{"references": ["EM-DAT, The OFDA/CRED International Disaster Database. 2008,\nUniversit'e Catholique de Louvain - Brussels - Belgium.", "Guzzetti, F., P. Reichenbach, F. Ardizzone, M. Cardinali, and M. Galli,\n\"Estimating the quality of landslide susceptibility models,\"\nGeomorphology. vol 1-2: pp. 166-184, 2006.", "Carrara, A., \"Multivariate models for landslide hazard evaluation,\"\nMathematical Geology. vol 3: pp. 403-426, 1983.", "Carrara, A., M. Cardinali, R. Detti, F. Guzzetti, V. Pasqui, and P.\nReichenbach, \"Gis Techniques and Statistical-Models in Evaluating\nLandslide Hazard,\" Earth Surface Processes and Landforms. vol 5: pp.\n427-445, 1991.", "Reger, J.P., \"Discriminant-Analysis as a Possible Tool in Landslide\nInvestigations,\" Earth Surface Processes and Landforms. vol 3: pp.\n267-273, 1979.", "Dai, F.C. and C.F. Lee, \"Landslide characteristics and slope instability\nmodeling using GIS, Lantau Island, Hong Kong,\" Geomorphology. vol\n3-4: pp. 213-228, 2002.", "Lee, S., \"Application of logistic regression model and its validation for\nlandslide susceptibility mapping using GIS and remote sensing data,\"\nInternational Journal of Remote Sensing. vol 7: pp. 1477-1491, 2005.", "van Den Eeckhaut, M., T. Vanwalleghem, J. Poesen, G. Govers, G.\nVerstraeten, and L. Vandekerckhove, \"Prediction of landslide\nsusceptibility using rare events logistic regression: A case-study in the\nFlemish Ardennes (Belgium),\" Geomorphology. vol 3-4: pp. 392-410,\n2006.", "Yesilnacar, E. and T. Topal, \"Landslide susceptibility mapping: A\ncomparison of logistic regression and neural networks methods in a\nmedium scale study, Hendek region (Turkey),\" Engineering Geology. vol\n3-4: pp. 251-266, 2005.\n[10] Chang, K.T., S.H. Chiang, and M.L. Hsu, \"Modeling typhoon-and\nearthquake-induced landslides in a mountainous watershed using logistic\nregression,\" Geomorphology. vol 3-4: pp. 335-347, 2007.\n[11] Melchiorre, C., M. Matteucci, A. Azzoni, and A. Zanchi, \"Artificial\nneural networks and cluster analysis in landslide susceptibility zonation,\"\nGeomorphology. vol 3-4: pp. 379-400, 2008.\n[12] Ermini, L., F. Catani, and N. Casagli, \"Artificial Neural Networks applied\nto landslide susceptibility assessment,\" Geomorphology. vol 1-4: pp.\n327-343, 2005.\n[13] van Asch, T.W.J., J.P. Malet, L.P.H. van Beek, and D. Amitrano,\n\"Techniques, advances, problems and issues in numerical modelling of\nlandslide hazard,\" Bulletin de la Societe Geologique de France. vol 2: pp.\n65-88, 2007.\n[14] van Westen, C.J., A.C. Seijmonsbergen, and F. Mantovani, \"Comparing\nLandslide Hazard Maps,\" Natural Hazards. vol 2: pp. 137-158, 1999.\n[15] Lee, S., J.H. Ryu, M.J. Lee, and J.S. Won, \"The Application of Artificial\nNeural Networks to Landslide Susceptibility Mapping at Janghung,\nKorea,\" Mathematical Geology. vol 2: pp. 199-220, 2006.\n[16] Neaupane, K.M. and S.H. Achet, \"Use of backpropagation neural network\nfor landslide monitoring: a case study in the higher Himalaya,\"\nEngineering Geology. vol 3-4: pp. 213-226, 2004.\n[17] Paliwal, M. and U. Kumar, \"Neural networks and statistical techniques: A\nreview of applications,\" Expert Syst Appl. vol 1: pp. 2-17, 2009.\n[18] Brieman, L., J.H. Friedman, R.A. Olshen, and C.J. Stone, \"Classification\nand Regression Trees,\" Wadsworth Inc. vol, 1984.\n[19] Camp, N.J. and M.L. Slattery, \"Classification tree analysis: a statistical\ntool to investigate risk factor interactions with an example for colon\ncancer (United States),\" Cancer Cause Control. vol 9: pp. 813-823, 2002.\n[20] De'ath, G. and K.E. Fabricius, \"Classification and Regression Trees: A\nPowerful Yet Simple Technique for Ecological Data Analysis,\" Ecology.\nvol 11: pp. 3178-3192, 2000.\n[21] Pal, M. and P.M. Mather, \"An assessment of the effectiveness of decision\ntree methods for land cover classification,\" Remote Sens Environ. vol 4:\npp. 554-565, 2003.\n[22] Friedl, M.A. and C.E. Brodley, \"Decision tree classification of land cover\nfrom remotely sensed data,\" Remote Sens Environ. vol 3: pp. 399-409,\n1997.\n[23] Scull, P., J. Franklin, and O.A. Chadwick, \"The application of\nclassification tree analysis to soil type prediction in a desert landscape,\"\nEcological Modelling. vol 1: pp. 1-15, 2005.\n[24] Lagacherie, P. and S. Holmes, \"Addressing geographical data errors in a\nclassification tree for soil unit prediction,\" International Journal of\nGeographical Information Science. vol 2: pp. 183-198, 1997.\n[25] Wu, J., et al., \"Exploratory spatial data analysis for the identification of\nrisk factors to birth defects,\" BMC Public Health. vol 1: pp. 23, 2004.\n[26] Getis, A. and J. Ord, \"The analysis of spatial association by use of\ndistance statistics,\" Geographical analysis. vol 3: pp. 189-206, 1992.\n[27] Ord, J. and A. Getis, \"Local spatial autocorrelation statistics:\ndistributional issues and an application,\" Geographical analysis. vol 4: pp.\n286-306, 1995."]}

Landslide susceptibility map delineates the potential zones for landslide occurrence. Previous works have applied multivariate methods and neural networks for mapping landslide susceptibility. This study proposed a new approach to integrate decision tree model and spatial cluster statistic for assessing landslide susceptibility spatially. A total of 2057 landslide cells were digitized for developing the landslide decision tree model. The relationships of landslides and instability factors were explicitly represented by using tree graphs in the model. The local Getis-Ord statistics were used to cluster cells with high landslide probability. The analytic result from the local Getis-Ord statistics was classed to create a map of landslide susceptibility zones. The map was validated using new landslide data with 482 cells. Results of validation show an accuracy rate of 86.1% in predicting new landslide occurrence. This indicates that the proposed approach is useful for improving landslide susceptibility mapping.