Remote Sensing and GIS Applications in Environmental Sciences

Identification of landslide-prone areas using multi layer perceptron (MLP) artificial neural network. Case study: Khalkhal city

Document Type : Original Article

Authors

1 Department of Remote Sensing and GIS. Faculty of Planning and Environmental Sciences. University of Tabriz

2 University of Tabriz

10.22034/rsgi.2024.58772.1057

Abstract

One of the hazards that threatens the existing infrastructures in different regions is the phenomenon of landslides. The present study tries to identify the prone areas of this natural phenomenon in Khalkhal city, which was done using the neural network method. For this purpose, 9 factors affecting landslides were identified and prepared, the layer of landslides that happened, obtained from aerial photos and satellite images and field visits, and using non-sliding points in the region, perceptron neural network training data. They created several layers. In order to model the neural network, these data were transferred to the MATLAB 2016 software after initial preparation in the ARC GIS 10.5 software environment and were trained using MLP neural network coding to deal with the data that they have not encountered. , make predictions. The structure of the designed neural network was selected from among the many networks that were created and tested, 1-12-9, which obtained 9 inputs as the number of effective criteria, 12 neurons in the middle layer and one neuron and layer for the output of the network. The results of the validation chart of the neural network (ROC) model show a high accuracy of 95% of the created model in predicting sliding pixels. According to the results, 0.57%, 0.11%, 0.07%, 0.06% and 0.07% of the studied area were placed in very high, high, medium, low and very low classes, respectively. Due to the fact that the largest area of the region is in a very high risk class,

Keywords

Main Subjects

یکی از مخاطراتی که زیر ساخت های موجود در مناطق مختلف را تهدید می کند، پدیده زمین لغزش است، که عوامل مختلفی بر وقوع یا عدم وقوع آن تاثیر گذار هستند. مطالعه حاضر سعی در شناسایی پهنه های مستعد این پدیده طبیعی در شهرستان خلخال دارد، که با استفاده از روش شبکه عصبی انجام گرفته است. برای این منظور ۹ عامل تاثیر گذار بر لغزش شناسایی و تهیه شدند، لایه لغزش های اتفاق افتاده، از عکس های هوایی و تصاویر ماهواره ای و بازدید های میدانی بدست آمده و با استفاده ازنقاط غیر لغزشی در سطح منطقه، داده های آموزش شبکه عصبی پرسپترون چند لایه را ایجاد کردند. این داده ها به منظور مدلسازی شبکه عصبی، پس از آماده سازی اولیه در محیط نرم افزار ARC GIS 10.5 به نرم افزار MATLAB 2016 منتقل شده و با استفاده از کد نویسی شبکه عصبی MLP آموزش دیدند تا در مورد داده هایی که با آنها برخورد نداشته اند، پیش بینی انجام دهند. ساختار شبکه عصبی طراحی شده از بین شبکه های بسیاری که ایجاد و آزمایش شدند، ۱-۱۲-۹  انتخاب شد، که ۹ ورودی به تعداد معیار های تاثیرگذار، ۱۲ نورون در لایه میانی و یک نورون و لایه برای خروجی شبکه بدست آمد. نتایج نمودار اعتبار سنجی مدل شبکه عصبی (ROC)  نشان دهنده دقت بالای ۹۵ درصدی مدل ایجاد شده در پیش بینی پیکسل های لغزشی است. 

  • performance of logistic and non-parametric statistical algorithms in order to manage areas sensitive to mass movements in the Goijeh Bel watershed. Geography and Environmental Hazards, No. 19, Fall 2015, Pages 57-77
  • Baharond, S. and Suri, S. (2014). Landslide risk zoning using artificial neural network. (Case study: Sepid Dasht area - Lorestan). Remote sensing and geographic information system in natural resources (6th year, 4th issue), winter 2014
  • Teshnelab, M. and Menshi, M. (2012). Climatic forecasting of meteorological parameters using neural-fuzzy networks based on the training of Tali sector parameters. The third regional climate change conference, October 29 to November 1, 2012, Isfahan
  • Rezai Moghadam, M.H.; Nikjo, M. Valizadeh Kamran, Kh. and Belvasi, A. and Belvasi, M. (2014). Application of artificial neural network in landslide risk zoning. Scientific Research Journal of Geography and Planning, Year 21, Number 59, Spring 2016, Pages 89 to 111
  • Raushi, S. and Khodayi, F. (2015). Risk zoning of slope instabilities in mountain roads using artificial neural network (MLP) case study: (Dere Diz Gorge). Quarterly Journal of Natural Geography, Year 9, Number 33, Fall 2015
  • Ranjbar, M. and Falak, A. (2013). Investigation and analysis of AHP and artificial neural network (ANN) models in the zoning of landslide risk in the southern slopes of Alborz (Tajrish region of Tehran), Geographical Quarterly of the Land, Year 11, Number 43, Fall 2013
  • ) Suri, S; Lashkaripour, Gha and Ghafouri, M. (2011). Landslide risk zoning using artificial neural network. Case Study (Kashori Basin), Engineering Geology Journal, Volume 5, Number 2, Autumn and Winter 2019
  • Salehipour, Alireza (1380) Investigating the effective hydromorphic parameters in the amplitude movements of the watershed of Gori Chai using geographic information system, Master's Thesis, University of Tehran
  • ) Fatemi Aqda, S. and Ghoumian, J. (2012). Evaluating the efficiency of statistical methods in determining the landslide risk potential. Journal of Earth Sciences, 11(47-48): 28-47
  • ) Minhaj, Mohammad Baqir (1381). Basics of neural networks. Amir Kabir Industrial Publications (Tehran Polytechnic), p. 715
  • ) Minhaj, Mohammad Baqer. (2004). Basics of Neural Networks (Computational Intelligence), Volume 1, Third Edition, Amirkabir University of Technology Publishing Center, p. 712.
  • ) Mahmoudi, Faraj A... (1388) authored by Roger Kek, Dynamic Geomorphology - Internal and External Dynamics, Tehran University Publications, p. 1
  • ) Moradi, M.; Baziar, M.H.; Mohammadi, Z (1390). Landslide risk zoning in Dana city based on GIS system and using AHP method. 6th National Civil Engineering Congress, Semnan University
  • Falahi, G; Dehghan Monshadi, A. (2014). Application of fuzzy logic and artificial neural network algorithm in preparation of landslide susceptibility map in Chalus river basin. Promotional Scientific Journal of Mapping and Geospatial Information Engineering, 7th Volume, Number 2, June 2015, Pages 47-59
  • ) Shirani, K; Heydari, F; Arab Ameri, A. (2016). Comparison of artificial neural network and multivariate regression methods in landslide risk zoning (Wank basin, Isfahan province). Scientific Research Journal of Watershed Engineering and Management, Volume 9, Number 4, Pages 451-464
  • ) Ehsani Far, Firoz (2019). Landslide Risk Modeling Using Artificial Neural Network (Case Study: Tajen Watershed, Mazandaran Province, Master's Thesis, Sari University of Agricultural Sciences and Natural Resources
  • Ayalew,l. and Yamagishi,H. (2005): The application of GIS-based Logistic regression for landslide susceptibility mapping in the Kakuda-Yaahiko Mountains, central Japan, Geomorphology 65, 15-31
  • Atkinson, P. M., & Tatnall, A. R. L. (1997). Introduction of neural networks in remote sensing. Remote Sensing, 18(4), 699-709.
  • Conrads, P.A., Roehle, E. A., 1999. Comparing Physics- Based and Neural Network Mo Simulating Salinity, Temperature and Dissolved in a Complex, Tidally Affected River Basin, Proceeding of the South Carolina Environmental Conference, pp 1-15.
  • Fulop, I. A., Jozsa, J., Karamer. T., 1998. A neural network application in estimating wind induced shallow lake motion, Hydro informatics 98, 2, pp 753-757
  • Gomez, H., Kavzoglu, T., (2005), “Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela”, Engineering Geology, 78: 11-27
  • Komac, M. (2006), “A landslide suscepility model using the analytical hierarchy process method and multivariate statistics in perialpine Slovenia
  • Melchiorre C, Matteucci M, Azzoni A, Zanchi A. 2008. Artificial neural networks and cluster analysis in landslide susceptibility zonation.Geomorphology, 94(3): 379-400
  • Ranjithan, J., Eheart, J., Garrett, J. H., 1995. Application of neural network in groundwater remediation under condition of uncertainty. New Uncertainty conceptsion Hydrology and Water Resources, pp133-140
  • Shalkoff, R. J. (1997). Artificial neural networks. New York, NY: McGraw-Hil
  • 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(6): 1125-1138
Remote Sensing and GIS Applications in Environmental Sciences
Volume 3, Issue 9 - Serial Number 8
January 2024
Pages 104-81
  • Receive Date: 09 October 2023
  • Revise Date: 27 February 2024
  • Accept Date: 07 April 2024