Ecology and Resilient Infrastructure

Korean Society of Ecology and Infrastructure Engineering (응용생태공학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Carbon Accumulation within Semi-Mangrove Ecosystems Using Remote Sensing and Artificial Intelligence Modeling in Jeju Island, South Korea

원격탐사와 인공지능 모델링을 활용한 제주도 지역의 준맹그로브 탄소 축적량 예측

  • Cheolho Lee (Department Biological Sciences and Bioengineering, Inha University) ;
  • Jongsung Lee (Department Biological Sciences and Bioengineering, Inha University) ;
  • Chaebin Kim (Department Biological Sciences, Inha University) ;
  • Yeounsu Chu (Department Biological Sciences and Bioengineering, Inha University) ;
  • Bora Lee (Warm-Temperate and Subtropical Forest Research Center, National Institute of Forest Science)
  • 이철호 (인하대학교 바이오시스템융합학부) ;
  • 이종성 (인하대학교 바이오시스템융합학부) ;
  • 김채빈 (인하대학교 생명과학과) ;
  • 추연수 (인하대학교 바이오시스템융합학부) ;
  • 이보라 (국립산림과학원 난대.아열대산림연구소)
  • Received : 2023.10.30
  • Accepted : 2023.11.09
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

We attempted to estimate the carbon accumulation of Hibiscus hamabo and Paliurus ramosissimus, semimangroves native to Jeju Island, by remote sensing and to build an artificial intelligence model that predicts its spatial variation with climatic factors. The aboveground carbon accumulation of semi-mangroves was estimated from the aboveground biomass density (AGBD) provided by the Global Ecosystem Dynamics Investigation (GEDI) lidar upscaled using the normalized difference vegetation index (NDVI) extracted from Sentinel-2 images. In Jeju Island, carbon accumulation per unit area was 16.6 t C/ha for H. hamabo and 21.1 t C/ha for P. ramosissimus. Total carbon accumulation of semi-mangroves was estimated at 11.5 t C on the entire coast of Jeju Island. Random forest analysis was applied to predict carbon accumulation in semi-mangroves according to environmental factors. The deviation of aboveground biomass compared to the distribution area of semi-mangrove forests in Jeju Island was calculated to analyze spatial variation of biomass. The main environmental factors affecting this deviation were the precipitation of the wettest month, the maximum temperature of the warmest month, isothermality, and the mean temperature of the wettest quarter. The carbon accumulation of semi-mangroves predicted by random forest analysis in Jeju Island showed spatial variation in the range of 12.0 t C/ha - 27.6 t C/ha. The remote sensing estimation method and the artificial intelligence prediction method of carbon accumulation in this study can be used as basic data and techniques needed for the conservation and creation of mangroves as carbon sink on the Korean Peninsula.

본 연구에서는 제주도에서 자생하는 준맹그로브인 황근 (Hibiscus hamabo)과 갯대추나무 (Paliurus ramosissimus)의 탄소 저장량을 원격탐사로 추정하고 기후요인에 의하여 공간변이를 예측하는 인공지능 모델을 구축하고자 하였다. 준맹그로브의 지상부 탄소 축적량은 Global Ecosystem Dynamics Investigation (GEDI) 라이다에 의하여 제공되는 지상부 생물량 밀도(aboveground biomass density, AGBD)를 Sentinel-2 영상으로부터 추출한 normalized difference vegetation index (NDVI)으로 해상도를 상향하여 추정하였다. 제주도에서 단위면적당 탄소 축적량은 황근이 16.6 t C/ha, 갯대추나무가 21.1 t C/ha이었다. 제주도 전 해안에서 준맹그로브의 탄소 축적량은 11.5 t C로 추정되었다. 환경요인에 따른 준맹그로브의 탄소 축적량을 예측하기 위하여 랜덤 포레스트 기술을 적용하였다. 제주도 준맹그로브림의 분포면적 대비 지상부 생물량의 잔차를 계산하였다. 이 잔차에 영향을 미치는 주요 환경요인으로는 가장 습한 달의 강수량, 가장 더운 달의 최고온도, 등온성 및 가장 습한 달의 평균 온도가 선정되었다. 제주도에서 랜덤 포레스트 분석으로 예측된 준맹그로브의 탄소 축적량은 12.0 t C/ha - 27.6 t C/ha 범위의 공간적 변이를 나타내었다. 본 연구에서 개발된 탄소 축적량의 원격탐사 추정법과 환경요인에 따른 인공지능 예측법은 한반도에서 탄소흡수원으로서 맹그로브의 보전과 조성에 필요한 기초자료로 활용할 수 있을 것이다.

Keywords

Acknowledgement

본 연구는 국립산림과학원 난대·아열대산림연구소 '자생 맹그로브 국내 잠재조성 예측 고도화 및 맹그로브 류 탄소지도 제작' (과제번호 FE0100-2022-04-2023)에 의해 수행되었습니다.

References

  1. Ahn, Y.H., Chung, K.H. and Park, H.S. 2003. Vegetation and flora of Hibiscus hamabo inhabited naturally in Soan Island. Journal of Environmental Science International 12(11): 1181-1187. (in Korean) https://doi.org/10.5322/JES.2003.12.11.1181
  2. Alongi, D.M. 2020. Carbon balance in salt marsh and mangrove ecosystems: A global synthesis. Journal of Marine Science and Engineering 8(10): 767.
  3. Breiman, L. 2001. Random forests. Machine Learning 45: 5-32. https://doi.org/10.1023/A:1010933404324
  4. Duncanson, L., Kellner, J.R., Armston, J., Dubayah, R., Minor, D.M., Hancock, S., Healey, S.P., Patterson, P.L., Saarela, S. and Marselis, S. 2022. Aboveground biomass density models for NASA's Global Ecosystem Dynamics Investigation (GEDI) lidar mission. Remote Sensing of Environment 270: 112845.
  5. GMA. 2022. The State of the World's Mangroves. Global Mangrove Alliance, Arlington, USA.
  6. Hickey, S.M., Callow, N.J., Phinn, S., Lovelock, C.E. and Duarte, C.M. 2018. Spatial complexities in aboveground carbon stocks of a semi-arid mangrove community: A remote sensing height-biomass-carbon approach. Estuarine. Coastal and Shelf Science 200: 194-201. https://doi.org/10.1016/j.ecss.2017.11.004
  7. IPCC. 2018. Special Report: Global Warming of 1.5℃. Intergovernmental Panel on Climate Change. Geneva, Switzerland.
  8. IPCC. 2019. IPCC Special Report on the Ocean and Cryosphere in a Changing Climate. Intergovernmental Panel on Climate Change. Geneva, Switzerland.
  9. IPCC. 2021. Climate change 2021: The Physical Science Basis. Intergovernmental Panel on Climate Change. Geneva, Switzerland.
  10. IPCC. 2022. Climate change 2022: Impacts, Adaptation and Vulnerability. Intergovernmental Panel on Climate Change, Geneva, Switzerland.
  11. Kolmogorov, A.N. 1933. Sulla determinazione empirica di una legge didistribuzione. Giorn Dell'inst Ital Degli Att 4: 89-91.
  12. Lariviere, B. and Van den Poel, D. 2005. Predicting customer retention and profitability by using random forests and regression forests techniques. Expert Systems with Applications 29(2): 472-484. https://doi.org/10.1016/j.eswa.2005.04.043
  13. Li, C.H., Zhou, H.W., Wong, Y.S. and Tam, N.F.Y. 2009. Vertical distribution and anaerobic biodegradation of polycyclic aromatic hydrocarbons in mangrove sediments in Hong Kong, South China. Science of the Total Environment 407(21): 5772-5779. https://doi.org/10.1016/j.scitotenv.2009.07.034
  14. Liaw, A. and Wiener, M. 2002. Classification and regression by random forest. R News 2(3): 18-22.
  15. Lovelock, C.E., Friess, D.A., Kauffman, J.B. and Fourqurean, J.W. 2018. Human impacts on blue carbon ecosystems. In, Windham-Myers, L., Crooks, S. and Troxler, T.G. (eds.), A Blue Carbon Primer, CRC Press, Boca Raton, USA. pp. 17-24.
  16. Lu, X., Zheng, G., Miller, C. and Alvarado, E. 2017. Combining multi-source remotely sensed data and a process-based model for forest aboveground biomass updating. Sensors 17(9): 2062.
  17. Mcleod, E., Chmura, G.L., Bouillon, S., Salm, R., Bjork, M., Duarte, C.M., Lovelock, C.E., Schlesinger, W.H. and Silliman, B.R. 2011. A blueprint for blue carbon: toward an improved understanding of the role of vegetated coastal habitats in sequestering CO2. Frontiers in Ecology and the Environment 9(10): 552-560. https://doi.org/10.1890/110004
  18. Musthafa, M. and Singh, G. 2022. Forest above-ground woody biomass estimation using multi-temporal spaceborne LiDAR data in a managed forest at Haldwani, India. Advances in Space Research 69(9): 3245-3257. https://doi.org/10.1016/j.asr.2022.02.002
  19. Natural Earth. 2022. Global 1:10 m Cultural Vectors. https://www.naturalearthdata.com. Accessed 24 April 2023.
  20. NIBR. 2023. National List of Species of Korea. National Institute of Biological Resources. https://species.nibr.go.kr/index.do. Accessed 3 April 2023.
  21. NIFS. 2022. Analysis and Prediction of Potential Distribution of Mangroves in Korea. National Institute of Forest Research, Seoul, South Korea. (in Korean)
  22. NIFS. 2023. Advanced Prediction of Potential Distribution and Production of Carbon Maps of Indigenous Mangroves in Korea. National Institute of Forest Research, Seoul, South Korea. (in Korean)
  23. Nobrega, G.N., Ferreira, T.O., Siqueira Neto, M., Mendonca, E.D.S., Romero, R.E. and Otero, X.L. 2019. The importance of blue carbon soil stocks in tropical semiarid mangroves: a case study in Northeastern Brazil. Environmental Earth Sciences 78: 1-10. https://doi.org/10.1007/s12665-019-8368-z
  24. OECD. 2011. OECD Environmental Outlook to 2050. Organisation for Economic Co-operation and Development. pp. 397-413.
  25. Oliveira, S., Oehler, F., San-Miguel-Ayanz, J., Camia, A. and Pereira, J.M. 2012. Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest. Forest Ecology and Management 275: 117-129. https://doi.org/10.1016/j.foreco.2012.03.003
  26. QGIS Association. 2022. QGIS Geographic Information System. http://www.qgis.org. Accessed 1 October 2022.
  27. R Development Core Team. 2023. R: A Language and Environment for Statistical Computing. Vienna, Austria.
  28. Sanderman, J., Hengl, T., Fiske, G., Solvik, K., Adame, M.F., Benson, L., Bukoski, J.J., Carnell, P., Cifuentes-Jara, M., Donato, D., Duncan, C., Eid, E.M., Ermgassen, P.z., Ewers, C., Glass, L., Gress, S., Jardine, S.L., Jones, T., Macreadie, P., Nsombo, E.N., Rahman, M.M., Sanders, C., Spalding, M. and Landis, E. 2018. A global map of mangrove forest soil carbon at 30 m spatial resolution. Environmental Research Letters 13(5): 055002.
  29. Taillardat, P., Ziegler, A.D., Friess, D. A., Widory, D., Van, V. T., David, F., Nguyen, T.N. and Marchand, C. 2018. Carbon dynamics and inconstant porewater input in a mangrove tidal creek over contrasting seasons and tidal amplitudes. Geochimica et Cosmochimica Acta 237: 32-48. https://doi.org/10.1016/j.gca.2018.06.012
  30. Worldclim. 2017. Global climate and weather data. https://www.worldclim.org/. Accessed 25 May 2023.