Natural Hazards

, Volume 79, Issue 3, pp 1621–1648 | Cite as

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)

  • L. Lombardo
  • M. Cama
  • C. Conoscenti
  • M. Märker
  • E. Rotigliano
Original Paper


This study aims to compare binary logistic regression (BLR) and stochastic gradient treeboost (SGT) methods in assessing landslide susceptibility within the Mediterranean region for multiple-occurrence regional landslide events. A test area was selected in the north-eastern sector of Sicily (southern Italy) where thousands of debris flows and debris avalanches triggered on the first October 2009 due to an extreme storm. Exploiting the same set of predictors and the 2009 event landslide archive, BLR- and SGT-based susceptibility models have been obtained for the two catchments separately, adopting a random partition (RP) technique for validation. In addition, the models trained in one catchment have been tested in predicting the landslide distribution in the second, adopting a spatial partition (SP)-based validation. The models produced high predictive performances with a general consistency between BLR and SGT in the susceptibility maps, predictor importance and role. In particular, SGT models reached a higher prediction performance with respect to BLR models for RP-modelling, while for the SP-based models, the difference in predictive skills dropped, converging to equally excellent performances. However, analysing the precision of the probability estimates, BLR produced more robust models around the mean value for each pixel, indicating possible overfitting effects, which affect decision trees to a greater extent. The assessment of the predictor roles allowed identifying the activation mechanisms which are primarily controlled by steep south-facing open slopes located near the coastal area. These slopes are characterised by low/middle altitude downhill from mountain tops, having a medium-grade metamorphic bedrock, under grassland and cultivated (terraced) uses.


Landslide susceptibility Forward logistic regression Stochastic gradient treeboost Prediction spatial transferability Messina 2009 disaster Sicily 



The findings and discussion of this research were carried out in the framework of the PhD research projects of Luigi Lombardo and Mariaelena Cama at the Department of Earth and Sea Sciences, University of Palermo. Luigi Lombardo PhD thesis is internationally co-tutored with the Department of Geography of the University of Tübingen (Germany). This research was supported by the project SUFRA_SICILIA funded by the ARTA-Regione Sicilia and the FFR 2012/2013 project funded by the University of Palermo. The group would like to thank Franco Formicola, student of Mathematics at the University of Palermo, for his specific support with the SGT algorithm.


  1. Akgün A (2012) A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at İzmir, Turkey. Landslides 9:93–106CrossRefGoogle Scholar
  2. Ardizzone F, Basile G, Cardinali M, Casagli N, Del Conte S, Del Ventisette C, Fiorucci F, Garfagnoli F, Gigli G, Guzzetti F, Iovine G, Mondini AC, Moretti S, Panebianco M, Raspini F, Reichenbach P, Rossi M, Tanteri L, Terranova O (2012) Landslide inventory map for the Briga and the Giampilieri catchments, NE Sicily, Italy. J Maps 8:176–180CrossRefGoogle Scholar
  3. Aronica GT, Brigandì G, Morey N (2012) Flash floods and debris flow in the city area of Messina, north-east part of Sicily, Italy in October 2009: the case of the Giampilieri catchment. Nat Hazards Earth Syst Sci 12(5):1295–1309. doi: 10.5194/nhess-12-1295-2012 CrossRefGoogle Scholar
  4. Beven KJ, Kirkby MJ (1979) A physically based variable contributing area model of basin hydrology. Hydrol Sci Bull 24:43–69CrossRefGoogle Scholar
  5. Brenning A (2005) Spatial prediction models for landslide hazards: review, comparison and evaluation. Nat Hazards Earth Syst Sci 5:853–862. doi: 10.5194/nhess-5-853-2005 CrossRefGoogle Scholar
  6. Burrough PA, McDonell RA (1998) Principles of geographical information systems. Oxford University Press, New YorkGoogle Scholar
  7. Büttner G, Kosztra B (2007) CLC2006 technical guidelines. Technical report no. 17/2007. EEA.
  8. Cascini L, Cuomo S, Guida D (2008) Typical source areas of May 1998 flow-like mass movements in the Campania region, Southern Italy. Eng Geol 96:107–125CrossRefGoogle Scholar
  9. Chung CJ, Fabbri AG (2003) Validation of spatial prediction models for landslide hazard mapping. Nat Hazards 30(3):451–472. doi: 10.1023/B:NHAZ.0000007172.62651.2b CrossRefGoogle Scholar
  10. Ciampi A (1991) Generalized regression trees. Comput Stat Data Anal 12(1):57–78. doi: 10.1016/0167-9473(91)90103-9 CrossRefGoogle Scholar
  11. Costanzo D, Rotigliano E, Irigaray C, Jiménez-Perálvarez JD, Chacón J (2012a) Factors selection in landslide susceptibility modelling on large scale following the gis matrix method: application to the river Beiro basin (Spain). Nat Hazards Earth Syst Sci 2(2):327–340. doi: 10.5194/nhess-12-327-2012 CrossRefGoogle Scholar
  12. Costanzo D, Cappadonia C, Conoscenti C, Rotigliano E (2012b) Exporting a Google Earth™ aided earth-flow susceptibility model: a test in central Sicily. Nat Hazards 61(1):103–114. doi: 10.1007/s11069-011-9870-0 CrossRefGoogle Scholar
  13. Costanzo D, Chacón J, Conoscenti C, Irigaray C, Rotigliano E (2014) Forward logistic regression for earth-flow landslide susceptibility assessment in the Platani river basin (southern Sicily, Italy). Landslides 11:639–653. doi: 10.1007/s10346-013-0415-3 CrossRefGoogle Scholar
  14. Crozier MJ (2005) Multiple-occurrence regional landslide events in New Zealand: hazard management issues. Landslides 2(4):247–256. doi: 10.1007/s10346-005-0019-7 CrossRefGoogle Scholar
  15. De Guidi G, Scudero S (2013) Landslide susceptibility assessment in the Peloritani Mts. (Sicily, Italy) and clues for tectonic control of relief processes. Nat Hazards Earth Syst Sci 13:949–963. doi: 10.5194/nhess-13-949-2013 CrossRefGoogle Scholar
  16. De’ath G, Fabricius KE (2000) Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology 81:3178–3192CrossRefGoogle Scholar
  17. Del Ventisette C, Garfagnoli F, Ciampalini A, Battistini A, Gigli G, Moretti S, Casagli N (2012) An integrated approach to the study of catastrophic debris-flows: geological hazard and human influence. Nat Hazards Earth Syst Sci 12:2907–2922. doi: 10.5194/nhess-12-2907-2012 CrossRefGoogle Scholar
  18. Den Eeckhaut MV, Marre A, Poesen J (2010) Comparison of two landslide susceptibility assessments in the Champagne-Ardenne region (France). Geomorphology 115(1–2):141–155. doi: 10.1016/j.geomorph.2009.09.042 CrossRefGoogle Scholar
  19. Elith J, Leathwick J, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77(4):802–813CrossRefGoogle Scholar
  20. Fabbri AG, Chung CJ (2008) On blind tests and spatial prediction models. Nat Resour Res 17(2):107–118. doi: 10.1007/s11053-008-9072-y CrossRefGoogle Scholar
  21. Felicísimo A, Cuartero A, Remondo J, Quirós E (2012) Mapping landslide susceptibility with logistic regression, multiple adaptive regression splines, classification and regression trees, and maximum entropy methods: a comparative study. Landslides 10:175–189. doi: 10.1007/s10346-012-0320-1 CrossRefGoogle Scholar
  22. Frattini P, Crosta G, Carrara A (2010) Techniques for evaluating the performance of landslide susceptibility models. Eng Geol 111(1–4):62–72. doi: 10.1016/j.enggeo.2009.12.004 CrossRefGoogle Scholar
  23. Friedman JH (1999) Stochastic gradient boosting. Technical report, Dept. of Statistics, Stanford UniversityGoogle Scholar
  24. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232CrossRefGoogle Scholar
  25. Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38:367–378CrossRefGoogle Scholar
  26. Goetz JN, Brenning A, Petschko H, Leopold P (2015) Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Comput Geosci 81:1–11. doi: 10.1016/j.cageo.2015.04.007 CrossRefGoogle Scholar
  27. Gómez Gutiérrez A, Schnabel S, Lavado Contador F (2009) Using and comparing two nonparametric methods (CART and MARS) to model the potential distribution of gullies. Ecol Model 220:3630–3637. doi: 10.1016/j.ecolmodel.2009.06.020 CrossRefGoogle Scholar
  28. Gonçalves JA, Henriques R (2015) UAV photogrammetry for topographic monitoring of coastal areas. ISPRS J Photogramm Remote Sens 104:101–111CrossRefGoogle Scholar
  29. Goswami R, Mitchell NC, Brocklehurst SH (2011) Distribution and causes of landslides in the eastern Peloritani of NE Sicily and western Aspromonte of SW Calabria, Italy. Geomorphology 132:111–122CrossRefGoogle Scholar
  30. Gullà G, Caloiero T, Coscarelli R, Petrucci O (2012) A proposal for a methodological approach to the characterisation of widespread landslide events: an application to Southern Italy. Nat Hazards Earth Syst Sci 12:165–173. doi: 10.5194/nhess-12-165-2012 CrossRefGoogle Scholar
  31. 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(1–4):181–216. doi: 10.1016/S0169-555X(99)00078-1 CrossRefGoogle Scholar
  32. Guzzetti F, Reichenbach P, Cardinali M, Galli M, Ardizzone F (2005) Probabilistic landslide hazard assessment at the basin scale. Geomorphology 72(1–4):272–299. doi: 10.1016/j.geomorph.2005.06.002 CrossRefGoogle Scholar
  33. Guzzetti F, Reichenbach P, Ardizzone F, Cardinali M, Galli M (2006) Estimating the quality of landslide susceptibility models. Geomorphology 81(1–2):166–184. doi: 10.1016/j.geomorph.2006.04.007 CrossRefGoogle Scholar
  34. Hosmer DW, Lemeshow S (2000) Applied logistic regression. Wiley, Wiley Series in Probability and StatisticsCrossRefGoogle Scholar
  35. Hungr O, Evans SG, Bovis MJ, Hutchinson JN (2001) A review of the classification of landslides of the flow type. Environ Eng Geosci 7(3):221–238CrossRefGoogle Scholar
  36. Hungr O, McDougall S, Bovis M (2005) Entrainment of material by debris flows. Debris-flow hazards and related phenomena. Springer, Berlin, pp 135–158CrossRefGoogle Scholar
  37. Irigaray C, Fernández T, El Hamdouni R, Chacón J (2007) Evaluation and validation of landslide-susceptibility maps obtained by a GIS matrix method: examples from the Betic Cordillera (southern Spain). Nat Hazards 41(1):61–79. doi: 10.1007/s11069-006-9027-8 CrossRefGoogle Scholar
  38. Lentini F, Catalano S, Carbone S (2000) Note illustrative della Carta Geologica della Provincia di Messina, scala 1:50.000. Provincia Regionale di Messina, Assessorato Servizio Territorio – Servizio GeologicoGoogle Scholar
  39. Liu X, Wang D, Jiang L, Chen F (2011) An improved algorithm for oblique decision tree classification based on rough set theory. J Comput Inf Syst 7(11):4042–4049Google Scholar
  40. Lombardo L, Cama M, Märker M, Rotigliano E (2014) A test of transferability for landslides susceptibility models under extreme climatic events: application to the Messina (Italy) disaster 2009. Nat Hazards 74:1951–1989. doi: 10.1007/s11069-014-1285-2 CrossRefGoogle Scholar
  41. Messina A, Somma R, Careri G, Carbone G, Macaione E (2004) Peloritani continental crust composition (southern Italy): geological and petrochemical evidences. Bollettino della Società Geologica Italiana 123:405–444Google Scholar
  42. Mondini AC, Guzzetti F, Reichenbach P, Rossi M, Cardinali M, Ardizzone F (2011) Semi-automatic recognition and mapping of rainfall induced shallow landslides using optical satellite images. Remote Sens Environ 115(7):1743–1757. doi: 10.1016/j.rse.2011.03.006 CrossRefGoogle Scholar
  43. Moore ID, Grayson RB, Landson AR (1991) Digital terrain modelling: a review of hydrological, geomorphological, and biological applications. Hydrol Process 5:3–30CrossRefGoogle Scholar
  44. Nefeslioglu HA, Gokceoglu C, Sonmez H (2008) An assessment on the use of logistic regression and artificial neural networks with different sampling strategies for the preparation of landslide susceptibility maps. Eng Geol 97(3–4):171–191. doi: 10.1016/j.enggeo.2008.01.004 CrossRefGoogle Scholar
  45. Petschko H, Brenning A, Bell R, Goetz J, Glade T (2014) Assessing the quality of landslide susceptibility maps—case study Lower Austria. Nat Hazards Earth Syst Sci 14:95–118. doi: 10.5194/nhess-14-95-2014 CrossRefGoogle Scholar
  46. Prasad A, Iverson L, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9:181–199CrossRefGoogle Scholar
  47. Rakotomalala R (2005) Tanagra: un logiciel gratuit pour l’enseignement et la recherche. In: Actes De EGC, pp 697–702Google Scholar
  48. Reichenbach P, Busca C, Mondini AC, Rossi M (2014) The influence of land use change on landslide susceptibility zonation: the Briga catchment test site (Messina, Italy). Environ Manag 54:1372–1384CrossRefGoogle Scholar
  49. Rossi M, Guzzetti F, Reichenbach P, Mondini AC, Peruccacci S (2010) Optimal landslide susceptibility zonation based on multiple forecasts. Geomorphology 114(3):129–142. doi: 10.1016/j.geomorph.2009.06.020 CrossRefGoogle Scholar
  50. Rotigliano E, Agnesi V, Cappadonia C, Conoscenti C (2011) The role of the diagnostic areas in the assessment of landslide susceptibility models: a test in the Sicilian chain. Nat Hazards 58(3):981–999. doi: 10.1007/s11069-010-9708-1 CrossRefGoogle Scholar
  51. Süzen ML, Doyuran V (2004) A comparison of the GIS based landslide susceptibility assessment methods: multivariate versus bivariate. Environ Geol 45(5):665–679. doi: 10.1007/s00254-003-0917-8 CrossRefGoogle Scholar
  52. Tagil S, Jenness J (2008) GIS-based automated landform classification and topographic, landcover and geologic attributes of landforms around the Yazoren Polje, Turkey. J Appl Sci 8:910–921CrossRefGoogle Scholar
  53. Tarboton DG, Bras RL, Rodriguez-Iturbe I (1991) On the extraction of channel networks from digital elevation data. Hydrol Process 5:81–100CrossRefGoogle Scholar
  54. Tarolli P, Borga M, Dalla Fontana G (2008) Analysing the influence of upslope bedrock outcrops on shallow landsliding. Geomorphology 93:186–200CrossRefGoogle Scholar
  55. Tien Bui D, Lofman O, Revhaug I, Dick O (2011) Landslide susceptibility analysis in the Hoa Binh province of Vietnam using statistical index and logistic regression. Nat Hazards 59:1413–1444CrossRefGoogle Scholar
  56. Tien Bui D, Tuan TA, Klempe H, Pradhan B, Revhaug I (2015) Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides. doi: 10.1007/s10346-015-0557-6 Google Scholar
  57. Van Den Eeckhaut M, Reichenbach P, Guzzetti F, Rossi M, Poesen J (2009) Combined landslide inventory and susceptibility assessment based on different mapping units: an example from the Flemish Ardennes, Belgium. Nat Hazards Earth Syst Sci 9(2):507–521. doi: 10.5194/nhess-9-507-2009 CrossRefGoogle Scholar
  58. Vapnik V (1995) The nature of statistical learning theory. Springer, New YorkCrossRefGoogle Scholar
  59. Von Ruette J, Papritz A, Lehmann P, Rickli C, Or D (2011) Spatial statistical modelling of shallow landslides—validating predictions for different landslide inventories and rainfall events. Geomorphology 133(1–2):11–22. doi: 10.1016/j.geomorph.2011.06.010 CrossRefGoogle Scholar
  60. Vorpahl P, Elsenbeer H, Märker M, Schröder B (2012) How can statistical models help to determine driving factors of landslides? Ecol Model 239:27–39. doi: 10.1016/j.ecolmodel.2011.12.007 CrossRefGoogle Scholar
  61. Wei F, Gao K, Hu K, Li Y, Gardner JS (2008) Relationships between debris flows and earth surface factors in Southwest China. Environ Geol 55:619–627CrossRefGoogle Scholar
  62. Wilson JP, Gallant GC (2000) Digital terrain analysis. In: Wilson JP, Gallant JC (eds) Terrain analysis: principles and applications. Wiley, New York, pp 1–27Google Scholar
  63. Yalcin A, Reis S, Aydinoglu AC, Yomralioglu T (2011) A GIS-based comparative study of frequency ratio, analytical hierarchy process, bivariate statistics and logistics regression methods for landslide susceptibility mapping in Trabzon, NE Turkey. Catena 85(3):274–287. doi: 10.1016/j.catena.2011.01.014 CrossRefGoogle Scholar
  64. Yesilnacar E, Topal T (2005) Landslide susceptibility mapping: a comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey). Eng Geol 79:251–266CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2015

Authors and Affiliations

  • L. Lombardo
    • 1
    • 2
  • M. Cama
    • 1
  • C. Conoscenti
    • 1
  • M. Märker
    • 2
    • 3
  • E. Rotigliano
    • 1
  1. 1.Department of Earth and Sea SciencesUniversity of PalermoPalermoItaly
  2. 2.Department of Physical Geography and GISUniversity of TuebingenTuebingenGermany
  3. 3.Department of Earth SciencesUniversity of FlorenceFlorenceItaly

Personalised recommendations