Presenting logistic regression-based landslide susceptibility results

Abstract A new work-flow is proposed to unify the way the community shares Logistic Regression results for landslide susceptibility purposes. Although Logistic Regression models and methods have been widely used in geomorphology for several decades, no standards for presenting results in a consistent way have been adopted; most papers report parameters with different units and interpretations, therefore limiting potential meta-analytic applications. We first summarize the major differences in the geomorphological literature and then investigate each one proposing current best practices and few methodological developments. The latter is mainly represented by a widely used approach in statistics for simultaneous parameter estimation and variable selection in generalized linear models, namely the Least Absolute Shrinkage Selection Operator (LASSO). The North-easternmost sector of Sicily (Italy) is chosen as a straightforward example with well exposed debris flows induced by extreme rainfall.

[1]  Frank E. Harrell,et al.  Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis , 2001 .

[2]  P. Reichenbach,et al.  Estimating the quality of landslide susceptibility models , 2006 .

[3]  Xiaoming Tang,et al.  Evaluation of different models in rainfall-triggered landslide susceptibility mapping: a case study in Chunan, southeast China , 2016, Environmental Earth Sciences.

[4]  E. Rotigliano,et al.  Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: application to the 2009 storm event in Messina (Sicily, southern Italy) , 2015, Natural Hazards.

[5]  J. Copas,et al.  Estimating the Residual Variance in Orthogonal Regression with Variable Selection , 1991 .

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

[7]  P. Atkinson,et al.  A systematic review of landslide probability mapping using logistic regression , 2015, Landslides.

[8]  C. Lee.  Statistical seismic landslide hazard analysis: An example from Taiwan , 2014 .

[9]  E. Rotigliano,et al.  A test of transferability for landslides susceptibility models under extreme climatic events: application to the Messina 2009 disaster , 2014, Natural Hazards.

[10]  Thomas Glade,et al.  The propagation of inventory-based positional errors into statistical landslide susceptibility models , 2016 .

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

[12]  Michele Calvello,et al.  A comparison of statistical and deterministic methods for shallow landslide susceptibility zoning in clayey soils , 2017 .

[13]  Ivan Marchesini,et al.  Non-susceptible landslide areas in Italy and in the Mediterranean region , 2014 .

[14]  Veerle Vanacker,et al.  Logistic regression applied to natural hazards: rare event logistic regression with replications , 2012 .

[15]  E. Rotigliano,et al.  Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north‐eastern Sicily, Italy) , 2016 .

[16]  P. Reichenbach,et al.  Combined landslide inventory and susceptibility assessment based on different mapping units: an example from the Flemish Ardennes, Belgium , 2009 .

[17]  Jui-Yi Ho,et al.  Assessment of susceptibility to rainfall-induced landslides using improved self-organizing linear output map, support vector machine, and logistic regression , 2017 .

[18]  M. Crozier.  Multiple-occurrence regional landslide events in New Zealand: Hazard management issues , 2005 .

[19]  R. Heerdegen,et al.  Quantifying source areas through land surface curvature and shape , 1982 .

[20]  L. Lombardo,et al.  Modelling the topsoil carbon stock of agricultural lands with the Stochastic Gradient Treeboost in a semi-arid Mediterranean region , 2017 .

[21]  H. Keselman,et al.  Backward, forward and stepwise automated subset selection algorithms: Frequency of obtaining authentic and noise variables , 1992 .

[22]  E. Rotigliano,et al.  Improving transferability strategies for debris flow susceptibility assessment: Application to the Saponara and Itala catchments (Messina, Italy) , 2017 .

[23]  L. Lombardo,et al.  Estimation of intrinsic aquifer vulnerability with index-overlay and statistical methods: the case of eastern Kopaida, central Greece , 2017, Applied Water Science.

[24]  M. Becht,et al.  Sample size matters: investigating the effect of sample size on a logistic regression susceptibility model for debris flows , 2014 .

[25]  V. Doyuran,et al.  A comparison of the GIS based landslide susceptibility assessment methods: multivariate versus bivariate , 2004 .

[26]  Keh-Jian Shou,et al.  Multi-scale landslide susceptibility analysis along a mountain highway in Central Taiwan , 2016 .

[27]  Florence W. Y. Ko,et al.  From landslide susceptibility to landslide frequency: A territory-wide study in Hong Kong , 2018, Engineering Geology.

[28]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

[29]  Christian Conoscenti,et al.  The role of the diagnostic areas in the assessment of landslide susceptibility models: a test in the sicilian chain , 2011 .

[30]  Zhaohua Chen,et al.  Landslide hazard mapping using logistic regression model in Mackenzie Valley, Canada , 2007 .

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

[32]  Alan Miller.  Bayesian subset selection , 2002 .

[33]  Giovanni B. Crosta,et al.  Techniques for evaluating the performance of landslide susceptibility models , 2010 .

[34]  E. Rotigliano,et al.  Predicting storm-triggered debris flow events: application to the 2009 Ionian Peloritan disaster (Sicily, Italy) , 2015 .

[35]  P. Reichenbach,et al.  Optimal landslide susceptibility zonation based on multiple forecasts , 2010 .

[36]  M. Rossi,et al.  Landslide susceptibility modeling in a landslide prone area in Mazandarn Province, north of Iran: a comparison between GLM, GAM, MARS, and M-AHP methods , 2017, Theoretical and Applied Climatology.

[37]  J. Böhner,et al.  Spatial Prediction of Soil Attributes Using Terrain Analysis and Climate Regionalisation , 2006 .

[38]  E. Rotigliano,et al.  Exploring the effect of absence selection on landslide susceptibility models: A case study in Sicily, Italy , 2016 .

[39]  Raphael Huser,et al.  Point process-based modeling of multiple debris flow landslides using INLA: an application to the 2009 Messina disaster , 2017, Stochastic Environmental Research and Risk Assessment.

[40]  Mauro Rossi,et al.  LAND-SE: a software for statistically based landslide susceptibilityzonation, version 1.0 , 2016 .

[41]  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 .

[42]  P. Reichenbach,et al.  Gis Technology in Mapping Landslide Hazard , 1995 .

[43]  A. Kawasaki,et al.  Landslide susceptibility mapping of the Sera River Basin using logistic regression model , 2017, Natural Hazards.

[44]  Kazuhide Sawada,et al.  Landslide susceptibility analysis with logistic regression model based on FCM sampling strategy , 2013, Comput. Geosci..

[45]  E. Rotigliano,et al.  Exploring relationships between grid cell size and accuracy for debris-flow susceptibility models: a test in the Giampilieri catchment (Sicily, Italy) , 2016, Environmental Earth Sciences.

[46]  C. Thorne,et al.  Quantitative analysis of land surface topography , 1987 .

[47]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[48]  M. Eeckhaut,et al.  Comparison of two landslide susceptibility assessments in the Champagne-Ardenne region (France). , 2010 .

[49]  Alexander Brenning,et al.  Landslide susceptibility near highways is increased by 1 order of magnitude in the Andes of southern Ecuador, Loja province , 2014 .

[50]  Massimo Mattei,et al.  GIS Methodology to Assess Landslide Susceptibility: Application to a River Catchment of Central Italy , 2009 .

[51]  N. Rosser,et al.  Spatial prediction of earthquake-induced landslide probability , 2017 .

[52]  Zong-De Shen,et al.  Improving the prediction of going concern of Taiwanese listed companies using a hybrid of LASSO with data mining techniques , 2016, SpringerPlus.

[53]  G. Fubelli,et al.  Presence-only approach to assess landslide triggering-thickness susceptibility: a test for the Mili catchment (north-eastern Sicily, Italy) , 2015, Natural Hazards.

[54]  Victor G. Jetten,et al.  Integration of two-phase solid fluid equations in a catchment model for flashfloods, debris flows and shallow slope failures , 2018, Environ. Model. Softw..

[55]  P. Martin Mai,et al.  Modeling soil organic carbon with Quantile Regression: Dissecting predictors' effects on carbon stocks , 2017, 1708.03859.

[56]  Jie Dou,et al.  Handling high predictor dimensionality in slope-unit-based landslide susceptibility models through LASSO-penalized Generalized Linear Model , 2017, Environ. Model. Softw..

[57]  A. Brenning,et al.  Assessing the quality of landslide susceptibility maps – case study Lower Austria , 2014 .