Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Landslide risk zoning using support vector machine algorithm

  • Vahed Ghiasi (Faculty of Civil Engineering, Malayer University) ;
  • Nur Irfah Mohd Pauzi (Department of Civil Engineering, College of Engineering, Institute of Energy Infrastructure, Universiti Tenaga Nasional) ;
  • Shahab Karimi (Department of Civil Engineering, Faculty of Engineering, Malayer University) ;
  • Mahyar Yousefi (Faculty of Engineering, Malayer University)
  • Received : 2022.08.08
  • Accepted : 2023.06.27
  • Published : 2023.08.10
⟨ Previous Next ⟩

Abstract

Landslides are one of the most dangerous phenomena and natural disasters. Landslides cause many human and financial losses in most parts of the world, especially in mountainous areas. Due to the climatic conditions and topography, people in the northern and western regions of Iran live with the risk of landslides. One of the measures that can effectively reduce the possible risks of landslides and their crisis management is to identify potential areas prone to landslides through multi-criteria modeling approach. This research aims to model landslide potential area in the Oshvand watershed using a support vector machine algorithm. For this purpose, evidence maps of seven effective factors in the occurrence of landslides namely slope, slope direction, height, distance from the fault, the density of waterways, rainfall, and geology, were prepared. The maps were generated and weighted using the continuous fuzzification method and logistic functions, resulting values in zero and one range as weights. The weighted maps were then combined using the support vector machine algorithm. For the training and testing of the machine, 81 slippery ground points and 81 non-sliding points were used. Modeling procedure was done using four linear, polynomial, Gaussian, and sigmoid kernels. The efficiency of each model was compared using the area under the receiver operating characteristic curve; the root means square error, and the correlation coefficient . Finally, the landslide potential model that was obtained using Gaussian's kernel was selected as the best one for susceptibility of landslides in the Oshvand watershed.

Keywords

Acknowledgement

The research described in this paper was financially supported by Malayer University, Iran.

References

  1. Abedini, M. (2015), Tectonic geomorphology. The compilation, second volume, first edition, Mohaghegh Ardabili University Publications, 227.
  2. Abedini, M., Raushit, S. and Fathi, M.H. (2017), "Identifying and classifying the types of landslides using spectral and spatial features with an object-oriented approach (Nasir Abad to Sattarkhan Ahar Dam)", J. Geography Planning, 22(66). 178-205.
  3. Basak, D., Pal, S. and Patranabis, D.C. (2007), "Support vector regression", Neural Inf. Process., 11, 203-225.
  4. Boulfoul, K., Hammoud, F. and Abbeche, K. (2020), "Numerical study on the optimal position of a pile for stabilization purpose of a slope", Geomech. Eng., 21(5), 401-411 https://doi.org/10.12989/gae.2020.21.5.401.
  5. Chalkias, C.H., Ferentinou, M. and Polykretis, C.H. (2014), "GIS-based landslide susceptibility mapping on the Peloponnese Peninsula, Greece", Geosci., 4(3), 176-190. https://doi.org/10.3390/geosciences4030176.
  6. Chauhan, S., Sharma, M., Arora, M.K. and Gupta, N.K. (2010), "Landslide susceptibility zonation through ratings derived from the artificial neural network", Int. J. Appl. Earth Observation Geoinform., 12, 340-350. https://doi.org/10.1016/j.jag.2010.04.006.
  7. Cristianini, N. and Shawe-Taylor, J. (2000), "An introduction to support vector machines and other kernel-based learning methods", Cambridge University Press, 256. https://doi.org/10.1017/CBO9780511801389.013.
  8. Cruden, D.M. and Varnes, D.J. (1996), Landslide types and processes. In: Turner A.K. and Schuster, R.L. Landslides, Investigation and Mitigation, Transportation Research Board Special Report, 247, 36-75
  9. Dahal, R.K., Hasegava, S.H., Nonoura, A., Yamanka, M., Dhakal, S. and Pauudyal, P. (2008), "Predictive modeling of rainfall-induced landslide hazard in the lesser Himalaya of Nepal based on weights of evidence", Geomorphology, 102(3-4), 496-510. https://doi.org/10.1016/j.geomorph.2008.05.041.
  10. Dai, F.C. and Lee, C.F. (2001), "Terrain-based mapping of landslide susceptibility using a geographical information system: a case study", Can. Geotech. J., 38, 911-923. https://doi.org/10.1139/t01-021.
  11. Dehnavi, A., Aghdam, I.N., Pradhan, B. andV arzandeh, M.H.M. (2015), A new hybrid model usi the stepwise weight assessment ratio analysis (SWARA) technique and adaptive neuro-fuz inference system (ANFIS) for regional landslide hazard assessment in Iran Catena, 135, 122-148. https://doi.org/10.1016/j.catena.2015.07.020.
  12. Dibike, Y.B.,Velikov, S., Solomatine, D. and Abbot, M.B. (2001), "Model induction with support vector machines-introduction and applications", J. Comput. Civ. Eng. ASCE, 15(3), 208-216. https://doi.org/10.1061/(ASCE)0887-3801(2001)15:3(208).
  13. Erasto, P. (2001), Support vector machines-backgrounds and practice. BSc Thesis, University of Helsinki, Faculty of Science, Rolf Nevanlinna Institute, Helsinki, Finland. 78.
  14. Ermini, L., Catani, F. and Casagli, N. (2005), "Artificial neural networks were applied to landslide susceptibility assessment", Geomorphology, 66, 327-343. https://doi.org/10.1016/j.geomorph.2004.09.025.
  15. Feng, Y., Jiang, L., Zhou, W., Lai, Z. and Chai, X. ( 2019), "An analytical solution to the mapping relationship between bridge structures vertical deformation and rail deformation of high-speed railway", Steel Compos. Struct., 33(2), 209-224. https://doi.org/10.12989/scs.2019.33.2.209.
  16. Ghanavati, E. (2011), "Landslide hazard zonation in Jajrud Basin Using Hierarchical Analysis Method", J. Appl. Res. Geograph. Sci., 20, 51- 68.
  17. Ghannadpour S.A.M. and Mehrparvar M. (2020), "Nonlinear and post-buckling responses of FGM plates with oblique elliptical cutouts using plate assembly technique", Steel Compos. Struct., 34(2), 227-239. https://doi.org/10.12989/scs.2020.34.2.227.
  18. Ghasemian, B., Abedini, M. and Raushi, S. (2016), "Landslide susceptibility evaluation using support vector machine algorithm. (Case study: Kamiyaran city, Kurdistan province)", Quantitative Geomorph. Res., 6(3), 15-36.
  19. Ghiasi, V., Ghasemi, S.A.R. and Yousefi, M. (2021), "Landslide susceptibility mapping through continuous fuzzification and geometric average multi-criteria decision-making approaches", Nat. Hazards, 107, 795-808. https://doi.org/10.1007/s11069-021-04606-y.
  20. Ghiasi, V., Mirzaei, S. and Yousefi, M. (2020), "Development of Prediction - Area charts to improve the output of landslide potential models", MCEJ, 20(6), 127-131. http://mcej.modares.ac.ir/article-16-39163-en.html.
  21. Hashemi, S.H., Karami J., Amini J. and Alimohamadi, A. (2010), "Zoning areas susceptible to landslides using Fuzzy Topsis algorithms and GIS (Case Study: Lorestan Province)", J. Remote Sens. GIS, 8, 23- 36.
  22. Hong, H., Pradhan, B., Xu, C. and Bui, D.T. (2015), "Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression", Alternating decision tree and support vector machines Catena, 133, 266-281. https://doi.org/10.1016/J.CATENA.2015.05.019.
  23. Hossein Zadeh, M M., Tharvati, M.R., Mansouri, A., Mirbagheri, B. and Khazri, S. (2009), "Zoning the risk of mass movements using logistic regression model", Sanandaj-Dehgolan route . Iranian Geology Quarterly, 11(3), 27-37.
  24. Hosseini, N. (2015), Application of the data-driven index homopology method in landslide risk modeling. Master's thesis, Malayer University, Iran.
  25. Ilderami, A., Nouri, H., Mohammadi, M. and Mousavi, M. (2016), "Investigating effective factors and landslide risk zoning using surface density model, hierarchical analysis (AHP), and logistic regression in Oshvand watershed", Environ. Erosion Res., 7, 1-23.
  26. Kamranzad, F., Afshar, E., Mojerab, M. and Memarian, H. (2013), "Landslide risk zoning in Tehran province using data-driven methods and hierarchical analysis", J. Earth Sci., 25(97). 101-114. https://doi.org/10.22071/gsj.2015.41372.
  27. Karam, A. (2004), "Application of Linear mixed models in landslide occurrence potential zonation (Case Study: Sarkhon area in Charmahal and Bakhteyari Province)", J. Geography Development, 4, 131-146. https://doi.org/10.22111/GDIJ.2004.3888.
  28. Karami, F., Bayati Khatibi, M., Khairizadeh, M. and Mokhtari Asl, A. (2018), "Evaluating the effectiveness of the support vector machine algorithm in landslide susceptibility zoning of Aharchai catchment area", Geography Environ. Hazards, 32, 1-17. https://doi.org/10.22067/GEO.V8I4.83263.
  29. Kornejadi, I. and Pourqasmi, H. (2015), "Landslide susceptibility assessment using data-mining models (case study: Chelchai watershed)", Watershed Eng. Management Scientific-Res. J., 11(1), 28-42. https://doi.org/10.22092/ijwmse.2019.118436.
  30. Lee, S., Hong, S.M. and Jung, H.S. (2017), "A support vector machine for landslide susceptibility mapping in Gangwon Provine, Korea", Susceptibility, 9(48), 1-15. https://doi.org/10.3390/su9010048.
  31. Lin, K.Y., Lin, T.K. and Lin, Y. (2020), "Real-time seismic structural response prediction system based on support vector machine", Earthq. Struct., 18(2), 163-170. https://doi.org/10.12989/eas.2020.18.2.163
  32. Mafian, S., Huat, B.B.K. and Ghiasi, V. (2009), "Evaluation on root theories and root strength properties in slope stability", Eur. J. Scientific Res., 30(4), 594-607.
  33. Malamud, B.D., Turcotte, D.L., Guzzeti, F. and Reicenbach, P. (2004), "Landslide inventories and their statistical properties", Earth Surf. Process, 29, 687-711. https://doi.org/10.1002/esp.1064.
  34. Nojavan, M., Shahzeidi, S.S., davudi, M. and Aminroaya, H. (2019), "Zonation of landslide risk using fuzzy and AHP model (Case Study: Komeh Basin)", Isfahan Province. Quantitative Geomorphological Research, 7(4), 142-159.
  35. Ost, L., Van-Den, E.M., Poesen, J. and Vanmaercke-Gottigny, M. C. (2003), "Characteristics and spatial distribution of large landslides in the Flemish Ardennes (Belgium)", Zeitschrift fur Geomorphologie N.F., 47(3), 329-350. https://doi.org/10.1127/zfg/47/2003/329.
  36. Pavel, M., Nelson, J.D. and Fannin, R.J. (2011), "An analysis of landslide susceptibility zonation using a subjective geomorphic mapping and existing landslides", Comput. Geosci., 37(4), 554-566. https://doi.org/10.1016/j.cageo.2010.10.006.
  37. Peng, L., Ruiqing, N., Bo, H., Xueling, W., Yannan, Z. and Runqing, Y. (2014), "Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China", Geomorphology, 204, 287-301. https://doi.org/10.1016/J.GEOMORPH.2013.08.013.
  38. Pontius, R.G. and Schneider, L.C. (2001), "Land-cover change model validation by an ROC method for the Ipswich watershed, Massachusetts, USA. Agriculture", Ecosyst. Environ., 85(1), 239-248. https://doi.org/10.1016/S0167-8809(01)00187-6.
  39. Pourghasemi, H.R., Jirandeh, A.G., Pradhan, B., Xu, C. and Gokceoglu, C. (2013), "Landslide susceptibility mapping using support vector machine and GIS at the Golestan Province, Iran", J. Earth Syst. Sci., 122(2), 349-369. https://doi.org/10.1007/s12040-013-0282-2.
  40. Samui, P. (2008), "Support vector machine applied to the settlement of shallow foundations on cohesionless soils", J. Comput. Geotech., 35, 419-427. https://doi.org/10.1016/j.compgeo.2007.06.014.
  41. Shokri, S., Mohammad Taqi., S. and Mehdi, A.M. (2012), "Presenting a combined method of data preprocessing in the regression vector machine to predict the quality of refined diesel", Oil Res., 23(75). 116-102.
  42. Sidle, RC. and Ochiai, H. (2006), "Landslides: Processes, prediction, and land use", Water Resour. Monograph, 18.
  43. Surmiri, A., Nayebi, A., Rokhgireh, H. and Varvani-Farahani, A. (2020), "Anisotropic continuum damage analysis of thin-walled pressure vessels under cyclic thermo-mechanical loading", Struct. Eng. Mech., 75(1), 101-108. https://doi.org/10.12989/sem.2020.75.1.101.
  44. Taner San, B. (2014), "An evaluation of SVM using polygon-based random sampling in landslide Susceptibility mapping: The Candir catchment area (western Antalya, Turkey)", Int. J. Appl. Earth Observation Geoinform., 26, 399-412. https://doi.org/10.1016/j.jag.2013.09.010.
  45. Tien Bui, D., Tuan, T.A., Klempe, H., Pradhan, B. and 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.
  46. Tsai H.C. and Liao, M.C. (2019), "Knowledge-based learning for modeling concrete compressive strength using genetic programming", Comput. Concrete, 23(4), 255-265. https://doi.org/10.12989/cac.2019.23.4.255.
  47. Vapnik, V.N. (1995). The Nature of Statistical Learning Theory, Springer Verlag, New York.
  48. Varnes, D.J. (1984), Landslide hazard zonation: A review of Principle and Practice, Unexco, Paries, 63.
  49. Xue, X. (2019), "Application of a support vector machine for prediction of piping and internal stability of soils", Geomech. Eng., 18(5), 493-502. https://doi.org/10.12989/gae.2019.18.5.493.
  50. Yamani, M., Ahmedabadi, A. and Zare, G. (2011), "Application of support vector machine algorithm in landslide risk zoning. (Case study: Derkeh watershed)", Geography Environ. Hazards, 3, 125-142.
  51. Yao, X., Tham, L.G. and Dai, F.C. (2008), "Landslide susceptibility mapping based on Support Vector Machine: a case study on natural slopes of Hong Kong. China", Geomorphology, 101(4), 572-582. https://doi.org/10.1016/j.geomorph.2008.02.011.
  52. Yesilnacar, E. and Topla, T. (2005), "Landslide susceptibility mapping a comparison of logistic regression and neural networks methods in a medium scale (Turkey)", Eng. Geol., 79, 251-266. https://doi.org/10.1016/j.enggeo.2005.02.002.
  53. Yousefi, M. and Carranza, E.J.M. (2015a), "Fuzzification of continuous-value spatial evidence for mineral prospectivity mapping", Comput. Geosci., 74, 97-109. https://doi.org/10.1016/j.cageo.2014.10.014.
  54. Yousefi, M. and Carranza, E.J.M. (2015b), "Geometric average of spatial evidence data layers: A GIS-based multi-criteria decision-making approach to mineral prospectivity mapping", Comput. Geosci., 83, 72-79. https://doi.org/10.1016/j.cageo.2015.07.006.
  55. Yousefi, M. and Nykanen, V. (2016), "Data-driven logistic-based weighting of geochemical and geological evidence layers in mineral prospectivity mapping", J. Geoch. Exploration, 164, 94-106. https://doi.org/10.1016/j.gexplo.2015.10.008.
  56. Yousefi, M., Carranza, E.J.M., Kreuzer, O.P., Nykanen, V., Hronsky, J.M.A. and Mihalasky, M.J. (2021), "Data analysis methods for prospectivity modelling as applied to mineral exploration targeting: State-of-the-Art and Outlook", J. Geochem. Exploration, 229, 106839. https://doi.org/10.1016/j.gexplo.2021.106839.
  57. Yousefi, M., Kreuzer, O.P., Nykanen, V. and Hronsky, J.M.A. (2019), "Exploration information systems-a proposal for the future use of GIS in mineral exploration targeting", Ore Geol. Reviews, 111, 103005.