Journal of Environmental Impact Assessment (환경영향평가)

Korean Society of Environmental Impact Assessment (한국환경영향평가학회)
권호 표지
DOI QR코드

DOI QR Code

Mapping Mammalian Species Richness Using a Machine Learning Algorithm

머신러닝 알고리즘을 이용한 포유류 종 풍부도 매핑 구축 연구

  • Zhiying Jin (Department of Landscape Architecture and Rural Systems Engineering, Seoul National University) ;
  • Dongkun Lee (Department of Landscape Architecture and Rural Systems Engineering, Seoul National University) ;
  • Eunsub Kim (Interdisciplinary Program and Life Science, Graduate School of Environmental Studies, Seoul National University) ;
  • Jiyoung Choi (Research Institute of Agriculture and Life Sciences, Seoul National University) ;
  • Yoonho Jeon (Korea Environment Institute)
  • 김지영 (서울대학교 조경.지역시스템공학부) ;
  • 이동근 (서울대학교 조경.지역시스템공학부) ;
  • 김은섭 (서울대학교 협동과정 조경학) ;
  • 최지영 (서울대학교 농업생명과학연구원) ;
  • 전윤호 (한국환경연구원)
  • Received : 2023.12.19
  • Accepted : 2024.04.22
  • Published : 2024.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Biodiversity holds significant importance within the framework of environmental impact assessment, being utilized in site selection for development, understanding the surrounding environment, and assessing the impact on species due to disturbances. The field of environmental impact assessment has seen substantial research exploring new technologies and models to evaluate and predict biodiversity more accurately. While current assessments rely on data from fieldwork and literature surveys to gauge species richness indices, limitations in spatial and temporal coverage underscore the need for high-resolution biodiversity assessments through species richness mapping. In this study, leveraging data from the 4th National Ecosystem Survey and environmental variables, we developed a species distribution model using Random Forest. This model yielded mapping results of 24 mammalian species' distribution, utilizing the species richness index to generate a 100-meter resolution map of species richness. The research findings exhibited a notably high predictive accuracy, with the species distribution model demonstrating an average AUC value of 0.82. In addition, the comparison with National Ecosystem Survey data reveals that the species richness distribution in the high-resolution species richness mapping results conforms to a normal distribution. Hence, it stands as highly reliable foundational data for environmental impact assessment. Such research and analytical outcomes could serve as pivotal new reference materials for future urban development projects, offering insights for biodiversity assessment and habitat preservation endeavors.

생물다양성은 환경영향평가 제도의 목표에 중요한 부문으로, 개발대상지 입지 선정, 주변 환경 파악 및 교란으로 인한 생물종 영향 등에서 활용되고 있다. 환경영향평가 분야에서 새로운 기술과 모델을 활용하여 생물다양성을 보다 정확하게 평가하고 예측하는 방안에 대한 연구가 많이 진행되고 있다. 비록 현장, 문헌조사를 통한 데이터를 바탕으로 종 풍부도 지수를 평가하고 있으나, 현장 데이터는 시·공간적으로 미흡하므로 고해상도의 종 풍부도 매핑을 통한 기초자료를 활용함으로서, 모니터링 실효성 문제 해결이 필요하다. 따라서 본 연구에서는 제4차 전국자연환경조사 데이터와 환경변수를 바탕으로 Random forest 모델을 활용하여 종 분포모형을 개발하였다. 해당 모델은 24종의 포유류 종 분포 매핑 결과를 species richness index를 활용하여 100m 해상도의 종 풍부도 매핑 결과를 도출하였다. 연구 결과, 종 분포모형은 평균 0.82의 AUC값으로 우수한 예측 정확도를 보였다. 또한, 전국자연환경조사 데이터와 비교결과, 고 해상도의 종 풍부도 매핑 결과의 종 풍부도 분포는 정규분포의 형태를 가지고 있어 환경영향평가에서의 기초자료로 사용함에 있어 신뢰성이 높다. 본 연구의 분석결과는 추후 도시개발과 사업을 함에 있어 생물다양성 평가, 서식지 보전 등에 새로운 참고자료로 활용될 수 있을 것으로 사료된다.

Keywords

Acknowledgement

본 결과물은 환경부의 재원으로 한국환경산업기술원의 ICT기반 환경영향평가 의사결정 지원 기술개발사업(2021003360002)의 지원을 받아 연구되었습니다.

References

  1. Aertsen W, Kint V, Van Orshoven J, Ozkan K, Muys B. 2010. Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests. Ecological Modelling 221, 1119-30.
  2. Bae J, Kim S. 2021. Predictions of COVID-19 in Korea Using Machine Learning Models. Journal of the Korean Institute of Industrial Engineers, 47(3), 272-279, 10.7232/JKIIE.2021.47.3.272. [Korean Literature]
  3. Butchart SHM, Walpole M, Collen B, van Strien A, Scharlemann JPW, Almond REA, Baillie JEM, Bomhard B, Brown C, Bruno J, Carpenter KE, Carr GM, Chanson J, Chenery AM, Csirke J, Davidson NC, Dentener F, Foster M, Galli A, ... Watson R. 2010. Global Biodiversity: Indicators of Recent Declines. Science, 328(5982), 1164-1168.
  4. Cardinale BJ, Duffy JE, Gonzalez A, Hooper DU, Perrings C, Venail P, Narwani A, Mace GM, Tilman D, Wardle DA, Kinzig AP, Daily GC, Loreau M, Grace JB, Larigauderie A, Srivastava DS, Naeem S. 2012. Biodiversity loss and its impact on humanity. Nature, 486(7401), Article 7401.
  5. Carroll KA, Farwell LS, Pidgeon AM, Razenkova E, Gudex-Cross D, Helmers DP, Lewinska KE, Elsen PR, Radeloff VC. 2022. Mapping breeding bird species richness at management-relevant resolutions across the United States. Ecological Applications, 32(6), e2624.
  6. Chung H, Choi Y, Ryu J, Jeon S. 2020. Accuracy Evaluation of Potential Habitat Distribution in Pinus thunbergii using a Species Distribution Model: Verification of the Ensemble Methodology. Journal of Climate Change Research, 11(1), 37-51. [Korean Literature] https://doi.org/10.15531/KSCCR.2020.11.1.37
  7. Coll M, Pennino MG, Steenbeek J, Sole J, Bellido JM. 2019. Predicting marine species distributions: Complementarity of food-web and Bayesian hierarchical modelling approaches. Ecological Modelling, 405, 86-101.
  8. Franca S, Cabral HN. 2016. Predicting fish species distribution in estuaries: Influence of species' ecology in model accuracy. Estuarine, Coastal and Shelf Science, 180, 11-20.
  9. Franklin J. 2009. Mapping species distributions spatial inference and prediction, Cambridge: Cambridge University Press.
  10. Hassall C. 2012. Predicting the distributions of underrecorded Odonata using species distribution models. Insect Conservation and Diversity, 5(3), 192-201.
  11. Hernandez-Urcera J, Murillo FJ, Regueira M, Cabanellas-Reboredo M, Planas M. 2021. Preferential habitats prediction in syngnathids using species distribution models. Marine Environmental Research, 172, 105488.
  12. Hu J, Jiang Z. 2011. Climate Change Hastens the Conservation Urgency of an Endangered Ungulate, PLOS ONE, 6(8), e22873.
  13. Ives AR, Carpenter SR. 2007. Stability and Diversity of Ecosystems. Science, 317(5834), 58-62.
  14. Jiang L, Pu Z. 2009. Different Effects of Species Diversity on Temporal Stability in Single-Trophic and Multitrophic Communities. The American Naturalist, 174(5), 651-659.
  15. Jin LS, Kim J, Park Y-C. 2015. Analysis of habitat characteristics of leopard cat (Prionailurus bengalensis) in Odaesan National Park. Journal of Agriculture & Life Science, 49(3), 99-111. [Korean Literature]
  16. Kim J, Kwon H, Seo C, Kim M. 2014. A nationwide analysis of mammalian biodiversity hotspots in South Korea. Journal of Environmental Impact Assessment, 23(6), 453-465. [Korean Literature] https://doi.org/10.14249/eia.2014.23.6.453
  17. Kim J, Seo C, Kwon H, Ryu J, Kim M. 2012. A Study on the Species Distribution Modeling using National Ecosystem Survey Data. Journal of Environmental Impact Assessment, 21(4), 593-607. [Korean Literature]
  18. Koo M, Lee D. 2012. A Study on the National and International Research Trend of Biodiversity Assessment method and Its Application of Environmental Impact Assessment. Journal of Environmental Impact Assessment, 21(1), 119-132. [Korean Literature]
  19. Kwon H, Seo C, Park C. 2012. Development of Species Distribution Models and Evaluation of Species Richness in Jirisan region. Journal of Korean Society for Geospatial Information Science, 20(3), 11-18. [Korean Literature] https://doi.org/10.7319/kogsis.2012.20.3.011
  20. Lee S, Cho KH, Lee W. 2016. Prediction of Potential Distributions of Two Invasive Alien Plants, Paspalum distichum and Ambrosia artemisiifolia, Using Species Distribution Model in Korean Peninsula. Ecology and Resilient Infrastructure, 3(3), 189-200. [Korean Literature] https://doi.org/10.17820/ERI.2016.3.3.189
  21. Li J, Fan G, He Y. 2020. Predicting the current and future distribution of three Coptis herbs in China under climate change conditions, using the MaxEnt model and chemical analysis. Science of The Total Environment, 698, 134141.
  22. Li X, Wang Y. 2013. Applying various algorithms for species distribution modelling. Integrative Zoology, 8(2), 124-135.
  23. Lim C, Lee C, Jung S, Park Y. 2017. A Study on the Trail Mangement in National Park Using Habitat Suitability Assessment: A Case Study of Yellow-throated Marten Habitats in Mt. Mudeung National Park. Journal of the Korea Society of Environmental Restoration Technology, 20(4), 63-75. [Korean Literature]
  24. McKerrow AJ, Tarr NM, Rubino MJ, Williams SG. 2018. Patterns of species richness hotspots and estimates of their protection are sensitive to spatial resolution. Diversity and Distributions, 24(10), 1464-1477.
  25. Park C, Mo Y. 2021. Impact of Climate Change on Urban Bird Species Richness and the Importance of Urban Green Spaces. Journal of Climate Change Research, 12(5-1), 371-381. [Korean Literature] https://doi.org/10.15531/KSCCR.2021.12.5.371
  26. Pavlov YL. 2019. Random Forests, 1-122.
  27. Seo C, Park Y, Choi Y. 2008. Comparison of Species Distribution Models According to Location Data. Journal of the Korean society for geospatial information system, 16(4), 59-64. [Korean Literature]
  28. Seo C, Thorne JH, Hannah L, Thuiller W. 2009. Scale effects in species distribution models: implications for conservation planning under climate change, Biology Letters, 5(1), 39-43. [Korean Literature] https://doi.org/10.1098/rsbl.2008.0476
  29. Shin M-S, Seo C, Lee M, Kim J-Y, Jeon J-Y, Adhikari P, Hong S-B. 2018. Prediction of Potential Species Richness of Plants Adaptable to Climate Change in the Korean Peninsula. Journal of Environmental Impact Assessment, 27(6), 562-581. [Korean Literature]
  30. Watson RT, Heywood VH, Baste I, Dias B, Gamez R, Janetos T, Reid W, Ruark G. 1995. Global Biodiversity Assessment, Summary for Policy-Makers, Cambridge University Press, Cambridge (published for the United Nations Environment Programme).
  31. WEF. "Global Risk 2023" Report.