Skip to main content
SpringerLink
Log in

Evaluation of MLP and RBF Methods for Hazard Zonation of Landslides Triggered by the Twin Ahar-Varzeghan Earthquakes

  • Original paper
  • Published:
Geotechnical and Geological Engineering Aims and scope Submit manuscript

Abstract

Seismic landslides are among the phenomena posing substantial financial and life losses to human societies. Although many studies have been conducted on detection and description of landslides in general, seismic studies of landslides, particularly in Iran, are in their early stages. In this research, two types of artificial neural networks including multilayer perceptron (MLP) and Gaussian radial basis function (RBF) were used for the zonation of seismic landslides at a 1:50,000 scale. The earthquake-stricken area of the twin Ahar-Varzeghan Earthquakes was selected as the modeling case. First, data including disturbance distance (distance from river and road), ground strength class, moisture content, shake intensity, slope angle, and vegetation were collected using the aerial photo, LANDSAT images, topography and geology maps, and site investigations. Next, these data were digitalized using the geographic information system and weighted based on the density of landslides occurred in the study area. Finally, by applying two artificial neural networks (MLP and RBF), the study area was zoned and the accuracy of these methods was evaluated using the occurred landslides triggered by twin Ahar-Varzeghan Earthquakes. Considering that the present research is conducted using a larger number of parameters and more accurate analyses, the obtained results showed that the sum of density ratio values of the occurred seismic landslides in the study area for “medium hazard”, “high hazard”, and “very high hazard” zones using the zonation maps prepared by MLP and Gaussian RBF is 4.054 and 2.032, respectively; with MLP providing the optimum response. Finally, comparing these two methods based on hazard zonation maps and quality sum criterion, it can be concluded that MLP technique involves a higher precision compared to the Gaussian RBF technique in the study area.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  • Arias A (1970) A measure of the earthquake intensity in seismic design for nuclear power plants. Massachusetts Institute of Technology Press, Cambridge, pp 438–468

    Google Scholar 

  • Brand EW (1984) Landslides in Southeast Asia: a state-of-the-art report. Proceedings, 4th International Symposium on Landslides, vol 1. Canadian Geotechnical Society, Toronto, pp 17–59

    Google Scholar 

  • Caniani D, Pascale S, Sdao F, Sole A (2008) Neural networks and landslide susceptibility: a case study of the urban area of Potenza. Nat Hazards 45(1):55–72

    Article  Google Scholar 

  • Chen H, Zeng Z (2011) Deformation prediction of landslide based on genetic-simulated annealing algorithm and BP neural network. In: Advanced computational intelligence (IWACI), 2011 fourth international workshop on IEEE, pp 675–679

  • Cruden D, Varnes D (1996) Landslide types and processes. In: Turner A, Schuster R (eds) Landslides: investigations and mitigation. National Academy Press, Washington, pp 36–75

    Google Scholar 

  • Deering DW, Rouse JW, Haas RH, Schell JA (1975) Measuring forage production of grazing using from Landsat MSS data, proceedings. In: 10th international symposium on remote sensing of environment, Ann Arbor, Michigan, vol 2, pp 1169–1178

  • Ehsanifar F (2011) Landslide hazard occurrence modeling using artificial neural networks (A case study of Tajan watershed, Mazandaran Province, Iran). A Master of Sciences thesis. Faculty of Natural Resources. Mazandaran University, p 125 (in Persian)

  • Fatemi Aghda SM, Bagheri V (2015) Evaluation of earthquake-induced landslides hazard zonation methods: a case study of Sarein, Iran, earthquake (1997). Arab J Geosci 8(9):7207–7227

    Article  Google Scholar 

  • Fatemi Aghda SM, Suzuki A, Kitazono Y (1994) Geological hazards risk analysis using multicriteria evaluation techniques. Mem Fac Eng Kumamoto Univ 39(2):215–255

    Google Scholar 

  • Fatemi Aghda SM, Sarikhani R, Teshneh Lab M (2003) Landslide zonation in Talesh area using the expert systems (MLP network). J Eng Geol 1(2):179–192 (in Persian)

    Google Scholar 

  • Florina CR (2013) Climatic dysfunctionalities observed with the aid of NDMI and SAVI indices in the LEU-ROTUNDA and DĂBULENI plains. Academic Journal of the Air & Water Components of the Environment/Aerul si Apa Compone, pp 500–507

  • Gee MD (1992) Classification of landslide hazard zonation methods and a test of predictive capability. In: Proceedings of 6th international symposium on landslides, Christchurch, New Zealand, vol 2, pp 947–952

  • Hansen A (1984) Strategies for classification of landslides. In: Brunsden D, Prior DB (eds) Slope instability. Wiley, New York, pp 523–602

    Google Scholar 

  • Jibson RW, Harp EL, Michael JA (1998) A method for producing digital probabilistic seismic landslide hazard maps: an example from the Los Angles, CA Area. U.S. Geological Survey Open-File Report 1998-113, p 17

  • Jin S, Sader SA (2005) Comparison of time series tasseled cap wetness and the normalized difference moisture index in detecting forest disturbances. Remote Sens Environ 94(3):364–372

    Article  Google Scholar 

  • Keefer DK (1984) Landslides caused by earthquakes. Geol Soc Am Bull 95(4):406–421

    Article  Google Scholar 

  • Keefer DK (1993) The susceptibility of rock slopes to earthquake-induced failure. Assoc Eng Geol Bull 30:406–421

    Google Scholar 

  • Keefer DK (2000) Statistical analysis of an earthquake-induced landslide distribution—the 1989 Loma Prieta, California event. Eng Geol 58:231–249

    Article  Google Scholar 

  • Krishna G, Raii A, Saxena S (2013) Land slide monitoring and hazard mapping in Uttrakhand using reinforcement leaning and neural network. Int J Adv Res Comput Sci Softw Eng 3(8):231–236

    Google Scholar 

  • Lanzano G, Salzanob E, de Magistrisa FS, Fabbrocinoa G (2013) Vulnerability of pipelines subjected to permanent deformation due to geotechnical co-seismic effects. Chem Eng Trans 32:415–420

    Google Scholar 

  • Lee S, Ryu JH, Lee MJ, Won JS (2006) The application of artificial neural networks to landslide susceptibility mapping at Janghung, Korea. Math Geol 38(2):199–220

    Article  Google Scholar 

  • Lu P, Rosenbaum MS (2003) Artificial neural networks and grey systems for the prediction of slope stability. Nat Hazards 30(3):383–398

    Article  Google Scholar 

  • Mahdavifar MR, Memarian P (2012) A report on the detection of geotechnical phenomena induced by Ahar-Varzeghan Earthquake (2012/08/11). International Institute of Earthquake Engineering and Seismology, p 40 (in Persian)

  • Mahdavifar MR, Jafari MK, Zolfaghari MR (2007) The attenuation of arias intensity in Alborz and Central Iran. In: The fifth international conference on seismology and earthquake engineering, Tehran, Iran, p 7

  • Mcguire B (2004) World atlas of natural hazards. Oxford University Press Inc, Oxford

    Google Scholar 

  • Menhaj MB (2003) Basics of artificial networks: computation intelligence. Amir Kabir University press (Tehran Polytechnic), p 716 (in Persian)

  • 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):1–17

    Article  Google Scholar 

  • Miles SB, Keefer DK (2007) Comprehensive areal model of earthquake-induced landslides: technical specification and user guide. U.S. Geological Survey Open-File Report 2007–1072, p 69

  • Miles SB, Keefer DK (2009a) Evaluation of CAMEL—comprehensive areal model of Earthquake-induced landslides. Eng Geol 104(1):1–15

    Article  Google Scholar 

  • Miles SB, Keefer DK (2009b) Toward a comprehensive areal model of Earthquake-induced landslides. Am Soc Civil Eng Nat Hazards Rev 10:19–28

    Article  Google Scholar 

  • Moradi HR, Sepahvand AR, Abdolmaleki P (2012) Investigating the effect of the number of input variables on accuracy level of artificial neural network for landslide hazard zonation: a case study of Haraz watershed. Ranging and Watersheds publications. J Nat Resour Iran 65(2):231–243 (in Persian)

    Google Scholar 

  • Nabavi MH (1976) An introduction to Geology of Iran in Central Alborz zone. Publication of Geological survey of Iran, p 109 (in Persian)

  • Nefeslioglu HA, Gokceoglu C, Sonmez H, Gorum T (2011) Medium-scale hazard mapping for shallow landslide initiation: the Buyukkoy catchment area (Cayeli, Rize, Turkey). Landslides 8(4):459–483

    Article  Google Scholar 

  • Olfati S, Safar Pour F, Mahmoud Abadi M (2012) Landslides and stabilization methods. Educ Dev J Geogr 26(4):1–7 (in Persian)

    Google Scholar 

  • Panico A, Lanzano G, Salzano E, de Magistris FS, Fabbrocino G (2013) Seismic vulnerability of wastewater treatment plants. Chem Eng Trans 32:13–18

    Google Scholar 

  • Pradhan B, Lee S (2010) Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models. Environ Earth Sci 60(5):1037–1054

    Article  Google Scholar 

  • Rakei B (2003) Landslide hazard zonation using the artificial neural network system in Sefidar Goleh, Semnan Province, Iran. A Master of Sciences thesis. Faculty of Basic Sciences. Tarbiat Modares University, p 120 (in Persian)

  • Salimi N (2015) Landslide hazard zonation using artificial neural networks: a case study in: Taleghan watershed (adjacent to Taleghan Dam). A Master of Sciences thesis. Faculty of Sciences. Kharazmi University, p 148 (in Persian)

  • Sepahvand AR (2010) Landslide susceptibility zonation using the artificial neural network in a part of Haraz watershed. A Master of Science thesis. Faculty of Natural Resources and Marine Sciences. Tarbiat Modares University, p 88 (in Persian)

  • Shariat Jafari M (2009) Specific risk zonation of landslides in the critical (Central Alborz) zones. National Disaster Mitigation Organization. A specialized workshop of earthquake and landslide, p 95 (in Persian)

  • Souri S, Lashkaripour G, Ghafouri M (2011) Landslide hazard zonation using artificial neural network: a case study of national Nozhian watershed. J Eng Geol 5(2):1269–1289 (in Persian)

    Google Scholar 

  • Wang H, Li J, Zhou B, Yuan Z, Chen Y (2013) Application of a hybrid model of neural networks and genetic algorithms to evaluate landslide susceptibility. Nat Hazards Earth Syst Sci Discuss 1(2):353–388

    Article  Google Scholar 

  • Wilson RC (1993) Relation of arias intensity to magnitude and distance in California. U. S Geological Survey Open-File report 1993-556, p 41

  • Zare Pour S (2005) Landslide hazard zonation in Roudbar-Manjil region using the artificial neural network at a 1:50,000 scale. A Master of Sciences thesis. Faculty of Sciences. Kharazmi University, p 107 (in Persian)

  • 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 basis function (RBF) algorithms. Arab J Geosci 6(8):2873–2888

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Geology, Faculty of Basic Sciences, Tarbiat Modares University, Tehran, 14115-111, Iran

    V. Bagheri, A. Uromeihy & M. Razifard

Authors
  1. V. Bagheri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. Uromeihy
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Razifard
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to V. Bagheri.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bagheri, V., Uromeihy, A. & Razifard, M. Evaluation of MLP and RBF Methods for Hazard Zonation of Landslides Triggered by the Twin Ahar-Varzeghan Earthquakes. Geotech Geol Eng 35, 2163–2190 (2017). https://doi.org/10.1007/s10706-017-0236-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10706-017-0236-6

Keywords

Search

Navigation