Skip to main content

Random forest and artificial neural networks in landslide susceptibility modeling: a case study of the Fão River Basin, Southern Brazil

Abstract

Empirical models based on machine learning methods have been used for landslide susceptibility mapping. The most accurate model is usually chosen to generate the final map. This paper demonstrates the importance of analyzing the spatial pattern of susceptibility maps, since models with similar performance can produce different output values. The relevance of terrain attributes and the sensitivity of models to input variables are also discussed. The applications of random forest (RF) and artificial neural network (ANN) models to the identification of landslide susceptible areas in the Fão River Basin, Southern Brazil, were evaluated and compared. The following have been included in the methodology: (1) the extraction of predictive attributes (e.g., slope, aspect, curvatures, valley depth) from a digital elevation model; (2) the organization of a landslide scar inventory; (3) the calibration and validation procedures of the models; (4) the analysis of model performance according to accuracy (area under the receiver operating characteristic curve) and parsimony (Akaike Information Criterion); (5) the reclassification of maps into susceptibility categories. All model configurations resulted in an accuracy above 0.9, demonstrating the ability of both techniques in landslide susceptibility mapping. The RF model stood out in this respect, recording the highest accuracy index among all tested configurations (0.949). The ANN model was more parsimonious, obtaining an accuracy of 0.925 with a much smaller number of internal connections. Thus, even with both having high and equivalent accuracy indexes, the models can establish different relationships between the input and the output susceptibility indexes, resulting in various possible landslide occurrence scenarios. These differences, together with the difficulty in defining which model presents more coherent results, reinforce the possibility of extracting spatial statistics, considering multiple configurations of models that combine accuracy and parsimony, in landslide susceptibility mapping.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

References

  • Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Control 19(6):716–723. https://doi.org/10.1109/tac.1974.1100705

    Article  Google Scholar 

  • Beven KJ, Kirkby MJ (1979) A physically based, variable contributing area model of basin hydrology/Un modèle à base physique de zone d’appel variable de l’hydrologie du bassin versant. Hydrol Sci B 24(1):43–69. https://doi.org/10.1080/02626667909491834

    Article  Google Scholar 

  • Bonham-Carter GF (1994) Geographic information system for geoscientists: modelling with GIS. Pergamon, Oxford, p 398

    Google Scholar 

  • BRASIL (2016) Terceira Comunicação Nacional do Brasil à Convenção-Quadro das Nações Unidas sobre Mudança do Clima – Sumário Executivo. Ministério da Ciência, Tecnologia e Inovação, Brasília

    Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/a:1010933404324

    Article  Google Scholar 

  • Bui DT, Tuan TA, Klempe H, Pradhan B, Revhaug I (2016) 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 13(2):361–378. https://doi.org/10.1007/s10346-015-0557-6

    Article  Google Scholar 

  • Bulut F, Boynukalin S, Tarhan F, Ataoglu E (2000) Reliability of isopleth maps. Bull Eng Geol Environ 58:95–98

    Article  Google Scholar 

  • Carrara A (1983) Multivariate models for landslide hazard evolution. Math Geol 15:403–427

    Article  Google Scholar 

  • Chalkias C, Kalogirou S, Ferentinou M (2014) Landslide susceptibility, Peloponnese Peninsula in South Greece. J Maps 10(2):211–222. https://doi.org/10.1080/17445647.2014.884022

    Article  Google Scholar 

  • Chen W, Xie X, Wang J, Pradhan B, Hong H, Bui DT, Ma J (2017) A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility. CATENA 151:147–160

    Article  Google Scholar 

  • Cheng G, Guo L, Zhao T, Han J, Li H, Fang J (2013) Automatic landslide detection from remote-sensing imagery using a scene classification method based on BoVW and pLSA. Int J Remote Sens 34(1):45–59. https://doi.org/10.1080/01431161.2012.705443

    Article  Google Scholar 

  • Coe JA, Michael JA, Crovelli RA, Savage WA (2000) Preliminary map showing landslides densities, mean recurrence intervals, and exceedance probabilities as determined from historic records. Open-file report 00-303. USGS, Seattle

  • Colesanti C, Wasowski J (2006) Investigating landslides with spaceborne synthetic aperture radar (SAR) interferometry. Eng Geol 88:173–199

    Article  Google Scholar 

  • Conforti M, Pascale S, Robustelli G, Sdao F (2014) Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy). CATENA 113:236–250. https://doi.org/10.1016/j.catena.2013.08.006

    Article  Google Scholar 

  • Corominas J, Van Westen CJ, Frattini P, Cascini L, Malet J-P, Fotopoulou S, Catani F, Van Den Eeckhaut M, Mavrouli O, Agliardi F, Pitilakis K, Winter MG, Pastor M, Ferlisi S, Tofani V, Hervás J, Smith JT (2014) Recommendations for the quantitative analysis of landslide risk. Bull Eng Geol Environ 73:209–263. https://doi.org/10.1007/s10064-013-0538-8

    Article  Google Scholar 

  • CRED - Centre for Research on the Epidemiology of Disasters (2017) The international disaster database. http://www.emdat.be/database. Accessed 29 June 2018

  • Crozier MJ (1989) Landslides: causes, consequences & environment. Routledge, Croom Helm, London

    Google Scholar 

  • Crozier MJ (2005) Multiple occurrence regional landslide events in New Zealand: hazard management issues. Landslides 2:247–256

    Article  Google Scholar 

  • Dai FC, Lee CF (2002) Landslide characteristics and slope instability modeling using GIS, Lantau Island, Hong Kong. Geomorphology 42(3–4):213–228. https://doi.org/10.1016/s0169-555x(01)00087-3

    Article  Google Scholar 

  • Dietrich WE, Reiss R, Hsu ML, Montgomery DR (1995) A process based model for colluvial soil depth and shallow landsliding using digital elevation data. Hydrol Process 9:383–400

    Article  Google Scholar 

  • Ermini L, Catani F, Casagli N (2005) Artificial neural networks applied to landslide susceptibility assessment. Geomorphology 66:327–343

    Article  Google Scholar 

  • Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874. https://doi.org/10.1016/j.patrec.2005.10.010

    Article  Google Scholar 

  • Fernandes NF, Guimarães RF, Gomes RAT, Vieira BC, Montgomery DR, Greenberg H (2001) Condicionantes Geomorfológicos dos Deslizamentos nas Encostas: Avaliação de Metodologias e Aplicação de Modelo de Previsão de Áreas Susceptíveis. Rev Bras Geomorfologia 2(1):51–71

    Google Scholar 

  • Fernández T, Irigaray C, Hamdouni RE, Chacón J (2003) Methodology for landslide susceptibility mapping by means of a GIS. Application to the Contraviesa Area (Granada, Spain). Nat Hazards 30(3):297–308. https://doi.org/10.1023/b:nhaz.0000007092.51910.3f

    Article  Google Scholar 

  • Flores T, Oliveira GG (2017) Utilização de dados sub-horários de precipitação para elaboração de equação IDF para a Região do Vale do Taquari - RS. 2° Congresso de Engenharia Ambiental do Sul do Brasil. Editora UDESC, Lajes

  • Frattini P, Crosta G, Carrara A (2010) Techniques for evaluating the performance of landslide susceptibility models. Eng Geol 111(1–4):62–72

    Article  Google Scholar 

  • Gitirana Jr G, Santos M, Fredlund M (2008) Three-dimensional slope stability model using finite element stress analysis. In: GeoCongress 2008, NewOrleans, LA, USA, 9–12 March 2008, pp 191–198

  • 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

    Article  Google Scholar 

  • Gomez H, Kavzoglu T (2005) Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela. Eng Geol 78(1–2):11–27

    Article  Google Scholar 

  • Gorsevski PV, Gessler P, Foltz RB (2000) Spatial prediction of landslide hazard using discriminant analysis and GIS. In: GIS in the Rockies 2000 Conference and Workshop: Applications for the 21st Century, Denver, CO, USA, 25–27 Sept 2000

  • 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

    Article  Google Scholar 

  • Guha-Sapir D, Hoyois PH, Below R (2016) Annual disaster statistical review 2016: The numbers and trends. CRED, Brussels

    Google Scholar 

  • Günther A (2003) SLOPEMAP: programs for automated mapping of geometrical and kinematical properties of hard rock hill slopes. Comput Geosci 29:865–875

    Article  Google Scholar 

  • Guzzetti F, Cardinali M, Reichenbach P, Carrara A (2000) Comparing landslide maps: a case study in the upper Tiber River Basin, central Italy. Environ Manag 25(3):247–363

    Article  Google Scholar 

  • He B, Sassa K, Nagai O, Takara K (2014) Simulation of a rapid and long-travelling landslide using 2D-RAPID and LS-RAPID 3D models. Landslide science for a safer geoenvironment. Springer, Berlin, pp 479–484

    Google Scholar 

  • Hearn GJ (1995) Landslide and erosion hazard mapping at Ok Tedi copper mine, Papua New Guinea. Q J Eng Geol Hydroge 28(1):47–60. https://doi.org/10.1144/gsl.qjegh.1995.028.p1.05

    Article  Google Scholar 

  • Highland LM, Bobrowsky P (2008) The landslide handbook—a guide to understanding landslides. U.S. Geological Survey Circular 1325, Reston

  • IPCC (2010) Summary for policymakers. In: Managing the risks of extreme events and disasters to advance climate change adaptation. A special report of working groups I and II of the intergovernmental panel on climate change. Cambridge University Press, Cambridge and New York

  • Jaiswal P, Van Westen CJ (2009) Estimating temporal probability for landslide initiation along transportation routes based on rainfall thresholds. Geomorphology 112:96–105

    Article  Google Scholar 

  • Jenson SK, Domingue JO (1988) Extracting topographic structure from digital elevation data for geographic information-system analysis. Photogramm Eng Rem S 54(11):1593–1600

    Google Scholar 

  • Kanungo DP, Arora MK, Sarkar S, Gupta RP (2006) A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas. Eng Geol 85(3–4):347–366

    Article  Google Scholar 

  • Karpatne A, Ebert-Uphoff I, Ravela S, Babaie HA, Kumar V (2018) Machine learning for the geosciences: challenges and opportunities. IEEE Trans Knowl Data Eng 31(8):1544–1554

    Article  Google Scholar 

  • Keefer DK (2002) Investigating landslides caused by earthquakes—a historical review. Surv Geophys 23:473–510

    Article  Google Scholar 

  • Kim JC, Lee S, Jung HS, Lee S (2018) Landslide susceptibility mapping using random forest and boosted tree models in Pyeong-Chang, Korea. Geocarto Int 33(9):1000–1015. https://doi.org/10.1080/10106049.2017.1323964

    Article  Google Scholar 

  • Lara AA, Marques EAG, Almeida LCR (1997) Mapeamento de risco de acidentes associados a escorregamentos - Morro da Serrinha, Rio de Janeiro, Brasil. 2ª COBRAE. ABMS, ABGE e ISSMGE, Rio de Janeiro

  • Lary DJ, Alavi AH, Gandomi AH, Walker AL (2016) Machine learning in geosciences and remote sensing. Geosci Front 7(1):3–10

    Article  Google Scholar 

  • Lazzari M, Gioia D, Anzidei B (2018) Landslide inventory of the Basilicata region (Southern Italy). J Maps 14(2):348–356. https://doi.org/10.1080/17445647.2018.1475309

    Article  Google Scholar 

  • Lee S (2005) Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data. Int J Remote Sens 26(7):1477–1491

    Article  Google Scholar 

  • Lee S, Ryu J-H, Won J-S, Park H-J (2004) Determination and application of the weights for landslide susceptibility mapping using an artificial neural network. Eng Geol 71(3–4):289–302

    Article  Google Scholar 

  • Melchiorre C, Matteucci M, Azzoni A, Zanchi A (2008) Artificial neural networks and cluster analysis in landslide susceptibility zonation. Geomorphology 94(3–4):379–400. https://doi.org/10.1016/j.geomorph.2006.10.035

    Article  Google Scholar 

  • Meten M, PrakashBhandary N, Yatabe R (2015) Effect of landslide factor combinations on the prediction accuracy of landslide susceptibility maps in the Blue Nile Gorge of Central Ethiopia. Geoenviron Disasters 2(1):9. https://doi.org/10.1186/s40677-015-0016-7

    Article  Google Scholar 

  • Michel GP, Kobiyama M, Goerl RF (2014) Comparative analysis of SHALSTAB and SINMAP for landslide susceptibility mapping in the Cunha River basin, southern Brazil. J Soils Sediments 14(7):1266–1277. https://doi.org/10.1007/s11368-014-0886-4

    Article  Google Scholar 

  • Micheletti N, Foresti L, Robert S, Leuenberger M, Pedrazzini A, Jaboyedoff M, Kanevski M (2014) Machine learning feature selection methods for landslide susceptibility mapping. Math Geosci 46(1):33–57

    Article  Google Scholar 

  • Möller M, Koschitzki T, Hartmann KJ, Jahn R (2012) Plausibility test of conceptual soil maps using relief parameters. CATENA 88(1):57–67. https://doi.org/10.1016/j.catena.2011.08.002

    Article  Google Scholar 

  • NASA (2013) NASA shuttle radar topography mission United States 1 arc second. Version 3. NASA EOSDIS land processes DAAC, USGS earth resources observation and science (EROS) Center, Sioux Falls, South Dakota. https://lpdaac.usgs.gov. Accessed 15 July 2017

  • Ohlmacher GC, Davis JC (2003) Using multiple logistic regression and GIS technology to predict landslide hazard in northeast Kansas. USA Eng Geol 69(33):331–343

    Article  Google Scholar 

  • Oliveira GG, Pedrollo OC, Castro NM (2015) Simplifying artificial neural network models of river basin behaviour by an automated procedure for input variable selection. Eng Appl Artif Intel 40:47–61. https://doi.org/10.1016/j.engappai.2015.01.001

    Article  Google Scholar 

  • Pascale S, Parisi S, Mancini A, Schiattarella M, Conforti M, Sole A, Murgante B, Sdao F (2013) Landslide susceptibility mapping using artificial neural network in the urban area of Senise and San Costantino Albanese (Basilicata, Southern Italy). International conference on computational science and its applications. Springer, Berlin, pp 473–488. https://doi.org/10.1007/978-3-642-39649-6_34

  • Reid LM, Page MJ (2003) Magnitude and frequency of landsliding in a large New Zealand catchment. Geomorphology 49:71–88

    Article  Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536. https://doi.org/10.1038/323533a0

    Article  Google Scholar 

  • Samia J, Temme A, Bregt A, Wallinga J, Guzzetti F, Ardizzone F, Rossi M (2017) Characterization and quantification of path dependency in landslide susceptibility. Geomorphology 292:16–24. https://doi.org/10.1016/j.geomorph.2017.04.039

    Article  Google Scholar 

  • Scaioni M, Longoni L, Melillo V, Papini M, Scaioni M, Longoni L, Melillo V, Papini M (2014) Remote sensing for landslide investigations: an overview of recent achievements and perspectives. Remote Sens 6(10):9600–9652. https://doi.org/10.3390/rs6109600

    Article  Google Scholar 

  • Simoni S, Zanotti F, Bertoldi G, Rigon R (2008) Modelling the probability of occurrence of shallow landslides and channelized debris flows using GEOtop-FS. Hydrol Process 22:532–545

    Article  Google Scholar 

  • Soeters R, Van Westen CJ (1996) Slope instability recognition, analysis and zonation. In: Turner AK, Schuster RL (eds) Landslides investigation and mitigation. TRB special report 247. National Academy Press, Washington, DC, pp 129–177

    Google Scholar 

  • Squarzoni C, Delacourt C, Allemand P (2003) Nine years of spatial and temporal evolution of the La Vallette landslide observed by SAR interferometry. Eng Geol 68:53–66

    Article  Google Scholar 

  • Stead D, Eberhardt E, Coggan J, Benko B (2001) Advanced numerical techniques in rock slope stability analysis: applications and limitations. In: LANDSLIDES—causes, impacts and countermeasures, Davos, Switzerland, 17–21 June 2001, pp 615–624

  • Suzen ML, Doyuran V (2004) Data driven bivariate landslide susceptibility assessment using geographical information systems: a method and application to Asarsuyu catchment. Turk Eng Geol 71:303–321

    Article  Google Scholar 

  • Tseng CM, Lin CW, Fontana GD, Tarolli P (2015) The topographic signature of a major typhoon. Earth Surf Proc Land 40(8):1129–1136. https://doi.org/10.1002/esp.3708

    Article  Google Scholar 

  • Valadão P, Gaspar JL, Queiroz G, Ferreira T (2002) Landslides density map of S Miguel Island, Azores archipelago. Nat Hazard Earth Syst Sci 2:51–56

    Article  Google Scholar 

  • Van Westen CJ (1993) Application of geographic information systems to landslide hazard zonation. Ph.D. dissertation. ITC publ. no. 15. ITC, Enschede, p 245

  • Widrow B, Hoff ME (1960) Adaptive Switching Circuits. IRE WESCON Convention Record, New York, pp 96–104

    Book  Google Scholar 

  • Wieczorek GF (1984) Preparing a detailed landslide-inventory map for hazard evaluation and reduction. Bull As Eng Geol 21(3):337–342

    Google Scholar 

  • Youssef AM, Pourghasemi HR, Pourtaghi ZS, Al-Katheeri MM (2016) Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia. Landslides 13(5):839–856. https://doi.org/10.1007/s10346-015-0614-1

    Article  Google Scholar 

  • Zare M, Pourghasemi HR, Vafakhah M, Pradhan B (2013) Landslide susceptibility mapping at Vaz Watershed (Iran) using an artificial neural network model: a comparison between multilayer perceptron (MLP) and radial basic function (RBF) algorithms. Arab J Geosci 6(8):2873–2888. https://doi.org/10.1007/s12517-012-0610-x

    Article  Google Scholar 

  • Zhang K, Wu X, Niu R, Yang K, Zhao L (2017) The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China. Environ Earth Sci 76(11):405. https://doi.org/10.1007/s12665-017-6731-5

    Article  Google Scholar 

Download references

Acknowledgements

Special thanks go to the Research Support Foundation of Rio Grande do Sul State – FAPERGS for granting financial support to the first author (process 17/2551-0000894-4, Edict 01/2017) (newly awarded doctorate).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Guilherme Garcia de Oliveira.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

de Oliveira, G.G., Ruiz, L.F.C., Guasselli, L.A. et al. Random forest and artificial neural networks in landslide susceptibility modeling: a case study of the Fão River Basin, Southern Brazil. Nat Hazards 99, 1049–1073 (2019). https://doi.org/10.1007/s11069-019-03795-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11069-019-03795-x

Keywords

  • Digital elevation model
  • Machine learning
  • Predictive attributes
  • Natural disasters
  • Landslide susceptibility mapping