Skip to main content

Advertisement

SpringerLink
Log in

Support Vector Machines for Landslide Susceptibility Mapping: The Staffora River Basin Case Study, Italy

  • Published:
Mathematical Geosciences Aims and scope Submit manuscript

Abstract

The aim of this study is the application of support vector machines (SVM) to landslide susceptibility mapping. SVM are a set of machine learning methods in which model capacity matches data complexity. The research is based on a conceptual framework targeted to apply and test all the procedural steps for landslide susceptibility modeling from model selection, to investigation of predictive variables, from empirical cross-validation of results, to analysis of predicted patterns. SVM were successfully applied and the final susceptibility map was interpreted via success and prediction rate curves and receiver operating characteristic (ROC) curves, to support the modeling results and assess the robustness of the model. SVM appeared to be very specific learners, able to discriminate between the informative input and random noise. About 78% of occurrences was identified within the 20% of the most susceptible study area for the cross-validation set. Then the final susceptibility map was compared with other maps, addressed by different statistical approaches, commonly used in susceptibility mapping, such as logistic regression, linear discriminant analysis, and naive Bayes classifier. The SVM procedure was found feasible and able to outperform other techniques in terms of accuracy and generalization capacity. The over-performance of SVM against the other techniques was around 18% for the cross-validation set, considering the 20% of the most susceptible area. Moreover, by analyzing receiver operating characteristic (ROC) curves, SVM appeared to be less prone to false positives than the other models. The study was applied in the Staffora river basin (Lombardy, Northern Italy), an area of about 275 km2 characterized by a very high density of landslides, mainly superficial slope failures triggered by intense rainfall events.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aizerman MA, Braverman EM, Rozonoér LI (1964) Theoretical foundations of the potential function method in pattern recognition learning. Autom Remote Control 25:821–837

    Google Scholar 

  • Aleotti P, Chowdhury R (1999) Landslide hazard assessment: summary review and new perspectives. Bull Eng Geol Environ 58:21–44

    Article  Google Scholar 

  • Ayalew L, Yamagishi H (2005) The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda–Yahiko Mountains, central Japan. Geomorphology 65:15–31

    Article  Google Scholar 

  • Ballabio C (2009) Spatial prediction of soil properties in temperate mountain regions using support vector regression. Geoderma 151(3–4):338–350

    Article  Google Scholar 

  • Beatrizzotti G, Bellinzona G, Beltrami G, Boni A et al. (1969) Geological map of Italy fg.71-Voghera (2nd ed). Tech rep, Servizio Geologico d’Italia, Roma

  • Bellman R (1961) Adaptive control processes. Princeton University Press, Princeton

    Google Scholar 

  • Bonham-Carter G (1994) Geographic information systems for geoscientists: modelling with GIS. Elsevier, London

    Google Scholar 

  • Boulesteix AL (2007) WilcoxCV: an R package for fast variable selection in cross-validation. Methods Biochem Anal 23:1702–1704

    Google Scholar 

  • Braga G, Braschi G, Calculli S, Caucia F et al (1985) I fenomeni franosi nell’Oltrepò Pavese: tipologia e cause. Geol Appl Idrogeol 20:621–666

    Google Scholar 

  • Brenning A (2005) Spatial prediction models for landslide hazard: review, comparison and evaluation. Nat Hazards Earth Syst Sci 5:853–862

    Article  Google Scholar 

  • CARG project (1992) The new Italian 1:50 000 geological map. Tech rep, National Geological Survey, Rome, Italy

  • Carrara A, Cardinali M, Guzzetti F, Reichenbach P (1995) GIS technology in mapping landslide hazard. In: Geographic information systems in assessing natural Hazards. Kluwer, Dordrecht, pp 125–175

    Google Scholar 

  • Carrara A, Crosta G, Frattini P (2003) Geomorphological and historical data in assessing landslide hazard. Earth Surf Processes Landf 28:1125–1142

    Article  Google Scholar 

  • Carrara A, Crosta G, Frattini P (2008) Comparing models of debris-flow susceptibility in the alpine environment. Geomorphology 94:353–378

    Article  Google Scholar 

  • Chen P, Lin C, Scholkopf B (2005) A tutorial on ν-support vector machines. Appl Stoch Models Bus Ind 21:111–136

    Article  Google Scholar 

  • Cherkassky V, Mullier F (2007) Support vector regression. In: Learning from data: concepts, theory and methods, 2ed edn. Wiley, New York, pp 439–445

    Google Scholar 

  • Chung CJ, Fabbri A (1999) Probabilistic prediction models for landslide hazard mapping. Photogramm Eng Remote Sens 65:1389–1399

    Google Scholar 

  • Chung CJ, Fabbri A (2003) Validation of spatial prediction models for landslide hazard mapping. Photogramm Eng Remote Sens 65:451–472

    Google Scholar 

  • Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297

    Google Scholar 

  • Cruden D, Varnes D (1996) Landslides types and processes. In: Landslides: investigation and mitigation. Transportation Research Board Special Report, vol 247. National Academy Press, Washington, pp 36–75

    Google Scholar 

  • Dubayah R, Rich P (1995) Topographic solar radiation models for GIS. Int J Geogr Inf Syst 9:405–419

    Article  Google Scholar 

  • DUSAF project (2003) Destinazione d’uso dei suoli agricoli e forestali. Tech rep, Lombardy Region, Milano, Italy

  • Eeckhaut MVD, Vanwalleghem T, Poesen J, Govers G et al (2006) Prediction of landslide susceptibility using rare events logistic regression: A case-study in the Flemish Ardennes (Belgium). Geomorphology 76(3–4):392–410

    Article  Google Scholar 

  • Egan J (1975) Signal detection theory and ROC analysis. Academic Press, New York

    Google Scholar 

  • Evangelista P, Embrechts M, Szymanski B (2006) Taming the curse of dimensionality in kernels and novelty detection. In: Applied soft computing technologies: the challenge of complexity. Advances in Soft Computing, vol 34. Springer, Berlin, pp 425–438

    Chapter  Google Scholar 

  • Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27:861–874

    Article  Google Scholar 

  • Fox J, Monette G (1992) Generalized collinearity diagnostics. J Am Stat Assoc 87:178–183

    Article  Google Scholar 

  • Goodacre C, Bonham-Carter G, Agterberg FP, Wright D (1993) A statistical analysis of spatial association of seismicity with drainage patterns and magnetic anomalies in western Quebec. Tectonophysics 217:285–305

    Article  Google Scholar 

  • Guyon I, Elisseeff A (2003) An introduction into variable and feature selection. J Mach Learn Res 3:1157–1182. Special Issue on Variable and Feature Selection

    Google Scholar 

  • Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46:389–422

    Article  Google Scholar 

  • Guzzetti F, Carrara A, Cardinali M, Reichenbach P (1999) Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, central Italy. Geomorphology 31:181–216

    Article  Google Scholar 

  • Guzzetti F, Reichenbach P, Ardizzone F, Cardinali M et al (2006) Estimating the quality of landslide susceptibility models. Geomorphology 81:166–184

    Article  Google Scholar 

  • Hastie T, Tibshirani R, Friedman J (2001) Local methods in high dimensions. In: The elements of statistical learning: data mining, inference and prediction. Springer, New York, pp 22–27

    Google Scholar 

  • Hjerdt K, McDonnel J, Seibert J, Rodhe A (2004) A new topographic index to quantify downslope controls on local drainage. Water Resour Res 40:6

    Article  Google Scholar 

  • Hsu CW, Chang CC, Lin CJ (2007) A practical guide to support vector classification. Department of Computer Science, National Taiwan University, Taipei 106, Taiwan

  • Kanevski M, Pozdnoukhov A, Timonin V (2009) Machine learning for spatial environmental data. EPFL-Press

    Book  Google Scholar 

  • Kanevsky M, Canu S (2000) Spatial data mapping with support vector regression. Tech rep, IDIAP

  • LeCun Y, Denker J, Solla S, Howard R et al (1990) Optimal brain damage. In: Advances in neural information processing systems 2. Morgan Kaufmann, Denver

    Google Scholar 

  • Lin Y, Lee Y, Wahba G (2002) Support vector machines for classification in nonstandard situations. Mach Learn 46:191–202

    Article  Google Scholar 

  • Mann HB, Whitney DR (1947) On a test of whether one of two random variables is stochastically larger than the other. Ann Math Stat 18(1):50–60

    Article  Google Scholar 

  • Marquardt D (1970) Generalized inverses, ridge regression, biased linear estimation, and nonlinear estimation. Technometrics 12:605–607

    Article  Google Scholar 

  • McKenzie N, Ryan P (1999) Spatial prediction of soil properties using environmental correlation. Geoderma 89:67–94

    Article  Google Scholar 

  • Meisina C, Zucca F, Fossati D, Ceriani M et al (2006) Ground deformation monitoring by using the permanent scatterers technique: the example of the Oltrepo Pavese (Lombardia, Italy). Eng Geol 86(3–4):240–249

    Article  Google Scholar 

  • Meyer D, Leisch F, Hornik K (2003) The support vector machines under test. Neurocomputing 55:169–186

    Article  Google Scholar 

  • Nilsson NJ (1965) Foundations of trainable pattern classifying systems. McGraw-Hill, New York

    Google Scholar 

  • O’Brien RM (2007) A caution regarding rules of thumb for variance inflation factors. Qual Quant 41:673–690

    Article  Google Scholar 

  • Oommen T, Laurie G, Vogel R (2011) Sampling bias and class imbalance in maximum-likelihood logistic regression. Math Geosci 43:99–120

    Article  Google Scholar 

  • Platt J (1999) Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. In: Advances in large margin classifiers. MIT Press, Cambridge

    Google Scholar 

  • Poli S, Sterlacchini S (2007) Landslide representation strategies in susceptibility studies using Weights-of-Evidence modeling technique. Nat Resour Res 16:121–134

    Article  Google Scholar 

  • Pozdnoukhov A, Matasci G, Kanevski M, Purves R (2011) Spatio-temporal avalanche forecasting with support vector machines. Nat Hazards Earth Syst Sci 11:367–382

    Article  Google Scholar 

  • Samui P, Sitharam T (2010) Applicability of statistical learning algorithms for spatial variability of rock depth. Math Geosci 42:433–446. doi:10.1007/s11004-010-9268-7

    Article  Google Scholar 

  • Schölkopf B (2001) The kernel trick for distances. In: Proceedings neural information processing systems, pp 301–307

    Google Scholar 

  • Smirnoff A, Boisvert E, Paradis S (2008) Support vector machine for 3d modelling from sparse geological information of various origins. Comput Geosci 34(2):127–143

    Article  Google Scholar 

  • Sterlacchini S, Masetti M, Poli S (2004) Spatial integration of thematic data for predictive landslide mapping: a case study from Oltrepo Pavese area, Italy. In: Landslides: evaluation and stabilization. Taylor & Francis Group, London, pp 109–115

    Google Scholar 

  • van Westen CJ, Rengers N, Soeters R (2003) Use of geomorphological information in indirect landslide susceptibility assessment. Nat Hazards 30:399–419. doi:10.1023/B:NHAZ.0000007097.42735.9e

    Article  Google Scholar 

  • Vapnik V (1995) The nature of statistical learning. Springer, New York

    Google Scholar 

  • Vapnik V (1998) Statistical learning theory. Wiley, New York

    Google Scholar 

  • Wilcoxon F (1945) Individual comparisons by ranking methods. Biom Bull 1(6):80–83

    Article  Google Scholar 

  • Yokoyama R, Shirasawa M, Pike R (2002) Visualizing topography by openness: A new application of image processing to digital elevation models. Photogramm Eng Remote Sens 68:257–265

    Google Scholar 

  • Zevenbergen L, Thorne C (1987) Quantitative analysis of land surface topography. Earth Surf Processes Landf 12:47–56

    Article  Google Scholar 

  • Zhou X, Tuck D (2007) MSVM-RFE: extension of SVM-RFE for multiclass gene selection on DNA microarray data. Methods Biochem Anal 23:1106–1114

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Environmental and Land Sciences Dept., Università degli Studi di Milano-Bicocca, Milano, 20126, Italy

    Cristiano Ballabio

  2. Institute for the Dynamic of Environmental Processes, National Research Council (CNR-IDPA), Milano, 20126, Italy

    Simone Sterlacchini

Authors
  1. Cristiano Ballabio
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Simone Sterlacchini
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Cristiano Ballabio.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ballabio, C., Sterlacchini, S. Support Vector Machines for Landslide Susceptibility Mapping: The Staffora River Basin Case Study, Italy. Math Geosci 44, 47–70 (2012). https://doi.org/10.1007/s11004-011-9379-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11004-011-9379-9

Keywords

Search

Navigation