Journal of Central South University

, Volume 22, Issue 9, pp 3512–3520 | Cite as

Landslide hazards mapping using uncertain Naïve Bayesian classification method

  • Yi-min Mao (毛伊敏)
  • Mao-sheng Zhang (张茂省)Email author
  • Gen-long Wang (王根龙)
  • Ping-ping Sun (孙萍萍)


Landslide hazard mapping is a fundamental tool for disaster management activities in Loess terrains. Aiming at major issues with these landslide hazard assessment methods based on Naïve Bayesian classification technique, which is difficult in quantifying those uncertain triggering factors, the main purpose of this work is to evaluate the predictive power of landslide spatial models based on uncertain Naïve Bayesian classification method in Baota district of Yan’an city in Shaanxi province, China. Firstly, thematic maps representing various factors that are related to landslide activity were generated. Secondly, by using field data and GIS techniques, a landslide hazard map was performed. To improve the accuracy of the resulting landslide hazard map, the strategies were designed, which quantified the uncertain triggering factor to design landslide spatial models based on uncertain Naïve Bayesian classification method named NBU algorithm. The accuracies of the area under relative operating characteristics curves (AUC) in NBU and Naïve Bayesian algorithm are 87.29% and 82.47% respectively. Thus, NBU algorithm can be used efficiently for landslide hazard analysis and might be widely used for the prediction of various spatial events based on uncertain classification technique.


uncertain Bayesian model landslide hazard assessment 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    WANG Huai-bing, LIU Guo-jun, XU Wei-ya. GIS-based landslide hazard assessment: An overview [J]. Progress in Physical Geography, 2005, 29(4): 548–567.MathSciNetCrossRefGoogle Scholar
  2. [2]
    CARRARA A, CARDINALI M, DETTI R, GUZZETTI F. GIS techniques and statistical models in evaluating landslide hazard [J]. Earth Surface Processes and Landforms, 1991, 16(2): 427–445.CrossRefGoogle Scholar
  3. [3]
    DAI F C, LEE C F. Terrain-based mapping of landslide susceptibility using a geographical information system: A case study [J]. Canadian Geotechnical Journal, 2001, 38(5): 911–923.CrossRefGoogle Scholar
  4. [4]
    BISWAJEET P, LEE S. Utilization of optical remote sensing data and geographic information system tools for regional landslide hazard analysis by using binomial logistic regression model [J]. Application of Remote Sensing, 2008, 36(2): 1–11.Google Scholar
  5. [5]
    BISWAJEET P, LEE S. Landslide risk analysis using artificial neural network model focusing on different training sites [J]. Nature Phys Sci, 2009, 3(11): 1–15.Google Scholar
  6. [6]
    BISWAJEET P, LEE S. Delineation of landslide hazard areas on Penaang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network model [J]. Environmental Modelling & Software, 2010, 25(6): 747–759.CrossRefGoogle Scholar
  7. [7]
    BISWAJEET P, AHMED M. Manifestation of remote sensing data and GIS on landslide hazard analysis using spatial-based statistical models [J]. Arabian Journal of Geosciences, 2009, 46(10): 1–12.Google Scholar
  8. [8]
    BISWAJEET P. Remote sensing and GIS-based landslide hazard analysis and cross-validation using multivariate logistic regression model on three test areas in Malaysia [J]. Advances in Space Research, 2010, 45(10): 1244–1256.CrossRefGoogle Scholar
  9. [9]
    VIJITH H, MADHU G. Estimating potential landslide sites of an upland sub-watershed in Western Ghat’s of Kerala (India) through frequency ratio and GIS [J]. Environmental Geology, 2008, 55(7): 1397–1405.CrossRefGoogle Scholar
  10. [10]
    BISWAJEET P, LEE S. Utilization of optical remote sensing data and GIS tools for regional landslide hazard analysis bu using artificial neural network model [J]. Earth Science Frontier, 2007, 14(6): 143–152.CrossRefGoogle Scholar
  11. [11]
    MARJANOVIC M, KOVACEVIC M, BRANISLAV B. Landslide susceptibility assessment using SVM machine learning algorithm [J]. Engineering Geology, 2011, 123(3): 225–234.CrossRefGoogle Scholar
  12. [12]
    XU Chong, XU Xi-wei. Landslide hazard mapping using GIS and weight of evidence model in Qingshui river watershed of 2008 Wenchuan earthquake struck region [J]. Journal of Earth Science, 2012, 23(1): 97–120.CrossRefGoogle Scholar
  13. [13]
    SAITO H, NAKAYAMA D,MATSUYAMA H. Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: The Akaishi mountains, Japan [J]. Geomorphology, 2009, 109(3/4): 108–121.CrossRefGoogle Scholar
  14. [14]
    YEON Y K, HAN J G, KEUN H R. Landslide susceptibility mapping in Injae, Korea, using a decision tree [J]. Engineering Geology, 2010, 116: 274–283.CrossRefGoogle Scholar
  15. [15]
    BISWAJEET P. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS [J]. Computers & Geosciences, 2013, 51(2): 350–365.Google Scholar
  16. [16]
    AlESSANDRO M, MARCHESINI I. Bayesian framework for mapping and classifying shallow landslides exploiting remote sensing and topographic data [J]. Geomorphology, 2013, 183(7): 1–13.Google Scholar
  17. [17]
    VENKATESAN M, ARUNKUMAR T, PRABHAVATY P. An improved Bayesian classification data mining method for early warning landslide susceptibility model using GIS [J]. Advances in Intelligent Systems and Computing, 2013, 202(2): 277–288.CrossRefGoogle Scholar
  18. [18]
    ISWAR D, ALFRED S, NORMAN K. Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logistic regression models [J]. Geomorphology, 2012, 179(4): 116–125.Google Scholar
  19. [19]
    OZDEMIR A. Landslide susceptibility mapping using Bayesian approach in the Sultan Mountains (Aksehir, Turkey) [J]. Natural Hazards, 2011, 59(8): 1573–1607.MathSciNetCrossRefGoogle Scholar
  20. [20]
    REGAMEY A G, STRAUB D. Spatially explicit avalanche risk assessment linking Bayesian networks to a GIS [J]. Natural Hazards and Earth System Sciences, 2006, 6(5): 911–926.CrossRefGoogle Scholar
  21. [21]
    QIN Biao, XIA Yu-ni. A novel Bayesian classification for uncertain data [J]. Knowledge-Based Systems, 2011, 24: 1151–1158.CrossRefGoogle Scholar
  22. [22]
    ZHANG Mao-sheng, LIU Jie. Controlling factors of loess landslide in western China [J]. Environ Earth Sci, 2010, 59(7): 1671–1680.CrossRefGoogle Scholar
  23. [23]
    XU Chong, DAI Fu-chu. DIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China [J]. Geomorphology, 2012, 145–146(4): 70–80.CrossRefGoogle Scholar
  24. [24]
    BERNECKER T. Probabilistic frequent itemset mining in uncertain databases [C]// Proceeding of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Paris, 2009: 119–127.Google Scholar
  25. [25]
    DAHAL R K, HASEGAWA S, NONOUMRA A. Predictive modelling of rainfall-induced landslide hazard in the lesser Himalaya of Nepal based on weights-of-evidence [J]. Geomorphology, 2008, 102(3/4): 496–510.CrossRefGoogle Scholar
  26. [26]
    EDWIN L, HARP M E. Mapping of hazard from rainfall-triggered landslides in developing countries: Examples from Honduras and Micronesia [J]. Engineering Geology, 2009, 104(3/4): 295–311.CrossRefGoogle Scholar
  27. [27]
    ZHAO Hua, CHEN Jin-fei. Landslide hazard mapping using logistic regression model in Mackenzie Valley, Canada [J]. Natural Hazards, 2007, 42(4): 75–89.Google Scholar
  28. [28]
    SAMUELE S, GUGLIELMO M. landslide triggered by rainfall: A semi-automated procedure to define consistent intensity-duration thresholds [J]. Computers & Geosciences, 2014, 63(2): 123–131.Google Scholar
  29. [29]
    MATHEW J, RAWAT J V. Weights of evidence modelling for landslide hazard zonation mappingin part of Bhagirathi valley, Uttarakhand [J]. Current Science, 2009, 92(5): 628–638.Google Scholar
  30. [30]
    REGMI N R, GIARDINO J R, VITEK J D. Modeling susceptibility to landslides using the weight of evidence approach: Western Colorado, USA [J]. Geomorphology, 2010, 115(3/4): 172–187.Google Scholar
  31. [31]
    ROSSI M, GUZZETTI F, REICHENBACH P. Optimal landslide susceptibility zonation based on multiple forecasts [J]. Geomorphology, 2010, 114(4/5): 129–142.Google Scholar

Copyright information

© Central South University Press and Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Yi-min Mao (毛伊敏)
    • 1
    • 2
    • 3
  • Mao-sheng Zhang (张茂省)
    • 1
    Email author
  • Gen-long Wang (王根龙)
    • 1
  • Ping-ping Sun (孙萍萍)
    • 1
  1. 1.Key Laboratory for Geo-hazard in Loess AreaMinistry of Land and Resources (MLR)Xi’anChina
  2. 2.School of Geology Engineering and GeomaticsChang’an UniversityXi’anChina
  3. 3.Applied Science InstituteJiangxi University of Science and TechnologyGanzhouChina

Personalised recommendations