Rockfall risk zoning on The Khalkhal to Shahroud road using multilayer perceptron algorithm

Document Type : Research Article

Authors

• Fariba Esfandyari Darabad ¹
• Masoud Rahimi ²
• Mehrdad Vahabzadeh ³

¹ Professor in Geomorphology, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran.

² Assistant professor in Geomorphology, Faculty of Literature and Human sciences, Ferdowsi University of Mashhad, Mashhad, Iran

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

10.22067/geoeh.2024.87847.1482

Abstract

Extended Abstract
Introduction
Rockfalls are a type of slope movement process that does not require a transporting medium (e.g., water) and predominantly occur under the influence of gravity (Dikau, 2006). The detachment of a single rock block or a volume of blocks from steep slopes is followed by motions mainly through the air. The fall trajectory is strongly controlled by the mean slope gradient, enabling different motion modes such as free-falling, bouncing, and rolling. Consequently, rockfalls present an unpredictable threat, especially along highways and railways, where they can cause damage to infrastructure or endanger human lives (Bostjančić et al., 2020). In high mountain regions, rockfall activity is thought to be changing due to accelerated climate warming and permafrost degradation, potentially resulting in increased activity and larger volumes involved in individual falls (Stoffel et al., 2024). Therefore, it is crucial to assess areas prone to rockfalls in mountainous regions. The aim of this research is to zone the risk of rockfalls long the Khalkhal–Shahroud road using a multi-layer perceptron algorithm.
Material and Methods
The multi-layer perceptron algorithm is a modern machine learning model capable of solving complex problems. In this study, the necessary data were obtained from topographic maps at a scale of 1:25,000, geological maps at a scale of 1:100,000, a digital elevation model (DEM) with 12.5-meter resolution from the ALOS-PALSAR satellite, Sentinel data (spatial resolution of 10 meters), Google Earth satellite images, and field studies. In rockfall hazard zoning using GIS, the most critical component is the preparation of a rockfall distribution map or rockfall inventory. Fieldwork was conducted to identify rockfalls and prepare the inventory.
Results and Discussion
To identify the factors contributing to rockfall occurrence, field studies identified eight key factors: elevation, vegetation, slope aspect, distance from faults, distance from roads, geology, land use, and slope gradient. After pre-processing, all layers were entered into SPSS Modeler software, and the model was designed with 8 input neurons, 8 intermediate neurons, and 1 output neuron. The results revealed that, in the multi-layer perceptron algorithm, the geological layer had the highest weight value (0.20), followed by the land use layer (0.14) and distance from roads (0.12). In the model validation phase, the results demonstrated an AUC value of 0.9810 in the training phase and 0.9876 in the testing phase, indicating high model validity in both phases.
Conclusion
This research aimed to identify areas at risk of rockfall along the Khalkhal–Shahroud road using a multi-layer perceptron algorithm. The results highlight the significant influence of geological conditions on rockfall occurrences, emphasizing the need to consider slope instability in all spatial planning efforts in this region. It is recommended that future studies explore other machine learning models, such as support vector machines, to further evaluate rockfalls and related slope movements.

Keywords

• Rockfall Hazard Zonation
• Multilayer Perceptron Algorithm
• Road Hazards
• Khalkhal Road
• Slope Stability Analysis

Main Subjects

• Sliding and mass movements

---

References

Abdi Bastami, S., Memarian, H., Tajbakhsh, S. M., & Azamy Rad, M. (2019). Prioritization of landslide effective factors using logistic regression (Case study: A part of KopeDagh- Hezar Masjed Zone). Journal of Watershed Management Resesrch, 10(19), 154-170. [In Persian]   http://dx.doi.org/10.29252/jwmr.10.19.154

Abedini, M., & Piroozi, E. (2020). Landslide hazard Zoning with Using Combination Methods of Hot Spot, ANP and WlC (Case Study: Khalkhal County). Journal of Geography and Environmental Hazards, 8(4), 19-36. [In Persian]  https://doi.org/10.22067/geo.v0i0.81836

Abedini, M., Mozafari, H., & Faal Naziri, M. (2019). Investigating and comparing the effectiveness of information value models and frequency ratio coefficient and Shannon's entropy in zoning rock fall risk (case study: Zanjan-Teham-Taram road). Journal of the Geographical Studies of Mountainous Areas, 3(1) ,55-75. [In Persian] http://dx.doi.org/Doi:10.52547/gsma.3.1.55

Amirpour Kohsareh, S. (2018). Investigating geomorphological hazards of Ardabil to Sarcham road with emphasis on rockfall and landslide using fuzzy logic model. Master's thesis, University of Mohaghegh Ardabili. [In Persian]

Asghari Saraskanrod, S., & Mozafari, H. (2020). Estimate and Comparison of Frequency Ratio and Network Analysis models in Rock falling Zoning( Case study Zanjan road to Taham and Tarom). Journal of Spatial Analysis Environmental Hazards, 6(4), 123-142. [In Persian]  http://dx.doi.org/10.29252/jsaeh.6.4.123

Cirillo, D., Zappa, M., Tangari, A. C., Brozzetti, F., & Ietto, F. (2024). Rockfall analysis from UAV-based photogrammetry and 3D models of a cliff area. Drones, 8(1), 31. https://doi.org/10.3390/drones8010031

Delashmit, W. H., & Manry, M. T. (2005). Recent developments in multilayer perceptron neural networks. Paper presented of the 17th Annual Memphis Area Engineering and Science Conference, MAESC (7).‏ https://ipnnl.uta.edu/publications/recent/

Demuth, H. B., Beale, M. H., De Jess, O., & Hagan, M. T. (2014). Neural network design. United States: Martin Hagan. https://dl.acm.org/doi/abs/10.5555/2721661

Elmoulat, M., Brahim, L. A., Elmahsani, A., Abdelouafi, A., & Mastere, M. (2021). Mass movements susceptibility mapping by using heuristic approach. Case study: province of Tétouan (North of Morocco). Geoenvironmental Disasters, 8, 1-19. https://doi.org/10.1186/s40677-021-00192-0

Emami, S. N., & Yousefi, S. (2023). Comparison of the efficiency of some machine learning models for mass movement susceptibility mapping (Case study: Chaharmahal and Bakhtiari province). Scientific Quarterly Journal of Geosciences, 33(2), 183-204. [In Persian] https://doi.org/10.22071/gsj.2022.345954.2003

Esfandiary Darabad, F., Rahimi, M., Navidfar, A., & Mehrvarz, A. (2020). Assessment of landslide sensitivity by neural network method and Vector machine algorithm (Case study: Heyran Road -Ardebil province). Quantitative Geomorphological Research, 9(3), 18-33. [In Persian] https://www.geomorphologyjournal.ir/article_122210.html

Eskandari, M. R., Nazarpour, A., & Khayat, N. (2023). Rockfall risk Mapping Using Multiple Criteria Decision Making (MCDM) AHP, and Fuzzy-Gamma methods in Khorramabad-Pol-e-Zal Freeway. Journal of Natural Environmental Hazards, 12(35), 139-156. [In Persian] https://doi.org/10.22111/jneh.2023.41400.1872

Fanos, A. M., Pradhan, B., Alamri, A., & Lee, C. W. (2020). Machine learning-based and 3d kinematic models for rockfall hazard assessment using LiDAR data and GIS. Remote Sensing, 12(11), 1755. https://doi.org/10.3390/rs12111755

Gasemyan, B., Abedini, M., Roostai, S., & Shirzadi, A. (2021). Landslide susceptibility assessment using a novel ensemble algorithm based model (Case Study: Kamyaran city, Kurdistan province). Quantitative Geomorphological Research, 9(4), 130-146. [In Persian] https://dor.isc.ac/dor/20.1001.1.22519424.1400.9.4.8.6

Guzzetti, F., Reichenbach, P., & Ghigi, S. (2004). Rockfall hazard and risk assessment along a transportation corridor in the Nera Valley, Central Italy. Environmental management, 34(2), 191-208. https://doi.org/10.1007/s00267-003-0021-6

Hatamifar, R., Mousavi, S.H., & Alimoradi, M. (2012). Landslide hazard zonation using AHP model and GIS technique in Khoram Abad City. Geography and Environmental Planning, 23(3), 43-60. [In Persian]  https://dorl.net/dor/20.1001.1.20085362.1391.23.3.3.5

Jaccard, C. J., Abbruzzese, J. M., & Howald, E. P. (2020). An evaluation of the performance of rock fall protection measures and their role in hazard zoning. Natural Hazards, 104(1), 459-491. https://doi.org/10.1007/s11069-020-04177-4

Jahandar, S., Aghagolzadeh, A., & Kazemitabar, J. (2020). Blind Recognition of Block Code Parameters in the Presence of High SNR Using Statistical Techniques. Journal of Advanced Defense Science & Technology, 10(4), 373-381. [In Persian] https://dor.isc.ac/dor/20.1001.1.26762935.1398.10.4.4.2

Jiang, N., Li, H. B., & Zhou, J. W. (2021). Quantitative hazard analysis and mitigation measures of rockfall in a high-frequency rockfall region. Bulletin of Engineering Geology and the Environment, 80, 3439-3456.‏ https://doi.org/10.1007/s10064-021-02137-1

Lee, S., Ryu, J. H., Lee, M. J., & Won, J. S. (2006). The application of artificial neural networks to landslide susceptibility mapping at Janghung, Korea. Mathematical Geology, 38, 199-220. https://doi.org/10.1007/s11004-005-9012-x

 Lucks, L., Stilla, U., Hoegner, L., & Holst, C. (2024). Photogrammetric rockfall monitoring in Alpine environments using M3C2 and tracked motion vectors. ISPRS Open Journal of Photogrammetry and Remote Sensing, 100058. https://doi.org/10.1016/j.ophoto.2024.100058

Nakajima, S., Abe, K., Shinoda, M., Nakamura, S., & Nakamura, H. (2021). Experimental study on impact force due to collision of rockfall and sliding soil mass caused by seismic slope failure. Landslides, 18, 195-216. https://doi.org/10.1007/s10346-020-01461-z

Nanehkaran, Y. A., Licai, Z., Chen, J., Azarafza, M., & Yimin, M. (2022). Application of artificial neural networks and geographic information system to provide hazard susceptibility maps for rockfall failures. Environmental Earth Sciences, 81(19), 475. https://doi.org/10.1007/s12665-022-10603-6   

Negahban, S., Jahan Tighmand, S., & Rahimi Herabadi, S. (2020). Explaining the Position of Positivism and Critical Methods in Geomorphic Hazard (Case: Rockfalls Hazard on Rudbar-Rostamabad Freeway). Quantitative Geomorphological Research, 9(1), 52-66. [In Persian] https://www.geomorphologyjournal.ir/article_109534.html

Ramdhani, Y., Mustofa, H., Topiq, S., Alamsyah, D. P., Setiawan, S., & Susanti, L. (2022). Sentiment analysis twitter based lexicon and multilayer perceptron algorithm. Paper presented of the 10th International Conference on Cyber and IT Service Management (CITSM) ,Yogyakarta, Indonesia, 1-6. https://doi.org/10.1109/CITSM56380.2022.9936029

Rana, A., Rawat, A. S., Bijalwan, A., & Bahuguna, H. (2018). Application of multi layer (perceptron) artificial neural network in the diagnosis system: a systematic review. Paper presented of the 2018 International conference on research in intelligent and computing in engineering (RICE) , 1-6. https://doi.org/10.1109/RICE.2018.8509069

Riedmiller, M., & Lernen, A. (2014). Multi layer perceptron. In Machine Learning Lab Special Lecture. Germany: University of Freiburg.

Vahabzadeh, M. (2023). Risk zoning of skirts on Khalkhal road to Shahroud using artificial neural network system. Master's thesis, University of Mohaghegh Ardabili. [In Persian]

Yan, J., Zeng, S., Tian, B., Cao, Y., Yang, W., & Zhu, F. (2023). Relationship between highway geometric characteristics and accident risk: A multilayer perceptron model (MLP) approach. Sustainability, 15(3), 1893. https://doi.org/10.3390/su15031893

Zhao, H., Tian, W. P., Li, J. C., & Ma, B. C. (2018). Hazard zoning of trunk highway slope disasters: a case study in northern Shaanxi, China. Bulletin of Engineering Geology and the Environment, 77, 1355-1364. https://doi.org/10.1007/s10064-017-1178-1