Geological and Environmental Engineering | Article | Published 2019

Comparative analysis of statistical methods for landslide susceptibility mapping in the Bostanlik District, Uzbekistan

Keywords: Landslide Inventory Statistical index Frequency ratio Certainty factor Evaluation


The Bostanlik district, Uzbekistan, is characterized bymountainous terrain susceptible to landslides. The present study aims at creating a statistically derived landslide susceptibility map – the first of its type for Uzbekistan - for part of the area in order to inform risk management. Statistical index (SI), frequency ratio (FR) and certainty factor (CF) are employed and compared for this purpose. Ten predictor layers are used for the analysis, including geology, soil, land use and land cover, slope, aspect, elevation, distance to lineaments, distance to faults, distance to roads, and distance to streams. 170 landslide polygons are mapped based on GeoEye-1 and Google Earth imagery. 119 (70%) out of them are randomly selected and used for the training of the methods, whereas 51 (30%) are retained for the evaluation of the results. The three landslide susceptibility maps are split into five classes, i.e. very low, low, moderate, high, and very high. The evaluation of the results obtained builds on the area under the success rate and prediction rate curves (AUC). The training accuracies are 82.1%, 74.3% and 74%,while the prediction accuracies are 80%, 70% and 71%, for the SI, FR and CF methods, respectively. The spatial relationships between the landslides and the predictor layers confirmed the results of previous studies conducted in other areas, whereas model performance was slightly higher than in some earlier studies – possibly a benefit of the polygon based landslide inventory.


  1. Akbari, A., Yahaya, F.B.M., Azamirad, M., Fanodi, M., 2014. Landslide susceptibility mapping
  2. using logistic regression analysis and GIS tools. Electron. J. Geotech. Eng. 19, 1687–1696.
  3. Akgun, A., 2012. A comparison of landslide susceptibility maps produced by logistic regression,
  4. multi-criteria decision, and likelihood ratio methods: a case study at
  5. İzmir, Turkey. Landslides 9, 93–106.
  6. Althuwaynee, O.F., Pradhan, B., Lee, S., 2012. Application of an evidential belief function
  7. model in landslide susceptibility mapping. Comput. Geosci. 44, 120–135. https://
  9. Basharat, M., Shah, H.R., Hameed, N., 2016. Landslide susceptibility mapping using GIS
  10. and weighted overlay method: a case study from NW Himalayas, Pakistan. Arab.
  11. J. Geosci. 9.
  12. Belolipov, I.V., Zaurov, D.E., Eisenman, S.W., 2013. The geography, climate and vegetation
  13. of Uzbekistan. In: Eisenman, S.W., Zaurov, D.E., Struwe, L. (Eds.), Medicinal Plants of
  14. Central Asia: Uzbekistan and Kyrgyzstan. Springer New York, New York, NY,
  15. pp. 5–7 (ISBN 978-1-4614-3911-0).
  16. Bilaşco, Ş., Horvath, C., Roşian, G., Sorin, F., Keller, I.E., 2011. Statisticalmodel using GIS for
  17. the assessment of landslide susceptibility. Case-study: the Someş plateau. Romanian
  18. J. Geogr. Ed. Acad. Rom. Bucur.
  19. Catani, F., Lagomarsino, D., Segoni, S., Tofani, V., 2013. Landslide susceptibility estimation
  20. by random forests technique: sensitivity and scaling issues. Nat. Hazards Earth Syst.
  21. Sci. 13, 2815–2831.
  22. Central Asia and Caucasus Disaster Risk Management Initiative (CAC DRMI), 2009. Risk
  23. Assessment for Central Asia and Caucasus Desk Study Review.
  24. Chen, W., Chai, H., Sun, X., Wang, Q., Ding, X., Hong, H., 2016. A GIS-based comparative
  25. study of frequency ratio, statistical index and weights-of-evidence models in landslide
  26. susceptibility mapping. Arab. J. Geosci. 9.
  27. 2150-7.
  28. Chen, W., Peng, J., Hong, H., Shahabi, H., Pradhan, B., Liu, J., Zhu, A.-X., Pei, X., Duan, Z.,
  29. 2018. Landslide susceptibility modelling using GIS-based machine learning techniques
  30. for Chongren County, Jiangxi Province, China. Sci. Total Environ. 626,
  31. 1121–1135.
  32. Constantin,M., Bednarik, M., Jurchescu,M.C., Vlaicu, M., 2011. Landslide susceptibility assessment
  33. using the bivariate statistical analysis and the index of entropy in the
  34. Sibiciu Basin (Romania). Environ. Earth Sci. 63, 397–406.
  35. s12665-010-0724-y.
  36. Cui, K., Lu, D., Li, W., 2017. Comparison of landslide susceptibility mapping based on statistical
  37. index, certainty factors, weights of evidence and evidential belief function
  38. models. Geocarto Int. 32, 935–955.
  39. Devkota, K.C., Regmi, A.D., Pourghasemi, H.R., Yoshida, K., Pradhan, B., Ryu, I.C., Dhital,
  40. M.R., Althuwaynee, O.F., 2013. Landslide susceptibility mapping using certainty factor,
  41. index of entropy and logistic regression models in GIS and their comparison at
  42. Mugling–Narayanghat road section in Nepal Himalaya. Nat. Hazards 65, 135–165.
  44. Dou, J., Chang, K.-T., Chen, S., Yunus, A., Liu, J.-K., Xia, H., Zhu, Z., 2015a. Automatic casebased
  45. reasoning approach for landslide detection: integration of object-oriented
  46. image analysis and a genetic algorithm. Remote Sens. 7, 4318–4342. https://doi.
  47. org/10.3390/rs70404318.
  48. Dou, J., Tien Bui, D., Yunus, A., Jia, K., Song, X., Revhaug, I., Xia, H., Zhu, Z., 2015b. Optimization
  49. of causative factors for landslide susceptibility evaluation using remote sensing
  50. and GIS data in parts of Niigata, Japan. PLoS ONE 10, e0133262.
  51. 10.1371/journal.pone.0133262.
  52. Ercanoglu, M., Gokceoglu, C., Van Asch, T.W., 2004. Landslide susceptibility zoning north
  53. of Yenice (NW Turkey) by multivariate statistical techniques. Nat. Hazards 32, 1–23.
  54. Fan,W.,Wei, X., Cao, Y., Zheng, B., 2017. Landslide susceptibility assessment using the certainty
  55. factor and analytic hierarchy process. J. Mt. Sci. 14, 906–925.
  56. 10.1007/s11629-016-4068-2.
  57. Golovko, D., Roessner, S., Behling, R., Wetzel, H.-U., Kleinschmit, B., 2017. Evaluation of
  58. remote-sensing-based landslide inventories for hazard assessment in Southern
  59. Kyrgyzstan. Remote Sens. 9, 943.
  60. Gutiérrez, F., Linares, R., Roqué, C., Zarroca, M., Carbonel, D., Rosell, J., Gutiérrez, M., 2015.
  61. Large landslides associated with a diapiric fold in Canelles Reservoir (Spanish Pyrenees):
  62. detailed geological–geomorphologicalmapping, trenching and electrical resistivity
  63. imaging. Geomorphology 241, 224–242.
  64. geomorph.2015.04.016.
  65. Guzzetti, F., Carrara, A., Cardinali, M., Reichenbach, P., 1999. Landslide hazard evaluation: a review
  66. of current techniques and their application in a multi-scale study, Central Italy. Geomorphology
  67. 31, 181–216.
  68. Guzzetti, F., Reichenbach, P., Ardizzone, F., Cardinali, M., Galli, M., 2006. Estimating the
  69. quality of landslide susceptibility models. Geomorphology 81, 166–184. https://doi.
  70. org/10.1016/j.geomorph.2006.04.007.
  71. Hong, H., Chen, W., Xu, C., Youssef, A.M., Pradhan, B., Tien Bui, D., 2016. Rainfall-induced
  72. landslide susceptibility assessment at the Chongren area (China) using frequency
  73. ratio, certainty factor, and index of entropy. Geocarto Int., 1–16
  74. 10.1080/10106049.2015.1130086.Hong, H., Liu, J., Zhu, A.-X., Shahabi, H., Pham, B.T., Chen,W., Pradhan, B., Bui, D.T., 2017. A
  75. novel hybrid integration model using support vectormachines and random subspace
  76. for weather-triggered landslide susceptibility assessment in the Wuning area
  77. (China). Environ. Earth Sci. 76.
  78. Hong, H., Liu, J., Bui, D.T., Pradhan, B., Acharya, T.D., Pham, B.T., Zhu, A.-X., Chen, W.,
  79. Ahmad, B.B., 2018. Landslide susceptibility mapping using J48 Decision Tree with
  80. AdaBoost, Bagging and Rotation Forest ensembles in the Guangchang area (China).
  81. Catena 163, 399–413.
  82. Hussin, H.Y., Zumpano, V., Reichenbach, P., Sterlacchini, S., Micu, M., van Westen, C.,
  83. Bălteanu, D., 2016. Different landslide sampling strategies in a grid-based bi-variate
  84. statistical susceptibility model. Geomorphology 253, 508–523.
  85. 10.1016/j.geomorph.2015.10.030.
  86. Ilia, I., Tsangaratos, P., 2016. Applying weight of evidence method and sensitivity analysis
  87. to produce a landslide susceptibility map. Landslides 13, 379–397.
  88. 10.1007/s10346-015-0576-3.
  89. Juliev, M., Pulatov, A., Hubl, J., 2017. Natural hazards in mountain regions of Uzbekistan: a
  90. review of mass movement processes in Tashkent province. Int. J. Sci. Eng. Res. 8,
  91. 1102–1108.
  92. Lan, H.X., Zhou, C.H., Wang, L.J., Zhang, H.Y., Li, R.H., 2004. Landslide hazard spatial analysis
  93. and prediction using GIS in the Xiaojiang watershed, Yunnan, China. Eng. Geol.
  94. 76, 109–128.
  95. Lee, S., Pradhan, B., 2007. Landslide hazard mapping at Selangor, Malaysia using frequency
  96. ratio and logistic regression models. Landslides 4, 33–41.
  97. 10.1007/s10346-006-0047-y.
  98. Manzo, G., Tofani, V., Segoni, S., Battistini, A., Catani, F., 2013. GIS techniques for regionalscale
  99. landslide susceptibility assessment: the Sicily (Italy) case study. Int. J. Geogr. Inf.
  100. Sci. 27, 1433–1452.
  101. Meinhardt, M., Fink, M., Tünschel, H., 2015. Landslide susceptibility analysis in central
  102. Vietnam based on an incomplete landslide inventory: comparison of a new method
  103. to calculate weighting factors by means of bivariate statistics. Geomorphology 234,
  104. 80–97.
  105. Meten, M., PrakashBhandary, N., Yatabe, R., 2015. Effect of landslide factor combinations
  106. on the prediction accuracy of landslide susceptibility maps in the Blue Nile Gorge
  107. of Central Ethiopia. Geoenviron. Disasters 2.
  108. 0016-7.
  109. Mohammady, M., Pourghasemi, H.R., Pradhan, B., 2012. Landslide susceptibility mapping
  110. at Golestan Province, Iran: a comparison between frequency ratio, Dempster–Shafer,
  111. and weights-of-evidence models. J. Asian Earth Sci. 61, 221–236.
  112. 10.1016/j.jseaes.2012.10.005.
  113. Niyazov, R., Nurtaev, B., 2013. Modern seismogenic landslides caused by the Pamir-Hindu
  114. Kush earthquakes and their consequences in central Asia. In: Margottini, C., Canuti, P.,
  115. Sassa, K. (Eds.), Landslide Science and Practice: Volume 5: Complex Environment.
  116. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 343–348 (ISBN 978-3-642-
  117. 31427-8).
  118. Nourani, V., Pradhan, B., Ghaffari, H., Sharifi, S.S., 2014. Landslide susceptibilitymapping at
  119. Zonouz Plain, Iran using genetic programming and comparison with frequency ratio,
  120. logistic regression, and artificial neural network models. Nat. Hazards 71, 523–547.
  122. Ozdemir, A., Altural, T., 2013. A comparative study of frequency ratio, weights of evidence
  123. and logistic regression methods for landslide susceptibility mapping: Sultan Mountains,
  124. SW Turkey. J. Asian Earth Sci. 64, 180–197.
  125. jseaes.2012.12.014.
  126. Park, S., Choi, C., Kim, B., Kim, J., 2013. Landslide susceptibility mapping using frequency
  127. ratio, analytic hierarchy process, logistic regression, and artificial neural network
  128. methods at the Inje area, Korea. Environ. Earth Sci. 68, 1443–1464.
  129. 10.1007/s12665-012-1842-5.
  130. Pourghasemi, H.R., Pradhan, B., Gokceoglu, C., 2012. Application of fuzzy logic and analytical
  131. hierarchy process (AHP) to landslide susceptibility mapping at Haraz watershed,
  132. Iran. Nat. Hazards 63, 965–996.
  133. Pourghasemi, H.R., Pradhan, B., Gokceoglu, C., Mohammadi,M., Moradi, H.R., 2013. Application
  134. of weights-of-evidence and certainty factor models and their comparison in
  135. landslide susceptibility mapping at Haraz watershed, Iran. Arab. J. Geosci. 6,
  136. 2351–2365.
  137. Pourghasemi, H.R., Teimoori Yansari, Z., Panagos, P., Pradhan, B., 2018. Analysis and evaluation
  138. of landslide susceptibility: a review on articles published during 2005–2016
  139. (periods of 2005–2012 and 2013–2016). Arab. J. Geosci., 11
  140. 10.1007/s12517-018-3531-5.
  141. Regmi, A.D., Devkota, K.C., Yoshida, K., Pradhan, B., Pourghasemi, H.R., Kumamoto, T.,
  142. Akgun, A., 2014. Application of frequency ratio, statistical index, and weights-ofevidence
  143. models and their comparison in landslide susceptibility mapping in Central
  144. Nepal Himalaya. Arab. J. Geosci. 7, 725–742.
  145. 0807-z.
  146. Saponaro, A., Pilz, M., Bindi, D., Parolai, S., 2015a. The contribution of EMCA to landslide
  147. susceptibility mapping in Central Asia. Ann. Geophys. 58.
  148. Saponaro, A., Pilz, M., Wieland, M., Bindi, D., Moldobekov, B., Parolai, S., 2015b. Landslide
  149. susceptibility analysis in data-scarce regions: the case of Kyrgyzstan. Bull. Eng. Geol.
  150. Environ. 74, 1117–1136.
  151. Sara, F., Silvia, B., Sandro, M., 2015. Landslide inventory updating by means of Persistent
  152. Scatterer Interferometry (PSI): the Setta basin (Italy) case study. Geomat. Nat. Haz.
  153. Risk 6, 419–438.
  154. Sarkar, S., Kanungo, D.P., 2004. An integrated approach for landslide susceptibility mapping
  155. using remote sensing and GIS. Photogramm. Eng. Remote. Sens. 70, 617–625.
  156. Sato, H.P., Harp, E.L., 2009. Interpretation of earthquake-induced landslides triggered by
  157. the 12 May 2008, M7.9 Wenchuan earthquake in the Beichuan area, Sichuan Province,
  158. China using satellite imagery and Google Earth. Landslides 6, 153–159.
  160. Shahabi, H., Hashim, M., 2015. Landslide susceptibility mapping using GIS-based statistical
  161. models and remote sensing data in tropical environment. Sci. Rep. 5. https://doi.
  162. org/10.1038/srep09899.
  163. Steger, S., Brenning, A., Bell, R., Glade, T., 2016. The propagation of inventory-based positional
  164. errors into statistical landslide susceptibility models. Nat. Hazards Earth Syst.
  165. Sci. 16 (12), 2729–2745.
  166. Steger, S., Brenning, A., Bell, R., Glade, T., 2017. The influence of systematically incomplete
  167. shallow landslide inventories on statistical susceptibility models and suggestions for
  168. improvements. Landslides 14, 1767–1781.
  169. 0820-0.
  170. Teerarungsigul, S., Torizin, J., Fuchs, M., Kühn, F., Chonglakmani, C., 2016. An integrative
  171. approach for regional landslide susceptibility assessment using weight of evidence
  172. method: a case study of Yom River Basin, Phrae Province, Northern Thailand. Landslides
  173. 13, 1151–1165.
  174. Tien Bui, D., Pradhan, B., Lofman, O., Revhaug, I., Dick, Ø.B., 2013. Regional prediction of
  175. landslide hazard using probability analysis of intense rainfall in the Hoa Binh province,
  176. Vietnam. Nat. Hazards 66, 707–730.
  177. 0510-0.
  178. Tien Bui, D., Tuan, T.A., Klempe, H., Pradhan, B., Revhaug, I., 2016. Spatial prediction models for
  179. shallow landslide hazards: a comparative assessment of the efficacy of support vectormachines,
  180. artificial neural networks, kernel logistic regression, and logistic model tree. Landslides
  181. 13, 361–378.
  182. Vakhshoori, V., Zare, M., 2016. Landslide susceptibility mapping by comparing weight of
  183. evidence, fuzzy logic, and frequency ratio methods. Geomat. Nat. Haz. Risk 7,
  184. 1731–1752.
  185. Van Westen, C.J., 2002. Use of Weights of Evidence Modeling for Landslide Susceptibility
  186. Mapping. Int. Inst. Geoinformation Sci. Earth Obs, Enschede Neth.
  187. VanWesten, C.J., Rengers, N., Terlien, M.T.J., Soeters, R., 1997. Prediction of the occurrence
  188. of slope instability phenomenal through GIS-based hazard zonation. Geol. Rundsch.
  189. 86, 404–414.
  190. Van Westen, C.J., Castellanos, E., Kuriakose, S.L., 2008. Spatial data for landslide susceptibility,
  191. hazard, and vulnerability assessment: an overview. Eng. Geol. 102, 112–131.
  193. Wang, Q., Li,W., Chen, W., Bai, H., 2015. GIS-based assessment of landslide susceptibility
  194. using certainty factor and index of entropy models for the Qianyang County of Baoji
  195. city, China. J. Earth Syst. Sci. 124, 1399–1415.
  196. Wu, Y., Li,W.,Wang, Q., Liu, Q., Yang, D., Xing, M., Pei, Y., Yan, S., 2016. Landslide susceptibility
  197. assessment using frequency ratio, statistical index and certainty factor models
  198. for the Gangu County, China. Arab. J. Geosci. 9.
  199. 2112-0.
  200. Zare,M., Pourghasemi, H.R., Vafakhah, M., Pradhan, B., 2013. Landslide susceptibility mapping
  201. at VazWatershed (Iran) using an artificial neural networkmodel: a comparison
  202. between multilayer perceptron (MLP) and radial basic function (RBF) algorithms.
  203. Arab. J. Geosci. 6, 2873–2888.
  204. Zêzere, J.L., Pereira, S., Melo, R., Oliveira, S.C., Garcia, R.A.C., 2017. Mapping landslide susceptibility
  205. using data-driven methods. Sci. Total Environ. 589, 250–267.
  206. Zhao, C., Chen, W., Wang, Q., Wu, Y., Yang, B., 2015. A comparative study of statistical
  207. index and certainty factor models in landslide susceptibility mapping: a case study
  208. for the Shangzhou District, Shaanxi Province, China. Arab. J. Geosci. 8, 9079–9088.
















Like and share on

Cite this publication

Copy text below and use in your article