Skip to main content
SpringerLink
Log in

Using statistical learning algorithms in regional landslide susceptibility zonation with limited landslide field data

  • Published:
Journal of Mountain Science Aims and scope Submit manuscript

Abstract

Regional Landslide Susceptibility Zonation (LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statistical learning algorithms are believed to be superior to traditional statistical algorithms for their data adaptability. The aim of the paper is to evaluate how statistical learning algorithms perform on regional LSZ with limited field data. The focus is on three statistical learning algorithms, Logistic Regression (LR), Artificial Neural Networks (ANN) and Support Vector Machine (SVM). Hanzhong city, a landslide prone area in southwestern China is taken as a study case. Nine environmental factors are selected as inputs. The accuracies of the resulting LSZ maps are evaluated through landslide density analysis (LDA), receiver operating characteristic (ROC) curves and Kappa index statistics. The dependence of the algorithm on the size of field samples is examined by varying the sizes of the training set. The SVM has proven to be the most accurate and the most stable algorithm at small training set sizes and on all known landslide sizes. The accuracy of SVM shows a steadily increasing trend and reaches a high level at a small size of the training set, while accuracies of LR and ANN algorithms show distinct fluctuations. The geomorphological interpretations confirm the strength of SVM on all landslide sizes. Our results show that the strengths of SVM in generalization capability and model robustness make it an appropriate and efficient tool for regional LSZ with limited landslide field samples.

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

  • Abdallah C, Chorowicz J, Bou Kheir R, et al. (2005) Detecting major terrain parameters relating to mass movements’ occurrence using GIS, remote sensing and statistical correlations, case study Lebanon. Remote Sensing of Environment 99: 448–461.

    Article  Google Scholar 

  • Aleotti P, Chowdhurry R (1999) Landslide hazard assessment: summary review and new perspectives. Bulletin of Engineering Geology and the Environment 58: 21–44.

    Article  Google Scholar 

  • Anbalagan R (1992) Landslide susceptibility evaluation and zonation mapping in mountainous terrain. Engineering Geology 32: 269–277.

    Article  Google Scholar 

  • Bai S, Wang J, Lv G, et al. (2007) GIS-based and data drive bivariate landslide susceptibility mapping in the Three Gorge Area, China. Journal of Mountain Science 25(1): 85–92. (In Chinese).

    Google Scholar 

  • Bai SB, Wang J, Lü G-N, et al. (2010) GIS-based logistic regression for landslide susceptibility mapping of the Zhongxian segment in the Three Gorges area, China. Geomorphology 115: 23–31.

    Article  Google Scholar 

  • Balabin RM and Lomakina EI (2011) Support vector machine regression (SVR/LS-SVM)-an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data. Analyst 136: 1703–1712.

    Article  Google Scholar 

  • Bălteanu D, Chendes V, Sima M, et al. (2010) A country-wide spatial assessment of landslide susceptibility in Romania (in press). Geomorphology.

    Google Scholar 

  • Basheer IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design and application. Journal of Microbiological Methods 43: 3–31.

    Article  Google Scholar 

  • Bishop CM (1995). Neural Networks for Pattern Recognition. Oxford University Press, Oxford, UK.

    Google Scholar 

  • Brabb EE, Pampeyan EH, Bonilla M (1972) Landslide susceptibility in the San Mateo County, California, scale 1:62,500. USGS Miscellaneous Field Studies Map, MF344.

    Google Scholar 

  • Brenning A, Trombotto D (2006) Logistic regression modeling of rock glacier and glacier distribution: topographic and climatic controls in the semi-arid Andes. Geomorphology 81: 141–154.

    Article  Google Scholar 

  • Bui DT, Pradhan B, Lofman O, et al. (2012) Landslide susceptibility assessment in Vietnam using suport vector machines, decision tree, and naïve bayes models. Mathematical problems in Engineering: 1–26.

    Google Scholar 

  • Carrara A, Cardinali M, Detti R, et al. (1991) GIS techniques and statistical models in evaluating landslide hazard. Earth Surface Processes and Landforms 16: 427–445.

    Article  Google Scholar 

  • Cascini L (2008) Applicability of landslide susceptibility and hazard zoning at different scales. Engineering Geology 102: 164–177.

    Article  Google Scholar 

  • Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM transactions on Intelligent Systems and Technology 2(27): 1–27.

    Article  Google Scholar 

  • Chauhan S, Sharma M, Arora MK, et al. (2010) Landslide susceptibility zonation through ratings derived from Artificial Neural Network. International Journal of Applied Earth Observation and Geoinformation 12: 340–350.

    Article  Google Scholar 

  • Chong X, Dai FC, Xu XW, et al. (2012) GIS-based support vector machine modelling of earthquake-triggered landslide suscpetibility in the Jianjiang River watershed, China. Geomorphology 145: 70–80.

    Google Scholar 

  • Clerici A, Perego S, Tellini C, et al. (2002) A procedure for landslide susceptibility zonation by the conditional analysis method. Geomorphology 48: 349–364.

    Article  Google Scholar 

  • Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment 37: 35–46.

    Article  Google Scholar 

  • Dai FC, Lee CF, Nagi Y (2002) Landslide risk assessment and management: an overview. Engineering Geology 64: 65–87.

    Article  Google Scholar 

  • DeGraff J, Romesburg H (1980) Regional landslide-susceptibility assessment for wildland management: a matrix approach. In: Coates D, Vitek J (Eds.) Thresholds in geomorphology. George Allen and Unwin, London, UK. pp 401–414.

    Google Scholar 

  • DLR (Shaanxi) (2003) Atlas of geological hazard in Shaanxi Province (Hanzhong Fascicule). Department of Land and Resources of Shaanxi Province, Xi’an, China.

    Google Scholar 

  • Ercanoglu M, Gokceoglu C, Van Asch TWJ (2004) Landslide susceptibility zoning north of Yenice (NW Turkey) by multivariate statistical techniques. Natural Hazards 32: 1–23.

    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 

  • Fell R, Corominas J, Bonnard C, et al. (2008) Guidlines for landslide susceptibility, hazard, risk zoning for land-use planning. Engineering Geology 102: 99–111.

    Article  Google Scholar 

  • Fieldings AH, Bell JF (1997) A review of methods for the assessment of prediction errors in the conservation presence/absence methods. Environmental Conservation 24(1): 38–49.

    Article  Google Scholar 

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

    Article  Google Scholar 

  • George D, Mallery P (2000). SPSS Windows Step by Step: A Simple Guide and Reference. Allyn and Bacon, New York, NY, USA.

    Google Scholar 

  • Gong P (1996) Integrated analysis of spatial data for multiple sources: using evidential reasoning and artificial neural network techniques for geological mapping. Photogrammetric Engineering and Remote Sensing 62(5): 513–523.

    Google Scholar 

  • Gupta RP, Kanungo DP, Arora MK et al. (2008) Approaches for comparative evaluation of raster GIS-based landslide susceptibility zonation maps. International Journal of Applied Earth Observation and Geoinformation (10): 330–341.

    Google Scholar 

  • Haykin S (1998) Neural Networks: A Comprehensive Foundation. Prentice Hall, London, UK.

    Google Scholar 

  • Holec J, Bednarik M, Sabo M, et al. (2013) A small-scale landslide susceptibility assessment for the territory of Western Carpathians. Natural Hazards 69(1): 1081–1107.

    Article  Google Scholar 

  • Jade S, Sarkar S (1993) Statistical models for slope instability classification. Engineering Geology 36: 91–98.

    Article  Google Scholar 

  • Kanungo DP, Arora MK, Starker S, et al. (2006) A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas. Engineering Geology 85(3–4): 347–366.

    Article  Google Scholar 

  • Lan HX, Zhou CH, Wang LJ, et al. (2004) Landslide hazard spatial analysis and prediction using GIS in the Xiaojiang watershed, Yunnan, China. Engineering Geology 76: 109–128.

    Article  Google Scholar 

  • Lee S, Ryu J, Min K, et al. (2003) Landslide susceptibility analysis using GIS and artificial neural network. Earth Surface Processes and Landforms 28: 1361–1376.

    Article  Google Scholar 

  • Lillesand TM, Kiefer RW, Chipman JR (2008) Remote Sensing and Image Interpretation, Sixth Edition. John Wiley & Sons Inc., Beijing, China.

    Google Scholar 

  • Liu MG, Ed. (1997) Atlas of Physical Geography in China. SinoMaps Press, Beijing, China.

    Google Scholar 

  • Ma LF, Ed. (2002) Atlas of China Geology. Geology Publishing House, Beijing, China.

    Google Scholar 

  • Marjanović M, Kovačević M, Bajat B, et al. (2011) Landslide susceptibility assessment using SVM machine learning algorithm. Engineering Geology 123: 225–234.

    Article  Google Scholar 

  • Micheletti N, Foresti L, Robert S, et al. (2013) Machine learning feature selection methods for landslide susceptibility mapping. Mathematical Geosciences 46: 33–57.

    Article  Google Scholar 

  • Monserud RA, Leemans R (1992) Comparing global vegetation maps with the Kappa statistics. Ecological Modelling 62: 275–293.

    Article  Google Scholar 

  • Nefeslioglu HA, Gokcegolu C, Sonmes 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. Engineering Geology 97: 171–191.

    Article  Google Scholar 

  • Pradhan B (2010) Remote sensing and GIS-based landslide hazard analysis and cross-validation using multivariate logistic regression model on three test areas in Malaysia. Advances in Space Research 45: 1244–1256.

    Article  Google Scholar 

  • Pradhan B (2013) A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Computers & Geosciences 51: 350–365.

    Article  Google Scholar 

  • Pradhan B, Lee S (2007) Utilization of optical remote sensing data and GIS tools for regional landslide hazard analysis using an artificial neural network model. Earth Science Frontiers 14(6): 143–152.

    Article  Google Scholar 

  • Pradhan B, Lee S (2010) Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling. Environmental Modelling & Software 25: 747–759.

    Article  Google Scholar 

  • Pradhan B, Lee S, Buchroithner MF (2010) A GIS-based backpropagation neural network model and its cross-application and validation for landslide susceptibility analysis. Computers, Environment and Urban Systems (34): 216–235.

    Google Scholar 

  • Rossi M, Guzzetti F, Reichenbach P, et al. (2010) Optimal landslide susceptibility zonation based on multiple forecasts. Geomorphology 114(3): 129–142.

    Article  Google Scholar 

  • Saha AK, Gupta RP, Starker I, et al. (2005) An approach for GIS based statistical landslide susceptibility zonation-with a case study in the Himalayas. Landslides 2: 61–69.

    Article  Google Scholar 

  • Samui P, Kothari DP (2010) Utilization of a least square support vector machine (LSSVM) for slope stability analysis. Scientia Iranica 18(1): 53–58.

    Article  Google Scholar 

  • Tax D, Duin E (1999) Support vector domain description. Pattern Recognition Letter 20: 1191–1199.

    Article  Google Scholar 

  • Vapnik VN (1995). The Nature of Statistical Learning Theory. Springer, New York, NY, USA.

    Book  Google Scholar 

  • Wang H, Liu G, Xu W, et al. (2005) GIS-based landslide hazard assessment: an overview. Progress in Physical Geography 29: 548–567.

    Article  Google Scholar 

  • Wang WD, Cui CM, Du XG (2009) Landslides susceptibility mapping in Guizhou province based on fuzzy theory. Mining Science and Technology (19): 399–404.

    Google Scholar 

  • Yalcin A, ReiS S, Aydinoglu AC, et al. (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: 274–287.

    Article  Google Scholar 

  • Yao X, Tham LG, Dai FC (2008) Landslide susceptibility mapping based on Support Vector Machine: a case study on natural slopes for Hongkong, China. Geomorphology 101: 572–582.

    Article  Google Scholar 

  • Yesilnacara E, Topal T (2005) Landslide susceptibility mapping: A comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey). Engineering Geology 79: 251–266.

    Article  Google Scholar 

  • Yilmaz I (2009) Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat-Turkey). Computers & Geosciences 35: 1125–1138.

    Article  Google Scholar 

  • Yilmaz I (2010a) Comparison of landslide susceptibility mapping methodologies for Koyulhisar, Turkey: conditional probability, logistic regression, artificial neural networks, and support vector machine. Environmental Earth Sciences 61: 821–836.

    Article  Google Scholar 

  • Yilmaz I (2010b) The effect of the sampling strategies on the landslide susceptibility mapping by conditional probability and artificial neural networks, Environmental Earth Science 60(3): 505–519.

    Article  Google Scholar 

  • Yilmaz I, Keskin I (2009) GIS based statistical and physical approaches to landslide susceptibility mapping (Sebinkarahisar, Turkey). Bulletin of Engineering Geology and the Environment 68(4): 459–471.

    Article  Google Scholar 

  • Zhang WB, Jin SL, Eds. (1995). Atlas of China. SinoMaps Press, Beijing, China.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. State Key Laboratory of Remote Sensing Science, School of Geography, Beijing Normal University, Beijing, 100875, China

    Yi-ting Wang

  2. National Marine Data & Information Service, Tianjin, 300171, China

    Yi-ting Wang

  3. Institute for Biodiversity and Ecosystem Dynamics, University of Amsterdam, Science Park 904, 1098 XH, Amsterdam, the Netherlands

    Arie Christoffel Seijmonsbergen & Willem Bouten

  4. Institute of Remote Sensing and GIS, Chengdu University of Technology, Chengdu, 610059, China

    Qing-tao Chen

Authors
  1. Yi-ting Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arie Christoffel Seijmonsbergen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Willem Bouten
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qing-tao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yi-ting Wang.

Additional information

http://orcid.org/0000-0002-2498-3123

http://orcid.org/0000-0002-7454-7637

http://orcid.org/0000-0002-5250-8872

http://orcid.org/0000-0003-3628-1441

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Yt., Seijmonsbergen, A.C., Bouten, W. et al. Using statistical learning algorithms in regional landslide susceptibility zonation with limited landslide field data. J. Mt. Sci. 12, 268–288 (2015). https://doi.org/10.1007/s11629-014-3134-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11629-014-3134-x

Keywords

Search

Navigation