Abstract
This article presents a multidisciplinary approach to landslide susceptibility mapping by means of logistic regression, artificial neural network, and geographic information system (GIS) techniques. The methodology applied in ranking slope instability developed through statistical models (conditional analysis and logistic regression), and neural network application, in order to better understand the relationship between the geological/geomorphological landforms and processes and landslide occurrence, and to increase the performance of landslide susceptibility models. The proposed experimental study concerns with a wide research project, promoted by the Tuscany Region Administration and APAT-Italian Geological Survey, aimed at defining the landslide hazard in the area of the Sheet 250 “Castelnuovo di Garfagnana” (1:50,000 scale). The study area is located in the middle part of the Serchio River basin and is characterized by high landslide susceptibility due to its geological, geomorphological, and climatic features, among the most severe in Italy. Terrain susceptibility to slope failure has been approached by means of indirect-quantitative statistical methods and neural network software application. Experimental results from different methods and the potentials and pitfalls of this methodological approach have been presented and discussed. Applying multivariate statistical analyses made it possible a better understanding of the phenomena and quantification of the relationship between the instability factors and landslide occurrence. In particular, the application of a multilayer neural network, equipped for supervised learning and error control, has improved the performance of the model. Finally, a first attempt to evaluate the classification efficiency of the multivariate models has been performed by means of the receiver operating characteristic (ROC) curves analysis approach.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aleotti P, Balzelli P, De Marchi D (1996) Le reti neurali nella valutazione della suscettibilità da frana. Geol Tecnica Ambientale 5(4):37–47
Bartolomei A, Brugioni M, Canuti P, Casagli N, Catani F, Ermini L, Kukavicic M, Menduni G, Tofani V (2006) Analisi della suscettibilità da frana a scala di bacino (Bacino del fiume Arno, Toscana-Umbria, Italia). Giornale di Geologia applicata 3:189–195
Begueria S (2006) Validation and evaluation of predictive models in hazard assessment and risk management. Nat Hazards 37(3):315–329. doi:10.1007/s11069-005-5182-6
Bernknopf RL, Brookshire DS, Shapiro CD (1988) A probabilistic approach to landslide hazard mapping in Cincinnati, Ohio, with applications for economic evaluation. Bull As Eng Geol 24:39–56
Bieniawski ZT (1989) Engineering rock mass classifications. Wiley, New York
Caredio F, Castaldini D, Puccinelli A (1997) Gravitational slope deformations near the Abetone pass (Tuscan-Emilian Apennines). Geogr Fisica Dinamica Quaternaria 19:287–296
Carrara A, Pugliese Carratelli E, Merenda L (1977) Computer-based data bank and statistical analysis of slope instability phenomena. Z fur Geom NF 21(2):122–187
Carrara A, Cardinali M, Guzzetti F, Reichenbach P (1995a) GIS technology in mapping landslide hazard. In: Carrara A, Guzzetti F (eds) Geographical information systems in assessing natural hazards. Kluwer Academic Publisher, Dordrecht, pp 135–175
Carrara A, Cardinali M, Guzzetti F, Reichenbach P (1995b) GIS-based techniques for mapping landslide hazard. http//:deis158.deis.unibo.it
Casella G, Berger L (1990) Statistical inference. Duxbury Press, Belmont
Castaldini D, Caredio F, D’Amato Avanzi G, Perilli N, Puccinelli A (2004) Glacial features in the Tuscan-Emilian Apennines (Italy): evidences from the Abetone area. In: Morini D, Bruni P (eds) The Regione Toscana Project of geological mapping. Case histories and data acquisition. Regione Toscana, Firenze, pp 67–76
Cherkassky V, Krasnopolsky V, Solomatine DP, Valdes J (2006) Computational intelligence in earth sciences and environmental applications: issues and challenges. Neural Netw 19:113–121. doi:10.1016/j.neunet.2006.01.001
Clerici A, Perego S, Tellini C, Vescovi P (2002) Il sistema Informativo Territoriale delle frane della Val Parma: modalità costruttive, caratteristiche ed esempi di utilizzo. Geol Tecnica Ambientale 2:21–40
D’Amato Avanzi G, Puccinelli A (1997) Deep-seated gravitational slope deformations in north-western Tuscany (Italy): remarks on typology, distribution and tectonic connections. Geogr Fisica Dinamica Quaternaria 19:325–334
D’amato Avanzi G, Puccinelli A, Verani M (2000) Progress in methods in the studies on slope instability in North-Western Tuscany. Atti della Società Toscana di Scienze Naturali Mem Ser A 107:115–123
Egan JP (1975) Signal detection theory and ROC analysis. Academic Press, New York
Ermini L, Catani F, Casagli N (2005) Artificial neural network applied to landslide susceptibility assessment. Geomorphology 66:327–343. doi:10.1016/j.geomorph.2004.09.025
Federici PR, Puccinelli A, Cantarelli E, Casarosa N, D’amato Avanzi G, Falaschi F, Giannecchini R, Pochini A, Ribolini A, Bottai M, Salvati N, Testi C (2005) Uso di tecniche GIS nella valutazione della pericolosità di frana nella valle del Serchio (Lu). Atti 9a Conferenza Nazionale ASITA 2:1059–1064
Federici PR, Puccinelli A, Cantarelli E, Casarosa N, D’amato Avanzi G, Falaschi F, Giannecchini R, Pochini A, Ribolini A, Bottai M, Salvati N, Testi C (2007) Multidisciplinary investigations in evaluating landslide hazard. An example in the Serchio River valley (Italy). Quat Int 171–172:52–63. doi:10.1016/j.quaint.2006.10.018
Fernandez-Steeger TM, Rohn J, Czurda K (2002) Identification of landslide areas with neural nets for hazard analysis. In: Rybar J, Stemnerk J, Wagner P (eds) Landslides. Proceedings of the I ECL, Prague. Balkema, The Netherlands, pp 163–168
Giudici P (2005) Data mining: metodi informatici, statistici e applicazioni. McGraw Hill, Milano, p 401
Gorsevski PV, Gessler PE, Foltz RB, Elliot WJ (2006) Spatial prediction of landslide hazard using logistic regression and ROC analysis. Trans GIS 10(3):395–415. doi:10.1111/j.1467-9671.2006.01004.x
Greco R, Sorriso-Valvo M, Catalano E (2007) Logistic regression analysis in the evaluation of mass-movements susceptibility: the Aspromonte case study, Calabria, Italy. Eng Geol 89:47–66. doi:10.1016/j.enggeo.2006.09.006
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. doi:10.1016/S0169-555X(99)00078-1
Hansen A (1984) Landslide hazard analysis. In: Brunsden D, Prior DB (eds) Slope instability. Wiley,
Hutchinson JN (1988) Morphological and geotechnical parameters of landslides in relation to geology and hydrogeology. Proceedings of the 5th international symposium on landslides, Losanna, vol 1, pp 3–35
ISRM (1978) Suggested methods for the quantitative description of discontinuities in rock masses. Int J Rock Mech Min Sci Geomech Abstr 15:319–368. doi:10.1016/0148-9062(78)91472-9
ISRM (1981) Rock characterization, testing and monitoring: suggested methods. Pergamon, New York
Jenks GF (1989) Geographic logic in line generalization. Cartographica 26(1):27–42
Kosko B (1992) Neural networks and fuzzy systems. Prentice Hall,
Krasnopolsky VM (2007) Neural network emulations for complex multidimensional geophysical mappings: applications of neural network techniques to atmospheric and oceanic satellite retrievals and numerical modelling. Rev Geophys 45:RG3009. doi:10.1029/2006RG000200
Lee S, Ryu J, Min K, Won J (2001) Proceedings of the geoscience and remote sensing symposium IGARSS ‘01. IEEE 2001 International 5:2364–2366
Mayoraz F, Cornu T, Vuillet L (1996) Using neural networks to predict slope movements. Proceedings of VII international symposium on landslides, Trondheim, June 1966, Balkema, pp 295–300
McCullagh P, Nelder JA (1989) Monographs on statistics and applied probability, vol 37. Chapman & Hall, London, p 511
Meijerink AMJ (1988) Data acquisition and data capture through terrain mapping unit. ITC J 1:23–44
Morini D, Bruni P (2004) (eds) The Regione Toscana Project of geological mapping. Case Histories and Data Acquisition. Regione Toscana special volume for the 32th IGC Congress, Florence, August 2004
Piccolo D (1998) Statistica. Il Mulino, Bologna, p 969
Soeters R, Van Westen CJ (1996) Slope instability recognition, analysis and zonation. In: Turner AK, Schuster RL (eds) Landslides. Investigation and mitigation. National Academy Press, Transportation Research Board, Special Report 247, Washington, DC, pp 129–177
Swets JA (1988) Measuring the accuracy of diagnostic systems. Science 240:1285–1293. doi:10.1126/science.3287615
Tzeng F-Y, Ma K-L (2005) Opening the black box—data driven visualization of neural networks. In: Proceedings of the 16th IEEE visualization (VIS 2005), p 49
Varnes DJ (1978) Slope movement types and processes. In: Schuster RL, Krizek RJ (eds) Landslides—analysis and control. National Academy of Sciences, Transportation Research Board, Special Report 176, Washington, DC, pp 12–33
Williams CJ, Lee SS, Fisher RA, Dickerman LH (1999) A comparison of statistical methods for prenatal screening for Down syndrome. Appl Stoch Models Data Anal 15:89–101. doi:10.1002/(SICI)1526-4025(199904/06)15:2<89::AID-ASMB366>3.0.CO;2-K
Acknowledgments
This study was supported by APAT (Italian Agency for Environmental Protection and Technical Services) and Tuscany Regional Administration funds, aimed at defining the landslide hazard in the middle–upper Serchio River valley and headed by P. R. Federici and A. Puccinelli. The authors are grateful to N. Casarosa, C. Testi, and Ilio who cooperated in surveying and building the database and to three anonymous referees whose comments and suggestions significantly improved the manuscript. A special thanks to C. Ieromazzo.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Falaschi, F., Giacomelli, F., Federici, P.R. et al. Logistic regression versus artificial neural networks: landslide susceptibility evaluation in a sample area of the Serchio River valley, Italy. Nat Hazards 50, 551–569 (2009). https://doi.org/10.1007/s11069-009-9356-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-009-9356-5