Landslide Risk Assessment in Darjeeling Hills Using Multi-criteria Decision Support System: A Bayesian Network Approach

Landslide is one of the most recurrent and hazardous events of hilly slopes all over the world and particularly in the hilly regions of Himalayas. Darjeeling district of northern West Bengal, being the most important hill station in terms of tourism and trance-boundary strategic location, experiences landslide very often which causes intermittent loss of tourism revenues and is a problem for national security. In order to assess the landslide risk and accordingly prepare a landslide-risk zonation for the Darjeeling district, factors like slope, drainage density, rainfall soil depth, land use/land cover and geology have been considered. The factors responsible for landslide and their interdependency have been critically evaluated. In the present study, Bayesian network model has been implemented which is a probabilistic statistical graphical model that represents a set of variables and their conditional dependencies. Bayesian network was applied to assess the influences of the factors, and accordingly weightage and ranking of the contributing factors for landslide have been calculated. Finally, using multi-criteria decision support system (MCDSS) in GIS environment, landslide-risk zonation of the Darjeeling district has been prepared. Validation has been done taking into account 25 historical landslide locations, and more than 92% accuracy has been achieved. Rangli Rangliot is the most landslide-susceptible block of Darjeeling district. Kalimpong I, Kalimpong II, Mirik, Jorebunglow Sukhiapokhri and Bijanbari also come under the ambit of the highly susceptible areas.

[1]  C. Gokceoğlu,et al.  Use of fuzzy relations to produce landslide susceptibility map of a landslide prone area (West Black Sea Region, Turkey) , 2004 .

[2]  V. Ferrara,et al.  Landslide hazard in the Nebrodi Mountains (Northeastern Sicily) , 2005 .

[3]  R. Yulita Molliq.  Solutions of Fractional Zakharov-Kuznetsov Equations By FCT method; This paper has been withdrawn , 2012 .

[4]  Biswajeet Pradhan,et al.  Manifestation of an adaptive neuro-fuzzy model on landslide susceptibility mapping: Klang valley, Malaysia , 2011, Expert Syst. Appl..

[5]  P. Aleotti,et al.  Landslide hazard assessment: summary review and new perspectives , 1999 .

[6]  S. Moreiras,et al.  Landslide susceptibility zonation in the Rio Mendoza Valley, Argentina , 2005 .

[7]  D. P. Kanungo,et al.  An Integrated Approach for Landslide Susceptibility Mapping Using Remote Sensing and GIS , 2004 .

[8]  Max Henrion,et al.  Some Practical Issues in Constructing Belief Networks , 1987, UAI.

[9]  Shraban Sarkar,et al.  Landslide susceptibility assessment using Information Value Method in parts of the Darjeeling Himalayas , 2013, Journal of the Geological Society of India.

[10]  Judea Pearl,et al.  Bayesian Networks , 1998, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[11]  K. Upton,et al.  A modern approach , 1995 .

[12]  Robert P. Goldman,et al.  A Language for Construction of Belief Networks , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  H. A. Nefeslioglu,et al.  Assessment of Landslide Susceptibility by Decision Trees in the Metropolitan Area of Istanbul, Turkey , 2010 .

[14]  Saro Lee,et al.  Combining landslide susceptibility maps obtained from frequency ratio, logistic regression, and artificial neural network models using ASTER images and GIS , 2012 .

[15]  S. L. Kuriakose,et al.  Spatial data for landslide susceptibility, hazard, and vulnerability assessment: An overview , 2008 .

[16]  Murat Ercanoglu,et al.  Application of logistic regression and fuzzy operators to landslide susceptibility assessment in Azdavay (Kastamonu, Turkey) , 2011 .

[17]  Florimond De Smedt,et al.  Evaluation of the consistency of landslide susceptibility mapping: a case study from the Kankai watershed in east Nepal , 2013, Landslides.

[18]  Manoj K. Arora,et al.  Landslide risk assessment using concepts of danger pixels and fuzzy set theory in Darjeeling Himalayas , 2008 .

[19]  L. Starkel,et al.  Extreme rainfalls in Eastern Himalaya and southern slope of Meghalaya Plateau and their geomorphologic impacts , 2007 .

[20]  Manoj K. Arora,et al.  A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas , 2006 .

[21]  N. Caine,et al.  The Rainfall Intensity - Duration Control of Shallow Landslides and Debris Flows , 1980 .

[22]  T. Kavzoglu,et al.  Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression , 2014, Landslides.

[23]  Ramkrishna Maiti,et al.  Integrating the Analytical Hierarchy Process (AHP) and the frequency ratio (FR) model in landslide susceptibility mapping of Shiv-khola watershed, Darjeeling Himalaya , 2013, International Journal of Disaster Risk Science.

[24]  S. De,et al.  Causes and consequences of landslides in the Darjiling-Sikkim Himalayas, India , 2003 .

[25]  M. Ruff,et al.  Landslide susceptibility analysis with a heuristic approach in the Eastern Alps (Vorarlberg, Austria) , 2008 .

[26]  D. Varnes.  Landslide hazard zonation: A review of principles and practice , 1984 .

[27]  Paul G. Ducksbury.  Parallel Texture Region Segmentation using a Pearl Bayes Network , 1993, BMVC.

[28]  C. F. Lee,et al.  Assessment of landslide susceptibility on the natural terrain of Lantau Island, Hong Kong , 2001 .

[29]  A. Erener,et al.  A comparative study for landslide susceptibility mapping using GIS-based multi-criteria decision analysis (MCDA), logistic regression (LR) and association rule mining (ARM) , 2016 .

[30]  Ebru Akcapinar Sezer,et al.  GeoFIS: An integrated tool for the assessment of landslide susceptibility , 2014, Comput. Geosci..

[31]  M. Summerfield,et al.  Tectonic uplift, threshold hillslopes, and denudation rates in a developing mountain range , 2007 .

[32]  Matthew C. Larsen,et al.  Assessing Landslide Hazards , 2007, Science.

[33]  Arvind Pandey,et al.  Visualization of 3-D digital elevation model for landslide assessment and prediction in mountainous terrain: A case study of Chandmari landslide, Sikkim, eastern Himalayas , 2005 .

[34]  Abbas Alimohammadi,et al.  Landslide Hazard Zonation Using Quantitative Methods in GIS , 2009 .

[35]  Timothy C. Haas,et al.  A Bayesian belief network advisory system for aspen regeneration , 1991 .

[36]  L. Ayalew,et al.  Landslide susceptibility mapping using GIS-based weighted linear combination, the case in Tsugawa area of Agano River, Niigata Prefecture, Japan , 2004 .

[37]  R. Soeters,et al.  Landslide hazard and risk zonation—why is it still so difficult? , 2006 .

[38]  A. Ozdemir,et al.  A comparative study of frequency ratio, weights of evidence and logistic regression methods for landslide susceptibility mapping: Sultan Mountains, SW Turkey , 2013 .