Prediction of Landslides Occurrence Probability under Climate Change using MaxEnt Model

MaxEnt 모형을 이용한 기후변화에 따른 산사태 발생가능성 예측

  • Kim, Hogul (Graduate School, Seoul National University) ;
  • Lee, Dong-Kun (Department of Landscape Architecture and Rural System Engineering, Seoul National University) ;
  • Mo, Yongwon (Graduate School, Seoul National University) ;
  • Kil, Sungho (Graduate School, Seoul National University) ;
  • Park, Chan (National Institute of Environmental Research, Climate Change Research Division) ;
  • Lee, Soojae (Korea Environment Institute)
  • 김호걸 (서울대학교대학원) ;
  • 이동근 (서울대학교조경.지역시스템공학부) ;
  • 모용원 (서울대학교대학원) ;
  • 길승호 (서울대학교대학원) ;
  • 박찬 (국립환경과학원기후변화연구과) ;
  • 이수재 (한국환경정책.평가연구원)
  • Received : 2012.11.27
  • Accepted : 2013.01.16
  • Published : 2013.02.28


Occurrence of landslides has been increasing due to extreme weather events(e.g. heavy rainfall, torrential rains) by climate change. Pyeongchang, Korea had seriously been damaged by landslides caused by a typhoon, Ewiniar in 2006. Moreover, the frequency and intensity of landslides are increasing in summer due to torrential rain. Therefore, risk assessment and adaptation measure is urgently needed to build resilience. To support landslide adaptation measures, this study predicted landslides occurrence using MaxEnt model and suggested susceptibility map of landslides. Precipitation data of RCP 8.5 Climate change scenarios were used to analyze an impact of increase in rainfall in the future. In 2050 and 2090, the probability of landslides occurrence was predicted to increase. These were due to an increase in heavy rainfall and cumulative rainfall. As a result of analysis, factors that has major impact on landslide appeared to be climate factors, prediction accuracy of the model was very high(92%). In the future Pyeongchang will have serious rainfall compare to 2006 and more intense landslides area expected to increase. This study will help to establish adaptation measure against landslides due to heavy rainfall.


maximum entropy model;RCP 8.5 scenario;heavy rainfall;landslide susceptibility


Grant : 산림 생태계서비스의 기후변화 리스크 평가 및 관리체계 수립을 위한 연구

Supported by : 한국환경정책.평가연구원


  1. 국립환경과학원, 2012, 기후변화 부문별 취약성 지도.
  2. 권혁춘, 이병걸, 이창선, 고정우, 2011, 로지스틱회귀분석기법과 인공신경망기법을 이용한 제주지역 산사태가능성분석, 한국지형공간정보학회지 19(3), 33-40.
  3. 김경수, 김원영, 채병공, 송영석, 조용찬, 2005, 강우에 의해 발생된 자연사면 산사태의 지질공학적 분석 -용인.안성지역을 대상으로- , 대한지질공학회지 15(2), 105-121.
  4. 김기흥, 정혜련, 박재현, 마호섭, 2011, 경남지역 산사태 발생지의 강우 및 지형특성분석, 한국환경복원기술학회지 14(2), 33-45.
  5. 김석우, 전근우, 김진학, 김민식, 김민석, 2012, 2011년 집중호우로 인한 산사태 발생특성분석, 한국임학회지 101(1), 28-35.
  6. 박종민, 마호섭, 강원석, 오경원, 박성학, 이성재, 2010, 전라북도 지역의 산사태발생 특성분석, 농업생명과학연구 44(4), 9-20.
  7. 연영광, 2011, 로지스틱 회귀분석 기법을 이용한 강원도 산사태 취약성 평가 및 분석, 한국지리정보학회지 14(4), 116-128.
  8. 오치영, 김경탁, 최철웅, 2009, SPOT5영상과 GIS분석을 이용한 인제지역의 산사태 특성 분석, 대한원격탐사학회지 25(5), 445-454.
  9. 윤홍식, 이동하, 서용철, 2009, GIS 기법 및 발생자료 분석을 이용한 산사태 위험지도 작성, 한국지리정보학회지 12(4), 59-74.
  10. 이명진, 이사로, 전성우, 2012, 미래 확률강우량 및 인공신경망을 이용한 산사태 위험도 분석기법 개발 및 검증, 한국지리정보학회지 15(2), 57-70.
  11. 이부경, 2003, 지질방재공학, pp. 241-245.
  12. 이수곤, 1999, 부산지역의 산사태 위험 연구, 한국환경복원녹화기술학회지 2(2), 9-23.
  13. 이진덕, 연상호, 김성길, 이호찬, 2002, 산사태의 발생가능지 예측을 위한 GIS의 적용, 한국지리정보학회지 5(1), 38-47.
  14. 조명희, 조윤원, 2009, 기상과 지형자료를 통합한 산사태 위험지 예측 기법 개발 -울진지역을 대상으로-, 한국지리정보학회지 12(2), 1-10.
  15. Elith J., Ferrier S., Huettmann F., and Leathwick J., 2006, The evaluation strip: A new and robust method for plotting predicted responses from species distribution models, Ecol Model 186(3), 280-289.
  16. Felicisimo, A., Cuartero A., Remondo J. and Quiros E., 2012, Mapping landslide susceptibility with logistic regression, multiple adaptive regression splines, classification and regression trees, and maximum entropy methods: a comparative study, Landslides (7 March 2012), pp.1-15.
  17. Mathewson, C.C., Keaton, J.R. and Santi, P.M., 1990, Role of Bedrock Ground Water in the Initiation of Debris Flows and Sustained Post-Flow Stream Discharge, Bulletin of the Association of Engineering Geologists 27(1), 73-83.
  18. Phillips, S.J., Anderson R.P. and Schapire R.E., 2004. A maximum entropy approach to species distribution modeling. In: Proceedings of the Twenty-First International Conference on Machine Learning, Banff, Alberta, Canada, p. 83 ff.
  19. Phillips, S.J. and Dudik, M., 2008. Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation. Ecography 31, 161-175.
  20. Pradhan B. and Lee S., 2010, Delineation of landslide hazard areas on Penang Island, Environment Earth Science 60, 1037-1054.
  21. Vorpahl, P., Helmut E., Michael M. and Boris S., 2012, How can statistical models help to determine driving factors of landslides?, Ecological Modelling 239, 27-39.

Cited by

  1. Policy Decision Making Through Wildlife Habitat Potential With Space Value Categorization vol.18, pp.1, 2015,
  2. Large-Scale Slope Stability Analysis Using Climate Change Scenario (2): Analysis of Application Results vol.17, pp.3, 2014,