Multi-Resolution Landslide Susceptibility Analysis Using a DEM and Random Forest

Landslide susceptibility (LS) mapping is a requisite for safety against sediment related disasters, and considerable effort has been exerted in this discipline. However, the size heterogeneity and distribution of landslides still impose challenges in selecting an appropriate scale for LS studies. This requires identification of an optimal scale for landslide causative parameters. In this study, we propose a method to identify the optimum scale for each parameter and use multiple optimal parameter-scale combinations for LS mapping. A random forest model was used, together with 16 geomorphological parameters extracted from 10, 30, 60, 90, 120, 150, and 300 m digital elevation models (DEMs) and an inventory of historical landslides. Experiments in two equal-sized (625 km2) areas in Niigata and Ehime, Japan, with different geological and environmental settings and landslide density, demonstrated the efficiency of the proposed method. It outperformed all other single scale LS analysis with a prediction accuracy of 79.7% for Niigata and 78.62% for Ehime. Values of areas under receiver operating characteristics (ROC) curves (AUC) of 0.877 and 0.870 validate the application of the multi-scale model.

[1]  José Vicente Pérez-Peña,et al.  Differentiating geology and tectonics using a spatial autocorrelation technique for the hypsometric integral , 2009 .

[2]  H. A. Nefeslioglu,et al.  Landslide susceptibility mapping for a part of tectonic Kelkit Valley (Eastern Black Sea region of Turkey) , 2008 .

[3]  G. Heuvelink,et al.  DEM resolution effects on shallow landslide hazard and soil redistribution modelling , 2005 .

[4]  A. Brenning.  Spatial prediction models for landslide hazards: review, comparison and evaluation , 2005 .

[5]  Kazuaki Nakamura,et al.  Late Cenozoic orogeny in Japan , 1967 .

[6]  P. Reichenbach,et al.  Different landslide sampling strategies in a grid-based bi-variate statistical susceptibility model , 2016 .

[7]  B. Has,et al.  Characteristics of earthquake-induced landslides in a heavy snowfall region—landslides triggered by the northern Nagano prefecture earthquake, March 12, 2011, Japan , 2012, Landslides.

[8]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[9]  A. Lucieer,et al.  Mapping Sub-Antarctic Cushion Plants Using Random Forests to Combine Very High Resolution Satellite Imagery and Terrain Modelling , 2013, PloS one.

[10]  Gary A. Peterson,et al.  Soil Attribute Prediction Using Terrain Analysis , 1993 .

[11]  R. J. Pike,et al.  Automated classifications of topography from DEMs by an unsupervised nested-means algorithm and a three-part geometric signature , 2007 .

[12]  Veronica Tofani,et al.  Landslide susceptibility estimation by random forests technique: sensitivity and scaling issues , 2013 .

[13]  N. Drake,et al.  Comparison of slope estimates from low resolution DEMs: scaling issues and a fractal method for their solution , 1999 .

[14]  L. Ayalew,et al.  The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, Central Japan , 2005 .

[15]  T. Oguchi,et al.  Drainage density, slope angle, and relative basin position in Japanese bare lands from high-resolution DEMs , 2004 .

[16]  Minoru Yamanaka,et al.  DEM-Based Analysis of Earthquake-Induced Shallow Landslide Susceptibility , 2009 .

[17]  A. N. Strahler.  Hypsometric (area-altitude) analysis of erosional topography. , 1952 .

[18]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[19]  Bruce D. Malamud,et al.  Power-law correlations of landslide areas in central Italy , 2001 .

[20]  C. J. Westen,et al.  Qualitative landslide susceptibility assessment by multicriteria analysis: A case study from San Antonio del Sur, Guantánamo, Cuba , 2008 .

[21]  Hiroshi P. Sato,et al.  Crustal structure in the northern Fossa Magna region, central Japan, modeled from refraction/wide-angle reflection data , 2004 .

[22]  M. Anderson,et al.  Landslide hazard and risk , 2005 .

[23]  H. A. Nefeslioglu,et al.  An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps , 2008 .

[24]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  E. Yesilnacar,et al.  Landslide susceptibility mapping : A comparison of logistic regression and neural networks methods in a medium scale study, Hendek Region (Turkey) , 2005 .

[26]  D. Turcotte,et al.  Landslide inventories and their statistical properties , 2004 .

[27]  Filippo Catani,et al.  Statistical analysis of drainage density from digital terrain data , 2001 .

[28]  B. Pradhan,et al.  Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models , 2012 .

[29]  M. Hsu,et al.  Modeling typhoon- and earthquake-induced landslides in a mountainous watershed using logistic regression , 2007 .

[30]  T. Glade,et al.  A Review of Scale Dependency in Landslide Hazard and Risk Analysis , 2012 .

[31]  H. Yoshimatsu,et al.  A review of landslide hazards in Japan and assessment of their susceptibility using an analytical hierarchic process (AHP) method , 2006 .

[32]  Boris Schröder,et al.  How can statistical models help to determine driving factors of landslides , 2012 .

[33]  E. E. Brabb.  Innovative approaches to landslide hazard and risk mapping , 1985 .

[34]  S. Pascale,et al.  Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy) , 2014 .

[35]  C. Chen,et al.  Morphometric analysis of debris flows and their source areas using GIS , 2011 .

[36]  D. Hendricks,et al.  The influence of slope aspect on soil weathering processes in the Springerville volcanic field, Arizona , 2001 .

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

[38]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[39]  Keith Beven,et al.  The role of bedrock topography on subsurface storm flow , 2002 .

[40]  S. Banno,et al.  Geology and metamorphic evolution of the Sanbagawa metamorphic belt, Japan , 1989, Geological Society, London, Special Publications.

[41]  A. Takeuchi.  Basement-involved tectonics in North Fossa Magna, central Japan: The significance of the northern Itoigawa-Shizuoka Tectonic Line , 2004 .

[42]  A. Akgun.  A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at İzmir, Turkey , 2012, Landslides.

[43]  D. Staley,et al.  The Use of Airborne Laser Swath Mapping on Fans and Cones: An Example from the Colorado Front Range , 2013 .

[44]  I. Moore,et al.  Digital terrain modelling: A review of hydrological, geomorphological, and biological applications , 1991 .

[45]  Oky Dicky Ardiansyah Prima,et al.  Characterization of volcanic geomorphology and geology by slope and topographic openness , 2010 .

[46]  D. Tarboton.  A new method for the determination of flow directions and upslope areas in grid digital elevation models , 1997 .

[47]  R. Yokoyama,et al.  Supervised landform classification of Northeast Honshu from DEM-derived thematic maps , 2006 .

[48]  Kyoji Sassa,et al.  The influence of intense rainfall on the activity of large-scale crystalline schist landslides in Shikoku Island, Japan , 2005 .

[49]  K. Ng.  Landslide locations and drainage network development: A case study of Hong Kong , 2006 .

[50]  Z. Yin,et al.  A comparison of drainage networks derived from digital elevation models at two scales , 1998 .

[51]  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 .

[52]  P. Atkinson,et al.  Generalised linear modelling of susceptibility to landsliding in the Central Apennines, Italy , 1998 .

[53]  H. Saito,et al.  Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: The Akaishi Mountains, Japan , 2009 .

[54]  Takashi Oguchi,et al.  Drainage Density and Relative Relief in Humid Steep Mountains with Frequent Slope Failure , 1997 .

[55]  Saro Lee,et al.  Probabilistic landslide susceptibility and factor effect analysis , 2005 .

[56]  F. Pabian,et al.  Quantitative Geomorphometrics for Terrain Characterization , 2014 .

[57]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[58]  H. Ishizuka,et al.  Low‐grade metamorphism of the Mikabu and northern Chichibu belts in central Shikoku, SW Japan: implications for the areal extent of the Sanbagawa low‐grade metamorphism , 1998 .

[59]  Netra R. Regmi,et al.  Modeling susceptibility to landslides using the weight of evidence approach: Western Colorado, USA , 2010 .

[60]  L. Band.  Topographic Partition of Watersheds with Digital Elevation Models , 1986 .

[61]  Frank E. Harrell,et al.  Multivariable Modeling Strategies , 2015 .

[62]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[63]  S. Kazama,et al.  Assessment of snowmelt triggered landslide hazard and risk in Japan , 2009 .

[64]  S. Reis,et al.  A GIS-based comparative study of frequency ratio, analytical hierarchy process, bivariate statistics , 2011 .

[65]  K. Chou,et al.  iDNA-Prot: Identification of DNA Binding Proteins Using Random Forest with Grey Model , 2011, PloS one.

[66]  Qiming Zhou,et al.  Generalization of DEM for terrain analysis using a compound method , 2011 .

[67]  P. Reichenbach,et al.  Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, Central Italy , 1999 .

[68]  David G. Tarboton,et al.  A New Method for Determination of Most Likely Landslide Initiation Points and the Evaluation of Digital Terrain Model Scale in Terrain Stability Mapping , 2006 .

[69]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[70]  B. Lowery,et al.  Identification of the spatial distribution of soils using a process-based terrain characterization , 2001 .

[71]  Jeroen M. Schoorl,et al.  Calibration and resolution effects on model performance for predicting shallow landslide locations in Taiwan , 2011 .

[72]  Kyoji Sassa,et al.  Analysis of a spatial distribution of landslides triggered by the 2004 Chuetsu earthquakes of Niigata Prefecture, Japan , 2007 .

[73]  Yoichi Okura,et al.  Application of Universal Soil Loss Equation (USLE) to mountainous forests in Japan , 2000, Journal of Forest Research.

[74]  D. Montgomery,et al.  Source areas, drainage density, and channel initiation , 1989 .

[75]  R. J. Pike,et al.  Elevation-Relief Ratio, Hypsometric Integral, and Geomorphic Area-Altitude Analysis , 1971 .

[76]  Samuele Segoni,et al.  An empirical geomorphology‐based approach to the spatial prediction of soil thickness at catchment scale , 2010 .

[77]  C. Chung,et al.  Predicting landslides for risk analysis — Spatial models tested by a cross-validation technique , 2008 .

[78]  S. Schumm.  EVOLUTION OF DRAINAGE SYSTEMS AND SLOPES IN BADLANDS AT PERTH AMBOY, NEW JERSEY , 1956 .