Assessment of landslide sensitivity and determination of effective factors in its occurrence using the random forest algorithm (Case study: Glandrood watershed)

Document Type : Research Article

Authors

• Ali Gilanipoor ¹
• Sadroddin Motevalli ²
• Khabat Derafshi ³

¹ Ph.D. Student in Climatology, Department of Geography, Islamic Azad University of Noor, Noor, Iran

² Associate Professor, Department of Geography, Islamic Azad University of Noor, Noor, Iran

³ Department of Natural Heritage, Research Institute of Cultural Heritage and Tourism, Tehran, Iran

10.22067/geoeh.2025.89542.1514

Abstract

The Glandrood watershed, given its geological, tectonic, climatic, hydrological characteristics, topography, and poor vegetation cover, has a landslide potential, and inappropriate human intervention in it leads to the occurrence and intensification of mass movements. In the present study, using a descriptive-analytical and survey approach, an attempt has been made to prepare a sensitivity map for slope instability and landslides in the study area using 11 factors effective in causing slope instability. These factors include: slope, aspect direction, elevation, distance from the road, distance from the fault, distance from the waterway, total annual precipitation, average annual temperature, land use, geology, and slope curvature. Then, a total of 352 landslide points were identified using satellite images and field visits, of which 70% were used for model training and the remaining 30% for validation. Subsequently, the random forest algorithm was coded in the MATLAB R2020a environment to identify areas susceptible to landslides. According to the landslide hazard map in the Glandrood watershed, over 30% of the area is classified as "very high risk," 19% as "high risk," 13% as "medium risk," 19% as "low risk," and 16% of the study area is classified as "very low" landslide risk. The prioritization of effective variables indicates that the highest weight, with a criterion ranking of 0.98, is related to elevation. The analysis of the catena concept, which reflects the relationship between soil patterns and landscape slopes with topography and leads to variability in soil properties and subsequently changes in vegetation cover, can well justify the relationship or influence of the elevation factor on landslide movements in the study area.
Extended Abstract
Introduction
Landslides are one of the most common natural phenomena that generally occur in mountainous regions around the world. In many cases, they lead to financial and human losses and are recognized as a natural disaster. Continuous monitoring of surface changes and identifying areas prone to slope movements, including landslides—especially in human settlements and infrastructure such as roads and railways—are among the most effective factors in reducing the casualties and financial losses from natural hazards like landslides. Many researchers have attempted to present models for hazard zoning of landslide phenomena, or in other words, to create landslide hazard maps, primarily based on inductive methods, quantitative, and statistical modeling. They have examined various factors influencing the occurrence of landslides and then analyzed how these factors affect the distribution of landslides. By correlating the landslide hazard map with land use maps, it is possible to identify areas at risk, including cities, villages, bridges, factories, and other structures, so that necessary measures can be taken to protect these assets.
Materials and Methods
The study area is located in Mazandaran Province, south of Noor County, within the Glandrood watershed, in the central part of the Alborz Mountain range. It is part of the larger Haraz watershed. The Glandrood watershed, given its geological, tectonic, climatic, and hydrological characteristics, topography, and poor vegetation cover, has a landslide potential, and inappropriate human intervention in it leads to the occurrence and intensification of mass movements. In the present study, using a descriptive-analytical and survey approach, an attempt has been made to prepare a sensitivity map for slope instability and landslides in the study area using 11 factors that are effective in causing slope instability. These factors include: slope, aspect direction, elevation, distance from the road, distance from the fault, distance from the waterway, total annual precipitation, average annual temperature, land use, geology, and slope curvature. Then, a total of 352 landslide points were identified using satellite images and field visits, of which 70% were used for model training and the remaining 30% for validation. Subsequently, the random forest algorithm was coded in the MATLAB R2020a environment to identify areas susceptible to landslides.
Results and Discussion
According to the landslide hazard map in the Glandrood watershed, over 30% of the area is classified as "very high risk," 19% as "high risk," 13% as "medium risk," 19% as "low risk," and 16% of the study area is classified as "very low risk" for landslides. The prioritization of effective variables indicates that the highest weight, with a criterion ranking of 0.98, is related to elevation. The analysis of the catena concept, which reflects the relationship between soil patterns and landscape slopes with topography and leads to variability in soil properties and subsequently changes in vegetation cover, can well justify the relationship or influence of the elevation factor on landslide movements in the study area. The study of slope movements in the examined watershed indicates that this area is prone to landslides due to natural conditions such as fault structures, steep slopes, humid climate, and sensitive and non-resistant soil. Human intervention in this area leads to the creation and intensification of these movements.
Conclusion
Identifying landslide-prone areas and evaluating landslide susceptibility is crucial for avoiding these areas and implementing preventive and control methods. One of the main actions in this regard is the preparation of landslide hazard susceptibility maps. Planners and decision-makers can use these maps in various fields such as soil and natural resource conservation management, infrastructure and tourism planning, land allocation for urban and rural development, environmental planning, and determining the routes for roads and power transmission lines. Additionally, determining the impact and importance of each variable on the occurrence of slope movements can be the next step in reducing and controlling these movements in the study area. Modeling using the random forest algorithm based on the variables affecting slope movements in the Glandrood watershed indicates that the largest area of this watershed falls within the classes with very high and high landslide susceptibility. The analysis of the relationship between landslide occurrence and influencing factors shows that elevation is the most significant factor affecting this phenomenon in the study area. To justify the impact of elevation as the most important factor, the relationship between vegetation density and elevation in the Glandrood watershed can be mentioned.
 

Keywords

• Landslide
• Susceptibility Assessment
• Random Forest Algorithm
• Glandrood Watershed

Main Subjects

• Sliding and mass movements

---

References

Abedini, M., & Mohammadzadeh Shisha Garan, M. (2022). Landslide assessment using radar images and radar interferometry Case area: Nirchai Basin. Journal of Environmental Science Studies, 7(3), 5161-5171. [In Persian] https://doi.org/:10.22034/jess.2022.335908.1758.html

Akbarimehr, M., Motagh, M., & Haghshenas-Haghighi, M. (2013). Slope stability assessment of the Sarcheshmeh Landslide, Northeast Iran, Investigated using InSAR and GPS observations. Remote Sensing, 5(8), 3681-3700. https://doi.org/10.3390/rs5083681

Aleotti, P., & Chowdhury, R. (1999). Landslide hazard assessment: summary review and new perspectives. Bulletin of Engineering Geology and the Environment, 58(1), 21-44. https://doi.org/10.1007/s100640050066

Alijani, B. (2003). The Climate of Iran. Payam Noor University Press, Tehran. [In Persian]

Amiri, M., Pourghasemi, H. R., Ghanbariana, G. A., & Afzali, S. F. (2019). Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms. Geoderma, 340, 55-69. https://doi.org/10.1016/j.geoderma.2018.12.042

Arabameri, A., Pradhan, B., Pourghasemi, H. R., Rezaei, K., & Kerle, N. (2018). Spatial modelling of gully erosion using GIS and R programing: A comparison among three data mining algorithms. Applied Sciences, 8(8), 1369. https://doi.org/10.3390/app8081369

Berardino, P., Fornaro, G., Lanari, R., & Sansosti, E. (2002). A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms. IEEE Transactions on Geoscience and Remote Sensing, 40, 2375-2383. https://doi.org/10.3390/app8081369

Carlà, T., Intrieri, E., Di Traglia, F., & Casagli, N. (2016). A statistical-based approach for determining the intensity of unrest phases at Stromboli volcano (Southern Italy) using one-step-ahead forecasts of displacement time series. Natural Hazards, 84(1), 669-683. https://doi.org/10.1007/s11069-016-2451-5

Carlà, T., Intrieri, E., Farina, P., & Casagli, N. (2017). A new approach to assess the stability of rock slopes and identify impending failure conditions. In Workshop on World Landslide Forum, Springer, Cham, 733-739. http://dx.doi.org/10.1007/978-3-319-53498-5_84

Chen, W., Zhang, S., Li, R., & Shahabi, H. (2018). Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. Science of the Total Environment, 644, 1006-1018. https://doi.org/10.1016/j.scitotenv.2018.06.389

Davoudi Moghaddam, D., Pourghasemi, H. R., & Rahmati, O. (2019). Assessment of the contribution of geo-environmental factors to flood inundation in a semi-arid region of SW Iran: Comparison of different advanced modeling approaches. Natural hazards GIS-based spatial modeling using data mining techniques. In HR. Pourghasemi, and M. Rossi (Eds.), Natural hazards GIS-based spatial modeling using data mining techniques. https://doi.org/10.1007/978-3-319-73383-8_3

Derafshi, K., Motevalli, S., Hosseinzadeh, M., & Esmaeili, R. (2013). Zoning the landslide hazard in the Taleghan watershed using frequency ratio and multivariate regression. Paper presented at the Proceedings of the Second National Conference of the Iranian Geomorphology Association (Geomorphology and Environmental Change Monitoring), Faculty of Geography, University of Tehran, 12-17. [In Persian]

Di Martire, D., Tessitore, S., Brancato, D., Ciminelli, M. G., Costabile, S., Costantini, M., ... & Calcaterra, D. (2016). Landslide detection integrated system (LaDIS) based on in-situ and satellite SAR interferometry measurements. Catena, 137, 406-421. https://doi.org/10.1016/j.catena.2015.10.002

Ebrahimkhani, R., Afzali, M., & Shokoohi, A. (2011). Prediction and analysis of factors in road traffic accidents using the random forest algorithm. Danesh-e Entezami-e Zanjan, 1(1), 111-127. [In Persian]

Fruneau, B., Achace, J., & Delacourt, C. (1996). Observation and modeling of the Saint- Etienne-de Tine'e landslide using SAR interferometry. Tectonophysics, 265(3-4), 181-190. https://doi.org/10.1016/S0040-1951(96)00047-9

Garosi, Y., Sheklabadi, M., Besalatpour, A. A., Pourghasemi, H. R., Conoscenti, C., & Van Oost, K. (2018). Comparison of the different resolution and source of controlling factors for gully erosion susceptibility mapping. Geoderma, 330, 65-78. https://doi.org/10.1016/j.geoderma.2018.05.027

Hilley, G. E., Bürgmann, R., Ferretti, A., Novali, F., & Rocca, F. (2004). Dynamics of slow-moving landslides from permanent scatterer analysis. Science, 304(5679), 1952- 1955. https://doi.org/10.1126/science.1098821

Hooper, A., Zebker, H., Segall, P., & Kampes, B. (2004). A new method for measuring deformation on volcanoes and other natural terrains using InSAR persistent scatterers. Geophysical Research Letters, 31(23), 1-5. https://doi.org/10.1029/2004GL021737

Intrieri, E., Gigli, G., Mugnai, F., Fanti, R., & Casagli, N. (2012). Design and implementation of a landslide early warning system. Engineering Geology, 147, 124-136. https://doi.org/10.1016/j.enggeo.2012.07.017

Jaboyedoff, M., Michoud, C., Derron, M. H., Voumard, J., Leibundgut, G., Sudmeier-Rieux, K., ... & Leroi, E. (2018). Human-induced landslides: toward the analysis of anthropogenic changes of the slope environment. In Landslides and engineered slopes. Experience, theory and practice. CRC Press, 217-232. http://dx.doi.org/10.1201/b21520-20

Karam, A., & Tourani, M. (2013). Zoning the land susceptibility to landslides using linear regression and hierarchical analysis process, case study: Haraz Axis from Rudehen to Rineh. Applied Research in Geographical Sciences, 13(28), 177-190. [In Persian] http://jgs.khu.ac.ir/article-1-691-fa.html

Karimi Sangchini, E., Awnagh, M., & Saedaldin, A. (2012). Comparing applicability of 4 quantitative and semi-quantitative models in landslide hazard zonation in Chehel-Chay watershed, Golestan province. Water and Soil Conservation, 19(1), 183-196. [In Persian] https://dorl.net/dor/20.1001.1.23222069.1391.19.1.11.2

Lauknes, T. R., Shanker, A. P., Dehls, J. F., Zebker, H. A., Henderson, I. H. C., & Larsen, Y. (2010). Detailed rockslide mapping in northern Norway with small baseline and persistent scatterer interferometric SAR time series methods. Remote Sensing of Environment, 114(9), 2097-2109. https://doi.org/10.1016/j.rse.2010.04.015

Lieb, M., Glaser, B., & Huwe, B. (2012). Uncertainty in the spatial prediction of soil texture: comparison of regression tree and Random Forest models. Geoderma, 170, 70-79. https://doi.org/10.1016/j.geoderma.2011.10.010

Metternicht, G., Hurni, L., & Gogu, R. (2005). Remote sensing of landslides: An analysis of the potential contribution to geospatial system for hazard assessment in mountainous environments. Remote Sensing of Environment, 98(2-3), 284-303. https://doi.org/10.1016/j.rse.2005.08.004

Mora, O., Mallorqui, J. J., & Broquetas, A. (2003). Linear and nonlinear terrain deformation maps from a reduced set of interferometric SAR images. IEEE Transactions on Geoscience and Remote Sensing, 41(10), 2243-2253. https://doi.org/10.1109/TGRS.2003.814657

Motevalli, S., Hosseinzadeh, M., Esmaeili, R., & Derafshi, K. (2015). Evaluation of the accuracy of Multivariate Regression (MR), Logistic Regression (RL), Analytic Hierarchy Process (AHP), and Fuzzy Logic (FL) methods in landslide hazard zoning in the Taleghan watershed. Quantitative Geomorphology Research, 14(1), 1-20. [In Persian] https://dor.isc.ac/dor/20.1001.1.22519424.1394.4.1.1.4

Naghibi, A., & Pourghasemi, H. R. (2015). A comparative assessment of three machine learning models and their performance comparison by bivariate and multivariate. Water Resource Management, 29, 5217-5236. http://dx.doi.org/10.1007/s11269-015-1114-8

Nicodemus, K. K. (2011). Letter to the Editor: On the stability and ranking of predictors from random forest variable importance measures. Briefings in Bioinformatics, 12, 369-373. https://doi.org/10.1093%2Fbib%2Fbbr016

Peters, J., Verhoest, N., Samson, R., Boeckx, P., & De Baets, B. (2008). Wetland vegetation distribution modelling for the identification of constraining environmental variables. Landscape Ecology, 23, 1049- 1065. https://doi.org/10.1007/s10980-008-9261-4

Pirasteh, S., & Li, J. (2017). Landslides investigations from geoinformatics perspective: quality, challenges, and recommendations. Geomatics, Natural Hazards and Risk, 8(2), 1-18. https://doi.org/10.1080/19475705.2016.1238850

Raefatnia, N., Kaviyanpour, M. K., & Ahmadi, T. (2011). Investigating the causes of landslide phenomena in the Glandrood forest (Case study, Series 3, Watershed 48). Natural Resources Science and Technology, 6(1), 53-63. [In Persian] https://sanad.iau.ir/journal/jstnr/Article/1077144

Rahmati, O., Pourghasemi, H. R., & Melesse, A. M. (2016). Application of GIS-based data-driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran. Catena, 137, 360-372. https://doi.org/10.1016/j.catena.2015.10.010

Rott, H., Scheuchl, B., Siegel, A., & Grasemann, B. (1999). Monitoring very slow slope movements by means of SAR interferometry: a case study from a mass waste above a reservoir in the Ötztal Alps, Austria. Geophysical Research Letters, 26(11), 1629-1632. https://doi.org/10.1029/1999GL900262

Sabeti, H., Motagh, M., Sharifi, M. A., Akbari, B., Akbarimehr, M., & Fard, D. (2019). Determination of the displacement rate of the Masoumeh landslide for management of landslide risk by Radar Interferometry. Iranian Journal of Watershed Management Sciences, 13(44), 103-113. [In Persian] http://jwmsei.ir/article-1-745-fa.html

Strozzi, T., Farina, P., Corsini, A., Ambrosi, C., Thüring, M., Zilger, J., ... & Werner, C. (2005). Survey and monitoring of landslide displacements by means of L-band satellite SAR interferometry. Landslides, 2, 193-201. https://doi.org/10.1007/s10346-005-0003-2

Talebi, A. (2011). Investigating the effect of subsurface flows on the occurrence of surface landslides. Paper presented at the Proceedings of the 7^th National Conference on Watershed Science and Engineering of Iran. [In Persian]

Talebi, A., Goudarzi, S., & Pourghasemi, H. R. (2018). Investigation of the possibility of landslide hazard mapping using the Random Forest algorithm (Case study: Sardarabad Watershed, Lorestan Province). Natural Environmental Hazards, 7(16), 45-64. [In Persian] https://doi.org/10.22111/jneh.2017.3213

Teimouri, M., & Asadi Nalivan, O. (2020). Susceptibility zoning and prioritization of the factors affecting landslide using MaxEnt, geographic information system and remote sensing models (Case study: Lorestan Province). Hydrogeomorphology, 6(21), 155-179. [In Persian] https://dorl.net/dor/20.1001.1.23833254.1398.6.21.8.3

Youssef, A. M., Pourghasemi, H. R., Pourtaghi, Z. S., & Al-Katheeri, M. M. (2015). Landslide susceptibility mapping using the random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin. Asir Region, Saudi Arabia, Landslides, 1-14. https://doi.org/10.1007/s10346-015-0614-1

Zeng, T., Guo, Z., Wang, L., Jin, B., Wu, F., & Guo, R. (2023). Tempo-Spatial landslide susceptibility assessment from the perspective of human engineering activity. Remote Sensing, 15(16), 4111(1-28). https://doi.org/10.3390/rs15164111

Zhao, C., & Lu, Z. (2018). Remote sensing of landslides - A review. Remote Sensing, 10(2), 279 (1-6). https://doi.org/10.3390/rs10020279