest canopy cover and height using landsat time series, samples of airborne LiDAR, and the random forest algorithm. ISPRS Journal of Photogrammetry and Remote Sensing 101:89-101. https://doi.org/10.1016/j.isprsjprs.2014.11.007
  2. Breiman, L. 2001. Random forests. Machine Learning 45:5-32. https://doi.org/10.1023/A:1010933404324
  3. Chapelle, O., V. Vapnik, O. Bousquet and S. Mukherjee. 2002. Choosing multiple parameters for support vector machines. Machine Learning 46:131-159. https://doi.org/10.1023/A:1012450327387
  4. Crist, E.P. and R.C. Cicone. 1984. A physically-based transformation of thematic mapper data - the TM tasseled cap. IEEE Geoscience and Remote Sensing 3:256-263.
  5. Dube, T., O. Mutanga, A. Elhadi and R. Ismail. 2014. Intra-and-inter species biomass prediction in a plantation forest: testing the utility of high spatial resolution spaceborne multispectral Rapideye sensor and advanced machine learning algorithms. Sensors 14(8):15348-15370. https://doi.org/10.3390/s140815348
  6. Erdody, T. and L.M. Moskal. 2010. Fusion of LiDAR and imagery for estimating forest canopy fuels. Remote Sensing of Environment 114:725-737. https://doi.org/10.1016/j.rse.2009.11.002
  7. Foody, G.M. and A. Mathur. 2006. The use of small training sets containing mixed pixels for accurate hard image classification: training on mixed spectral responses for classification by a SVM. Remote Sensing of Environment 103(2):179-189. https://doi.org/10.1016/j.rse.2006.04.001
  8. Fuchs, H., P. Magdon, C. Kleinn and H. Flessa. 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
  9. Gleason, C.J. and J. Im. 2011. A review of remote sensing of forest biomass and biofuel: options for small area applications. GIScience and Remote Sensing 48(2):141-170. https://doi.org/10.2747/1548-1603.48.2.141
  10. Gleason, C.J. and J. Im. 2012. Forest biomass estimation from airborne lidar data using machine learning approaches. Remote Sensing of Environment 125:80-91. https://doi.org/10.1016/j.rse.2012.07.006
  11. Goetz, S.J., A. Baccini, N.T. Laporte, T. Johns, W. Walker, J. Kellndorfer, R.A. Houghton and M. Sun. 2009. Mapping and monitoring carbon stocks with satellite observations: a comparison of methods. Carbon Balance Management 4(2):2-8. https://doi.org/10.1186/1750-0680-4-2
  12. Hastie, T., R. Tibshirani and J.H. Friedman. 2009. The Elements of Statistical Learning Data Mining, Inference, and Prediction. Springer, 552pp.
  13. Huang, C.L. and C.J. Wang. 2006. A GA-based feature selection and parameters optimization for support vector machines. Expert Systems with Applications 31:231-240. https://doi.org/10.1016/j.eswa.2005.09.024
  14. Im, J.S., W.S. Han, J.H. Hwang, S.Y. Jeong, H.K. Cho and M.Y. Shin. 2009. Forest biomass estimation using satellite images and NFI data. Korean Journal of Remote Sensing 25(4):311-320 (임종수, 한원성, 황주호, 정상영, 조현국, 신만용. 2009. 위성영상자료 및 국가 산림자원조사 자료를 이용한 산림 바이오매스추정. 대한원격탐사학회지 25(4):311-320).
  15. Jung, J.H., J. Heo, S.H. Yoo, K.M. Kim and J.B. Lee. 2010. Estimation of aboveground biomass carbon stock in Danyang area using kNN algorithm and Landsat TM seasonal satellite images. Journal of Korean Society for Geospatial Information System 18(4):119-129 (정재훈, 허준, 유수홍, 김경민, 이정빈. 2010. kNN 알고리즘과 계절별 Landsat TM 위성영상을 이용한 단양군 지역의 지상부 바이오매스 탄소저장량 추정. 한국지형공간정보학회지 18(4):119-129).
  16. Jung, J.H., K.H. Uen, J. Heo, K.M. Kim and J.H. Im. 2014. Aboveground forest biomass estimation using satellite images - comparison and analysis of k-nearest neighbor method and regression tree analysis method. Korean Journal of Remote Sensing 30(5):651-654 (정재훈, 우엔 콩 효, 허 준, 김경민, 임정호. 2014. 위성영상을 활용한 지상부 산림바이오매스 탄소량 추정-k- Nearest Neighbor 및 Regression Tree Analysis 방법의 비교 분석. 대한원격탐사학회지 30(5):651-654). https://doi.org/10.7780/kjrs.2014.30.5.10
  17. Kattenborn, T., J. Maack, F. Fassnacht, F. Enssle, J. Ermert and B. Koch. 2015. Mapping forest biomass from space-Fusion of hyperspectral EO1-hyperion data and Tandem-X and WorldView-2 canopy height models. International Journal of Applied Earth Observation and Geoinformation 35:359-367. https://doi.org/10.1016/j.jag.2014.10.008
  18. Keerthi, S.S. and C.J. Lin. 2003. Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Computation 15:1667-1689. https://doi.org/10.1162/089976603321891855
  19. Kim, C.K., and S.H. Do. 2008. Planning research for applying the new IPCC guideline of national greenhouse gases responding to the climatic change convention. Korea Energy Economics Institute pp.1-170 (김찬규, 도승희. 2008. 기후변화협약 대응 국가온실가스 IPCC 신규 가이드라인 적용을 위한 기획연구. 에너지경제연구원 연구보고서. 1-170쪽).
  20. Kim, K.M., J.B. Lee, E.S. Kim, H.J. Park, Y.H. Roh, S.H. Lee, K.H. Park and H.S. Shin. 2011. Overview of research trends in estimation of forest carbon stocks based on remote sensing and GIS. Journal of the Korean Association of Geographic Information Studies 14(3):236-256 (김경민, 이정빈, 김은숙, 박현주, 노영희, 이승호, 박기호, 신휴석. 2011. 원격탐사와 GIS 기반의 산림탄소저장량 추정에 관한 주요국 연구동향 개관. 한국지리정보학회지 14(3):236-256). https://doi.org/10.11108/kagis.2011.14.3.236
  21. Kim, K.M., Y.H. Roh and E.S. Kim. 2014. Comparison of three kinds of methods on estimation of forest carbon stocks distribution using national forest inventory DB and forest type map. Journal of the Korean Association of Geographic Information Studies 17(4):69-85 (김경민, 노영희, 김은숙. 2014. 국가산림자원조사 DB와 임상도를 이용한 산림탄소저장량 공간분포 추정방법 비교. 한국지리정보학회지 17(4):69-85). https://doi.org/10.11108/kagis.2014.17.4.069
  22. Latifi, H., F.E. Fassnachtb, F. Hartig, C. Berger, J. Hernandez, P. Corvalan and B. Koch. 2015. Stratified aboveground forest biomass estimation by remote sensing data. International Journal of Applied Earth Observation and Geoinformation 38:229-241. https://doi.org/10.1016/j.jag.2015.01.016
  23. Li, M., J. Im, L.J. Quackenbush and T. Liu. 2014. Forest biomass and carbon stock quantification using airborne lidar data: a case study over huntington wildlife forest in the Adirondack park. Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Selected Topics in Applied Earth Observations and Remote Sensing 7(7):3143-3156. https://doi.org/10.1109/JSTARS.2014.2304642
  24. Markham, B.L. and J.L. Barker. 1987. Radiometric properties of US processed Landsat MSS data. Remote Sensing of Environment 22(1):39-71. https://doi.org/10.1016/0034-4257(87)90027-7
  25. Muukkonen, P. and J. Heiskanen. 2007. Biomass estimation over a large area based on standwise forest inventory data and ASTER and MODIS satellite data: a possibility to verify carbon inventories. Remote Sensing of Environment 107(4):617-624. https://doi.org/10.1016/j.rse.2006.10.011
  26. Neumann, M., S.S. Saatchi, L.M. Ulander and J.E. Fransson. 2012. Assessing performance of L-and P-band polarimetric interferometric SAR data in estimating boreal forest above-ground biomass. IEEE Geoscience and Remote Sensing 50(3):714-726. https://doi.org/10.1109/TGRS.2011.2176133
  27. Park, H.J., H.S. Shin, Y.H. Roh, K.M. Kim and K.H. Park. 2012. Estimating forest carbon stocks in Danyang using kriging methods for aboveground biomass. Journal of the Korean Association of Geographic Information Studies 15(1):16-33 (박현주, 신휴석, 노영희, 김경민, 박기호. 2012. 크리깅기법을 이용한 단양군의 산림 탄소저장량 추정-지상부 바이오매스를 대상으로-. 한국지리정보학회지 15(1):16-33). https://doi.org/10.11108/kagis.2012.15.1.016
  28. Popescu, S.C., R.H. Wynne and J.A. Scrivani. 2004. Fusion of smallfootprint LiDAR and multispectral data to estimate plot-level volume and biomass in deciduous and pine forests in Virginia, USA. Forest Science 50(4):551-565.
  29. Ramedani, Z., M. Omid, A. Keyhani, S. Shamshirband and B. Khoshnevisan. 2014. Potential of radial basis function based support vector regression for global solar radiation prediction. Renewable and Sustainable Energy Reviews 39:1005-1011. https://doi.org/10.1016/j.rser.2014.07.108
  30. Refsgaard, J.C., J.P. Sluijs, A.L. Hojberg and P.A. Vanrolleghem. 2007. Uncertainty in the environmental modeling process - a framework and guidance. Environmental Modeling & Software 22:1543-1556. https://doi.org/10.1016/j.envsoft.2007.02.004
  31. Shevade, S.K., S.S. Keerthi, C. Bhattacharyya and K.R.K. Murthy. 2000. Improvements to the SMO algorithm for SVM regression. IEEE Neural Networks 11:1188-1193. https://doi.org/10.1109/72.870050
  32. Wulder, M.A., J.C. White, R.A. Fournier, J.E. Luther and S. Magnussen. 2008. Spatially explicit large area biomass estimation: three approaches using forest inventory and remotely sensed imagery in a GIS. Sensors 8:529-560. https://doi.org/10.3390/s8010529
  33. Xu, C., F. Dai, X. Xu, and Y.H. Lee. 2012. GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang river watershed, China. Geomorphology 145:70-80.
  34. Yu, X., J. Hyyppa, M. Vastaranta, M. Holopainen and R. Viitala. 2011. Predicting individual tree attributes from airborne laser point clouds based on the random forests technique. ISPRS Journal of Photogrammetry and Remote Sensing 66(1):28-37. https://doi.org/10.1016/j.isprsjprs.2010.08.003
  35. Zhang, J., S. Huang, E.H. Hogg, V. Lieffers, Y. Qin and F. He. 2014. Estimating spatial variation in Alberta forest biomass from a combination of forest inventory and remote sensing data. Biogeosciences 11(10):2793-2808. https://doi.org/10.5194/bg-11-2793-2014

Cited by

  1. Mapping Forest Ecosystem Biomass Density for Xiangjiang River Basin by Combining Plot and Remote Sensing Data and Comparing Spatial Extrapolation Methods vol.9, pp.3, 2017, https://doi.org/10.3390/rs9030241
  2. Brief history of Korean national forest inventory and academic usage vol.43, pp.3, 2016, https://doi.org/10.7744/kjoas.20160032
  3. 산림의 CO2 흡수량 평가를 위한 통계 및 공간자료의 활용성 검토 - 안산시를 대상으로 - vol.27, pp.2, 2015, https://doi.org/10.14249/eia.2018.27.2.124
  4. 환경공간정보를 활용한 도시녹지의 탄소흡수량 추정 -안산시를 대상으로- vol.21, pp.3, 2015, https://doi.org/10.13087/kosert.2018.21.3.13
  5. 랜덤포레스트와 Sentinel-2를 이용한 식생 분류의 입력특성 최적화 vol.23, pp.4, 2020, https://doi.org/10.11108/kagis.2020.23.4.052