Identification of Rockfall Hazard Zones Along The Meshginshahr-Ahar Road Using Artificial Neural Networks

Articles in Press

Document Type : Original Article

Authors

1 Assistant professor of Geomorphology, Faculty of Literature and Human science, Ferdowsi University of Mashhad, Mashhad, Iran

2 Professor of Geomorphology, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran.

3 Masters graduate, Geomorphology and Environmental Management, Faculty of Social Sciences University of Mohaghegh Ardabili, Ardabil, Iran

4 Masters graduate, Geomorphology and Environmental Management, Faculty of Social Sciences University of Mohaghegh Ardabili, Ardabil,Iran

Abstract

Rockfall hazards can cause significant human and financial losses along mountain roads. The Meshginshahr-Ahar road is one of the main transport routes constantly threatened by rockfalls. Therefore, the identification of rockfall zones along this route is crucial. In this study, a Multilayer Perceptron (MLP)  artificial neural network was used to identify areas susceptible to rockfall. For this purpose, nine factors influencing rockfall occurrence in the study area were identified and selected. Subsequently, through field surveys and satellite images, a rockfall occurrence layer was prepared for the road corridor. The modeling process, based on these nine influencing factors and the rockfall occurrence layer, was conducted in the SPSS Modeler software. The results showed that the highest weighted factors contributing to rockfall occurrence in the study area were geology (0.20), slope and distance from faults (0.14), and elevation (0.12). On the other hand, the lowest weights were assigned to precipitation (0.05), land use, and slope aspect (0.08). The results also showed that 13%, 14%, 28%, and 45% of the study area fell into the very high, high, moderate, and low-risk classes respectively. The results of this research can help to reduce slope hazards and improve environmental stability in the study area, thereby making a significant contribution to the sustainable development of the region.

Keywords

Main Subjects

References

References (in Persian)
Abedini, Musa; Mozafari, Hassan;  Active Naziri, Mehdi.  (1401).  Investigating and comparing the effectiveness of information value models and frequency ratio coefficient and Shannon's entropy in rock fall risk zoning (case study: Zanjan-Tham-Taram road).  Geographical studies of mountainous regions, 3 (1): 55-75.  Doi:10.52547/gsma.3.1.55. [In Persian] Asghari Saraskanroud, fisherman;   Mozafari, Hassan.  (2018).  Evaluation and comparison of frequency ratio coefficient models and network analysis in rock fall zoning.  Spatial analysis of environmental hazards, 6(4), 123-142.  Doi: 10.29252/jsaeh.6.4.123. [In Persian]
Esfandiari Darabad, Fariba;  Rahimi, Massoud;  Navidfar, Asghar;  Mehrovarz, Arslan.  (2019).  Landslide susceptibility assessment using artificial neural network methods and support vector machine algorithm (case study: Hiran road, Ardabil province).  Quantitative Geomorphology Research, 9(3), 18-33, doi: 10.22034/gmpj.2020.122210. [In Persian]
Esfandiari Darabad, Fariba;  Rahimi, Massoud;  Vahabzadeh, Mehrdad.  (2024).  Rockfall risk zoning on Khalkhal to Shahroud road using the multi-layer perceptron algorithm.  Journal of Geography and Environmental Hazards, doi: 10.22067/geoeh.2024.87847.1482. [In Persian]
Eskandari, Mohammadreza;  Nazarpur, Ahad;  Tailor, Navid.  (1402).  Rockfall risk zoning using multi-criteria decision-making methods in Khorramabad-Pul Zal freeway.  Natural Environment Hazards, 12(35), 139-156.  doi: 10.22111/jneh.2023.41400.187. [In Persian]
 Ilanlo, Maryam;  Ebrahimi, Leila.  (1395).  Zoning the risk of mass movements using models of information value, surface density, and LNRF in the Abkhiz Zahra basin.   Risk Knowledge magazine.  Volume 3, Number 2, pp. 141-153. [In Persian]
Maddi, Agil.  (1389).  Investigating the geomorphological instability of the Sain pass (between the cities of Nair and Sarab, Azerbaijan region) using the Anbalagan method.  Geography and Environmental Planning, 21(1), 9-77 dor: 20.1001.1.20085362.1389.21.1.5.9. [In Persian]
 Nemati, Maryam;  Khabazi, Mustafa;  Abdullahi, Ali Asghar;  Judges, Ali.  (2019).  The role of "falling" range movements in creating railway hazards (Zahedan-Kerman railway axis)., https://civilica.com/doc/1162599. Doi: 20.1001.1.20085656.1399.13.47.7.9. [In Persian]
Wahabzadeh; Mehrdad  (1402).  Zoning of range hazards on Khalkhal to Shahroud road using artificial neural network system, master's thesis in geomorphology and environmental planning, Mohaghegh Ardabili University. [In Persian]
Zarmardian, M., (2012).  Geomorphology of Iran, second volume, Press of Ferodosi University of Mashhad. [In Persian]
 
References (in English)
Abdullah, S., Ismail, M., & Ahmed, A. N. (2019). Multi-layer perceptron model for air quality prediction. Malaysian Journal of Mathematical Sciences, 13, 85-95.
Aitkin, M., & Foxall, R. (2003). Statistical modeling of artificial neural networks using the multi-layer perceptron. Statistics and Computing, 13, 227-239.
Bickel, V.T., Jordan, A.P., Manconi, A., Loew, S., & Mall, U. (2021). Global Drivers of Lunar Rockfall. ‏
Kanno, H., Moriguchi, S., Tsuda, Y., Yoshida, I., Iwanaga, S., & Terada, K. (2023). A method for rockfall risk quantification and optimal arrangement of protection structures along a road. Engineering Geology, 314, 107004.
Li, D., Huang, F., Yan, L., Cao, Z., Chen, J., & Ye, Z. (2019). Landslide susceptibility prediction using particle-swarm-optimized multilayer perceptron: Comparisons with multilayer-perceptron-only, bp neural network, and information value models. Applied Sciences, 9(18), 3664.
Pham, B. T., Bui, D. T., Prakash, I., & Dholakia, M. B. (2017). Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment in the Himalayan area (India) using GIS. Catena, 149, 52-63.
Pierson, L.A., Davis, S.A., & Vickle, R.V. (1990). ROCKFALL HAZARD RATING SYSTEM: IMPLEMENTATION MANUAL.
Rathore, H., Wenzel, L., Al-Ali, A. K., Mohamed, A., Du, X., & Guizani, M. (2018). Multi-layer perceptron model on chip for secure diabetic treatment. IEEE Access, 6, 44718-44730.‏ doi: 10.1109/ACCESS.2018.2854822.
Rossi, M., Sarro, R., Reichenbach, P., & Mateos, R. M. (2021). Probabilistic identification of rockfall source areas at a regional scale in El Hierro (Canary Islands, Spain). Geomorphology, 381, 107661.
Wang, Z. H., Hu, Z. W., Zhao, W. J., Guo, Q. Z., & Wan, S. M. (2015). Research on regional landslide susceptibility assessment based on multiple layers perceptron-Take the hilly area in Sichuan as an Example. Journal of Disaster Prevention and Mitigation Engineering, 35(5), 691-698.
Wei, L., Xu, Y., Lv, D., Cui, H., Liu, S., & Ao, M. (2024). Rockfall susceptibility assessment in Kuandian County (Northeast China) by combining information content method and analytic hierarchy process. Bulletin of Engineering Geology and the Environment, 83(6), 240.
Yan, J., Chen, J., Tan, C., Zhang, Y., Liu, Y., Zhao, X., & Wang, Q. (2023). Rockfall source area identification at the local scale by integrating discontinuity-based threshold slope angle and rockfall trajectory analyses. Engineering Geology, 313, 106993.
Stoffel, M., Trappmann, D. G., Coullie, M. I., Ballesteros Cánovas, J. A., & Corona, C. (2024). Rockfall from an increasingly unstable mountain slope driven by climate warming. Nature Geoscience, 17(3), 249-254.
Journal of Natural Environmental Hazards

Articles in Press, Accepted Manuscript
Available Online from 12 January 2025

Files

History

  • Receive Date: 14 October 2024
  • Revise Date: 10 December 2024
  • Accept Date: 12 January 2025

Share

How to cite

Statistics