산사태 분포 예측을 위한 로지스틱, 베이지안, Maxent의 비교
Comparison of Logistic, Bayesian, and Maxent Models for Prediction of Landslide Distribution
2
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
Quantitative forecasting methods based on spatial data and geographic information system have been used in predicting the landslide location. This study compared the simulated results of logistic, Bayesian, and maximum entropy models to understand the uncertainties of each model and identify the main factors that influence landslide. The study area is Boeun gun where 388 landslides occurred in the year of 1998. The verification results showed that the AUC of the three models was 0.84. However, the landslide susceptibility distribution of Maxent model was different from those of the other two models. With the same landslide occurrence data, the result of high susceptible area in Maxent model is smaller than Logistic or Bayesian. Maxent model, however, proved to be more efficient in predicting landslide than the other two models. In Maxent’s simulations, the responsible factors for landslide susceptibility are timber age class, land cover, timber diameter, crown closure, and soil drainage. The results suggest that it is necessary to consider the possibility of overestimation when using Logistic or Bayesian model, and forest management around the study area can be an effective way to minimize landslide possibility.
Abstract
Quantitative forecasting methods based on spatial data and geographic information system have been used in predicting the landslide location. This study compared the simulated results of logistic, Bayesian, and maximum entropy models to understand the uncertainties of each model and identify the main factors that influence landslide. The study area is Boeun gun where 388 landslides occurred in the year of 1998. The verification results showed that the AUC of the three models was 0.84. However, the landslide susceptibility distribution of Maxent model was different from those of the other two models. With the same landslide occurrence data, the result of high susceptible area in Maxent model is smaller than Logistic or Bayesian. Maxent model, however, proved to be more efficient in predicting landslide than the other two models. In Maxent’s simulations, the responsible factors for landslide susceptibility are timber age class, land cover, timber diameter, crown closure, and soil drainage. The results suggest that it is necessary to consider the possibility of overestimation when using Logistic or Bayesian model, and forest management around the study area can be an effective way to minimize landslide possibility.
참고문헌 (29)
- Akgun, A., "A comparison of landslide susceptibility maps produced by logistic regression, multi criteria decision, and likelihood ratio methods, a case study at Izmir, Turkey", Landslide, 9, pp.93~106 (2012)
- Al-Mamun, "Landslide susceptibility mapping using Logistic Regression and Fuzzy Set model at the Boeun Area, Korea", 한국지형학회지, 23(2), pp.109~125 (2016), 한국지형학회[DOI]
- Convertino, M., "Detecting fingerprints of landslide drivers: A MaxEnt model", Journal of Geography Research, 118(3), pp.1367~1386 (2013)
- "Center for Research on the Epidemiology of Disasters (CREM)", CRED, ~ (2009)
- Davis, J., "A hybrid physical and maximun-entropy landslide susceptibility model", Entropy, 17(6), pp.4271~4292 (2015)
- Elith, J., "Novel methods improve prediction of species’ distributions from occurrence data", Ecography, 29(2), pp.129~151 (2006)
- Felicisimo, A. M., "Mapping landslide susceptibility with logistic regression, multiple adaptive regression splines, classification and regression trees, and maximum entropy methods: a comparative study", Landslides, 10(2), pp.175~189 (2013)
- Franklin, J., "Mapping species distributions spatial inference and prediction" (2009), Cambridge University Press
- Hanley, J.A., "The Meaning and Use of the Area under a Receiver Operating Characteristic (ROC) Curve", Radiology, 143(1), pp.29~36 (1982)
- Sara Khodadad, "Assessment of Landslide Susceptibility Using GIS-Based Models in Jinbu Area", 한국지형학회지, 23(4), pp.153~167 (2016), 한국지형학회[DOI]
- 김호걸, "MaxEnt 모형을 이용한 기후변화에 따른 산사태 발생가능성 예측", 환경영향평가, 22(1), pp.39~50 (2013), 한국환경영향평가학회
- 김경민, "1:25,000 수치임상도 제작체계 표준화 연구", 한국지리정보학회지, 12(3), pp.143~151 (2009), 한국지리정보학회
- 권혁수, "종분포모형의 불확실성 확인을 위한 앙상블모형 적용", 한국지형공간정보학회지, 22(4), pp.47~52 (2014), 한국지형공간정보학회[DOI]
- Lee, S., "Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data", International Journal of Remote Sensing, 26, pp.1477~1491 (2005)
- Lee, S., "Probabilistic Landslide Hazard Mapping Using GIS and Remote Sensing Data at Boun, Korea", International Journal of Remote Sensing, 25(11), pp.37~41 (2004)
- Lee, S., "Utilization of optical remote sensing data and GIS tools for regional landslide hazard analysis by using an artificial neural network model at Selangor, Malaysia", Earth Science, 14(6), pp.143~151 (2007)
- Lombardo, L., "Presence-only approach to assess landslide triggering-thickness susceptibility: a test for the Mili catchmate, Italy", Natural Hazards, 84(1), pp.565~588 (2016)
- Nefeslioglu, H.A., "Assessment of landslide susceptibility by decision trees in the metropolitan area of Istanbul, Turkey", Math Problems in Engineering (2010)[DOI]
- O’Banion, M.S., "Predictive seismically induced landslide hazard mapping in origon using a maximum entropy model", Tenth U.S. National Conference on Earthquake Engineering (2014)
- Park, S., "Landslide susceptibility mapping using frequency ratio, analytic hierarchy process, logistic regression, and artificial neural network methods at the InJe area, Korea", Environmental Earth Sciences, 68(5), pp.1443~1464 (2013)
- Petley, D. N., "Environmental Hazards: Assessing Risk and Reducing Disaster" (2009), Routledge
- Phillips, S. J., "A maximum entropy approach to species distribution modeling", Proceedings of the Twenty- First International Conference on Machine Learning, pp.655~662 (2004)
- Pradhan, B., "Utilization of optical remote sensing data and GIS tools for regional landslide hazard analysis by using an artificial neural network model at Selangor, Malaysia", Earth Science Front, 14(6), pp.143~152 (2008)
- Pradhan, B., "A GIS-based back-propagation neural network model and its cross-application and validation for landslide susceptibility analyses", Computer Environment Urban System, 34, pp.216~235 (2010)
- Remondo, J., "Validation of landslide susceptibility maps: examples and applications from a case study in Northern Spain", Natural Hazards, 30, pp.437~449 (2003)
- 서창완, "위치자료의 종류에 따른 생물종 분포모형 비교 연구", 한국지형공간정보학회지, 16(4), pp.59~64 (2008), 한국지형공간정보학회
- Shahabi, H., "Landslide Susceptibility Mapping at Central Zab Basin, Iran: A Comparison between Analytical Hierarchy Process, Frequency Ratio and Logistic Regression Models", CATENA, 115, pp.55~70 (2014)
- Swets, J. A., "Measures of the accuracy of diagnostic systems", Science, 240, pp.1285~1293 (1988)
- "Maxent software for modeling species niches and distributions (Version 3.4.0)" (2017)[URL]