대한공간정보학회지 (Journal of Korean Society for Geospatial Information Science)

  • 제18권4호
  • /
  • Pages.61-69
  • /
  • 2010
  • /
  • 1598-2955(pISSN)
  • /
  • 2287-6693(eISSN)
대한공간정보학회 (Korea Spatial Information Society)
권호 표지

시맨틱 기술과 베이시안 네트워크를 이용한 산사태 취약성 분석

Landslide Susceptibility Analysis Using Bayesian Network and Semantic Technology

  • 이상훈 (한국건설기술연구원 U-국토연구실)
  • 투고 : 2010.10.20
  • 심사 : 2010.11.19
  • 발행 : 2010.12.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

비탈면 혹은 절성토지의 파괴로 사람과 재산에 심각한 피해를 입히기 때문에 미리 산사태 취약성 분석을 수행하여 개발 혹은 자연재해로부터 위험을 대비하는 것이 필요하다. 기존의 산사태 취약성 분석은 휴리스틱, 통계학적, 결정론적 혹은 확률론적 방법을 통해 이뤄졌다. 그러나, 적은 현장정보 등으로 분석의 신뢰도가 떨어지거나, 전문가의 경험과 지식을 기존 정량적인 해석모델에 반영하기 어려웠다. 본 연구는 산사태 취약성 분석에 대한 전문가 지식과 공간입력자료의 시맨틱을 추출하여 온톨로지 모델을 구축하고, 이를 베이시안 네트워크에 반영하여 확률적인 산사태 모델링을 제안하였다. 기존에 전문가 수작업으로 이뤄지던 베이시안 네트워크의 구조 생성을 온톨로지 모델의 지식추론으로 자동화하고, 현장정보뿐만 아니라 전문가 지식을 모델링에 반영하여 조건부 산사태 발생확률분포를 작성하였다. 이 결과를 GIS에 적용하여 산사태 취약성 지도를 작성하였다. 검증을 위해 충남 홍성일원의 오서산 지역에 적용한 결과 기존 산사태 발생흔적과 86.5% 일치하였다. 본 연구를 통해 일반 사용자도 전문가 도움 없이도 광역적인 산사태 취약성 분석이 가능하리라 기대된다.

The collapse of a slope or cut embankment brings much damage to life and property. Accordingly, it is very important to analyze the spatial distribution by calculating the landslide susceptibility in the estimation of the risk of landslide occurrence. The heuristic, statistic, deterministic, and probabilistic methods have been introduced to make landslide susceptibility maps. In many cases, however, the reliability is low due to insufficient field data, and the qualitative experience and knowledge of experts could not be combined with the quantitative mechanical?analysis model in the existing methods. In this paper, new modeling method for a probabilistic landslide susceptibility analysis combined Bayesian Network with ontology model about experts' knowledge and spatial data was proposed. The ontology model, which was made using the reasoning engine, was automatically converted into the Bayesian Network structure. Through conditional probabilistic reasoning using the created Bayesian Network, landslide susceptibility with uncertainty was analyzed, and the results were described in maps, using GIS. The developed Bayesian Network was then applied to the test-site to verify its effect, and the result corresponded to the landslide traces boundary at 86.5% accuracy. We expect that general users will be able to make a landslide susceptibility analysis over a wide area without experts' help.

키워드

참고문헌

  1. 산림청, 2004, "산사태위험지관리시스템", http://sansatai.forest.go.kr.
  2. 이상훈, 장병욱, 2009, "시멘틱 공유를 위한 MDA기반 지하공간정보 온톨로지 모델 개발", 지형공간정보학회, 제17권 제1호, pp.121-129.
  3. Barredo, J.I., Benavides, A., Hervas, J., Van Westen, C.J., 2000, "Comparing heuristic landslide hazard assessment techniques using GIS in the Tirajana basin", ITC Journal, Issue 1, 2000, pp.9-23.
  4. Chandrasekaran, B., Josephson, J.R. and Benjamins, V.R., 1999, "What are ontologies, and why do we need them", IEEE Intelligent Systems, Vol.14, No.1, pp.20-26. https://doi.org/10.1109/5254.747902
  5. Charniak, E, 1991, "Bayesian networks without tears", AI Magazine, Vol. 12(4), pp.50-63.
  6. Chen H, Lee CF, 2003, "A dynamic model for rainfall-induced landslides on natural slopes". Geomorphology vol. 51, pp.269-288. https://doi.org/10.1016/S0169-555X(02)00224-6
  7. Chung, C.F., Fabbri, A.G., van Westen, C.J., 1995, "Multivariate regression analysis for landslide hazard zonation", Geographical Information Systems in Assessing Natural Hazards, pp.107-133.
  8. Cooper, G. and Herskovits, E., 1991, "A bayesian method for constructing bayesian belief networks from databases", In Proceedings of Uncertainty in Artificial Intelligence.
  9. Chung, C.F. and Fabbri, A.G., 1999, "Probabilistic prediction models for landslide hazard mapping", Photogrammetric Engineering & Remote Sensing, Vol.65, No.12, pp.1389-1399.
  10. Cruden, D. M. and Varnes, D. J., 1996, "Landslide types and processes", Landslides: Investigation and Mitigation, TRB Special Report, 247, National Academy Press, Washington, pp.36-75.
  11. De Vel, O, Liu, N., Caelli, T. and Caetano, T., 2006, "An Embedded Bayesian Network Hidden Markov Model for Digital Forensics", IEEE Intelligence and Security Informatics Conference (ISI 2006), pp.459-465.
  12. Devitt, A., Danev, B., Matusikova, K., 2006, "Ontology-driven Automatic Construction of Bayesian Networks for Telecommunication Network Management", 2nd Int. Workshop : Formal Ontologies Meet Industry(FOMI 2006).
  13. Gritzner ML, Marcus WA, Aspinall R, Custer SG, 2001, "Assessing landslide potential using GIS, soil wetness modelling and topographic attributes", Geomorphology, vol. 37, pp.149-165. https://doi.org/10.1016/S0169-555X(00)00068-4
  14. Gruber, T., 1992, "A translation approach to portable ontology specification", Knowledge Systems Laboratory, Stanford University, Stanford, CA, Technical Report KSL 92-71.
  15. Helsper, E. and der Gaag, L. C. Van, 2002, "Building bayesian networks through ontologies", In Proceedings of the 15th European Conference on Artificial Intelligence, pp.680-684.
  16. Jensen, F.V., 2001, "Bayesian Networks and Decision Graphs", Springer, New York.
  17. Kalacska, M., Sanchez-Azofeifa, G.A., Caelli, T., Rivard, B.; Boerlage, B., 2005, "Estimating leaf area index from satellite imagery using Bayesian networks", Geoscience and Remote Sensing, IEEE Transactions on Vol. 43, Issue 8, pp.1866-1873. https://doi.org/10.1109/TGRS.2005.848412
  18. Lam, W. and Bacchus, F., 1993, "Learning bayesian belief networks: An approach based on the mdl principle", Computational Intelligence, Vol. 10, pp.269-293.
  19. Lee, S.M. and Abbott, P. A., 2003, "Bayesian networks for knowledge discovery in large datasets", Journal of Biomedical Informatics, Vol.36, pp.389-399. https://doi.org/10.1016/j.jbi.2003.09.022
  20. Lu P, and Rosenbaum MS, 2003, "Artificial Neural Networks and Grey Systems for the Prediction of Slope Stability", National Hazards Vol. 30, pp.383-398. https://doi.org/10.1023/B:NHAZ.0000007168.00673.27
  21. Mejia-Navarro M., Wohl EE.,1994, "Geological hazard and risk evaluation using GIS : methodology and model applied to Medellin", Bulletin of the Association of Engineering Geologists 31(4), pp.459-481.
  22. Netica-API, Norsys System Corp., http://www.norsys.com/
  23. Pearl, J .,1986, "Fusion, propagation and structuring in belief networks", Artificial Intelligence, Vol. 29, pp.241-288. https://doi.org/10.1016/0004-3702(86)90072-X
  24. Protege, Stanford Center for Biomedical informatics Research, http://protege.stanford.edu
  25. Jena, Hewlett-Packard Development Company, http://jena.sourceforge.net
  26. Stassopoulou, A., Petrou, M., Kittler, J., 1998, "Application of a Bayesian network in a GIS based decision making system", International Journal of Geographical Information Science 12 (1), pp.23-45. https://doi.org/10.1080/136588198241996
  27. Suzen, M.L. and Doyuran, V., 2003, "A comparison of the GIS based landslide susceptibility assessment methods: multivariate versus bivariate", Environmental Geology.
  28. Van Westen, C.J. ,1993, "Application of Geographic Information Systems to Landslide Hazard Zonation", Ph-D Dissertation Technical University Delft. ITC-Publication Number 15, ITC, Enschede, The Netherlands.
  29. Wallace, C. S., Korb, K., and Dai, H., 1996, "Causal discovery via mml", The 13th International Conference on Machine Learning, pp.516-524.