Atmosphere (대기)

Korean Meteorological Society (한국기상학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Forest Carbon Stock in South Korea Using Machine Learning with High-Resolution Remote Sensing Data

고해상도 원격탐사 자료와 기계학습을 이용한 한국 산림의 탄소 저장량 산정

  • Jaewon Shin (Environmental Planning Institute, Seoul National University) ;
  • Sujong Jeong (Environmental Planning Institute, Seoul National University) ;
  • Dongyeong Chang (Environmental Planning Institute, Seoul National University)
  • 신재원 (서울대학교 환경계획연구소) ;
  • 정수종 (서울대학교 환경계획연구소) ;
  • 장동영 (서울대학교 환경계획연구소)
  • Received : 2023.02.15
  • Accepted : 2023.02.19
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Accurate estimation of forest carbon stocks is important in establishing greenhouse gas reduction plans. In this study, we estimate the spatial distribution of forest carbon stocks using machine learning techniques based on high-resolution remote sensing data and detailed field survey data. The high-resolution remote sensing data used in this study are Landsat indices (EVI, NDVI, NDII) for monitoring vegetation vitality and Shuttle Radar Topography Mission (SRTM) data for describing topography. We also used the forest growing stock data from the National Forest Inventory (NFI) for estimating forest biomass. Based on these data, we built a model based on machine learning methods and optimized for Korean forest types to calculate the forest carbon stocks per grid unit. With the newly developed estimation model, we created forest carbon stocks maps and estimated the forest carbon stocks in South Korea. As a result, forest carbon stock in South Korea was estimated to be 432,214,520 tC in 2020. Furthermore, we estimated the loss of forest carbon stocks due to the Donghae-Uljin forest fire in 2022 using the forest carbon stock map in this study. The surrounding forest destroyed around the fire area was estimated to be about 24,835 ha and the loss of forest carbon stocks was estimated to be 1,396,457 tC. Our model serves as a tool to estimate spatially distributed local forest carbon stocks and facilitates accounting of real-time changes in the carbon balance as well as managing the LULUCF part of greenhouse gas inventories.

Keywords

Acknowledgement

본 논문의 개선을 위해 좋은 의견을 제시해 주신 두 분의 심사위원께 감사를 드립니다. 본 연구는 국토교통부/국토교통과학기술진흥원의 지원(과제번호 23UMRG-B158194-04)으로 수행되었습니다.

References

  1. Dixon, R. K., A. M. Solomon, S. Brown, R. A. Houghton, M. C. Trexier, and J. Wisniewski, 1994: Carbon pools and flux of global forest ecosystems. Science, 263, 185-190, doi:10.1126/science.263.5144.185. 
  2. Eggleston, H., L. Buendia, K. Miwa T. Ngara, and K. Tanabe, 2006: 2006 IPCC guidelines for national greenhouse gas inventories. 
  3. Friedlingstein, P., and Coauthors, 2020: Global carbon budget 2020. Earth Syst. Sci. Data., 12, 3269-3340, doi:10.5194/essd-12-3269-2020. 
  4. Gallaun, H., G. Zanchi, G.-J. Nabuurs, G. Hengeveld, M. Schardt, and P. J. Verkerk, 2010: EU-wide maps of growing stock and above-ground biomass in forests based on remote sensing and field measurements. Forest ecology and management, 260, 252-261, doi:10.1016/j.foreco.2009.10.011. 
  5. Harris, N. L., and Coauthors, 2021: Global maps of twenty-first century forest carbon fluxes. Nature Climate Change, 11, 234-240, doi:10.1038/s41558-020-00976-6. 
  6. Jung, J., H. Nguyen, J. Heo, K.-M. Kim, and J. Im, 2014: Estimation of aboveground forest biomass carbon stock by satellite remote sensing - A Comparison between k-nearest neighbor and regression tree analysis -. Korean Journal of Remote Sensing, 30, 651-664, doi:10.7780/kjrs.2014.30.5.10. 
  7. Lee, J.-H., J.-H. Im, K.-M. Kim, and J. Heo, 2015: Change analysis of aboveground forest carbon stocks according to the land cover change using multi-temporal landsat TM images and machine learning algorithms. Journal of the Korean Association of Geographic Information Studies, 18, 81-99, doi:10.11108/kagis. 2015.18.4.081. 
  8. Olivier, J., K. Schure, and J. Peters, 2017: Trends in global CO2 and total greenhouse gas emissions. PBL Netherlands Environmental Assessment Agency, 5, 1-11. 
  9. Sim, W., J. Park, and J. Lee, 2017: A study on the utilization plan of national geospatial information for land use change matrix. Journal of Forest Economics, 24, 41-50. 
  10. Yu, S. C., J. W. Ahn, and J. A. Ok, 2015: A study on constriction plan of the statistics for national green house gas inventory (LULUCF Sector). Journal of Korea Spatial Information Society, 23, 67-77.  https://doi.org/10.12672/ksis.2015.23.3.067
  11. GIR (Greenhouse Gas Inventory & Research Center of Korea). National Greenhouse Gas Inventory Report of Korea. 
  12. IPCC, 2006: IPCC guidelines for national greenhouse gas inventories. 
  13. Korea Forest Resarch Institute, 2007: Survey Manual for Forest Biomass and Soil Carbon. 
  14. Korea Forest Resarch Institute, 2010: Forest Biomass Assessment in Korea. 
  15. Korea Forest Servise, 2017: The 7th National Forest Inventory and Forest Health Monitoring Guidebook. 
  16. UNFCCC, 1997: Kyoto Protocol. 
  17. FGIS, 2023: Korea Forest Servise. Forest Geospatial Information System. [Available online at https://www.forest.go.kr/newkfsweb/html/HtmlPage.do?pg=/fgis/UI_KFS_5002_020100.html&mn=KFS_02_04_03_04_0 1&orgId=fgis] (in Korean). 
  18. Ministry of Government Legislation, 2021: Guidelines for preparing land cover maps. [Available online at https://www.law.go.kr/%ED%96%89%EC%A0%95%EA%B7%9C%EC%B9%99/%ED%86%A0%EC%A7%80%ED%94%BC%EB%B3%B5%EC%A7%80%EB%8F%84%EC%9E%91%EC%84%B1%EC%A7%80%EC%B9%A8] (in Korean). 
  19. NASA, 2023: Fire Information for Resource Management System. [Available online at https://firms.modaps.eosdis.nasa.gov/map/#d:24hrs;@0.0,0.0,3z]. 
  20. NOAA, 2023. Global Monitering Laboratory. [Available online at https://gml.noaa.gov/ccgg/trends/].