Assessment and Analysis of Landslide Susceptibility Using the Random Forest Model and the Capabilities of GEE and GIS (Case Study: Navroud Watershed, Gilan Province)

Shahzeidi, Somayeh Sadat; Babaei Olam, Tayebeh; Abedini, Mousa

Assessment and Analysis of Landslide Susceptibility Using the Random Forest Model and the Capabilities of GEE and GIS (Case Study: Navroud Watershed, Gilan Province)

Document Type : Origional Article

Authors

Somayeh Sadat Shahzeidi ¹ ^¶

Tayebeh Babaei olam ²

Mousa Abedini ³

¹ Associate Professor of Geomorphology, Department of Geography, Faculty of Literature and Humanities, University of Guilan, Rasht, Iran.

² Ph.D Student, Department of Physical Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran.

³ Professor, Department of Physical Geography, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran.

Abstract

Background and Objective: Landslides are among the most significant natural hazards in the mountainous and humid regions of northern Iran, causing substantial damage to natural resources, infrastructure, and human settlements each year. The Navroud watershed in Gilan Province is considered highly susceptible to landslide occurrence due to its complex topography, relatively high precipitation, and intensive human activities. The primary objective of this study is to assess and map landslide susceptibility and to determine the relative importance of the influencing factors using the Random Forest model in combination with the capabilities of Google Earth Engine (GEE) and Geographic Information Systems (GIS) within the Navroud watershed.
Methodology: This research adopts an applied–analytical approach, in which eleven landslide-conditioning factors including slope, aspect, elevation, geology, land use, vegetation cover, slope curvature, distance to roads, distance to drainage networks, distance to faults, and annual precipitation were selected as independent variables. The required thematic layers were generated using remote sensing data, the ALOS PALSAR digital elevation model with a spatial resolution of 12.5 m, geological maps, and meteorological data. After fuzzification and normalization, the datasets were integrated into the modeling process. A landslide inventory map comprising 150 landslide locations was prepared based on satellite imagery interpretation and field observations, and the data were divided into training (70%) and validation (30%) subsets. The Random Forest model was implemented in the Google Earth Engine environment, and the final landslide susceptibility map was produced in five classes: very low, low, moderate, high, and very high.
Results and findings: The results indicate that approximately 32% of the watershed area falls within the high and very high susceptibility classes, predominantly concentrated in the elevated and steep slopes of the northwestern ad southwestern parts of the basin. Furthermore, variable importance analysis revealed that slope, elevation, precipitation, land use, and distance to roads are the most influential factors controlling landslide occurrence. Model performance evaluation using the ROC curve showed that the Area Under the Curve (AUC) value during the validation stage was 0.897, demonstrating the high accuracy and strong predictive capability of the Random Forest model in identifying landslide-prone areas.

Keywords

Landslide

Random Forest (RF) algorithm

Receiver Operating Characteristic (ROC) curve

GIS

Navroud watershed

Gilan Province

Subjects

Physical geogeaphy

1. Abedini, M., & Pasban, A. H. (2025). Assessment and comparison of Random Forest and Support Vector Machine models in landslide hazard zonation (Case study: Firozabad Watershed). Quantitative Geomorphological Research. Advance online publication. https://doi.org/10.22034/gmpj.2025.543572.1578 (In Persian)

2. Agrawal, N., & Dixit, J. (2022). Assessment of landslide susceptibility for Meghalaya (India) using bivariate (frequency ratio and Shannon entropy) and multi-criteria decision analysis (AHP and fuzzy-AHP) models. All Earth, 34(1), 179–201. https://doi.org/10.1080/27669645.2022.2101256

3. Alcántara-Ayala, I., & Sassa, K. (2023). Landslide risk management: From hazard to disaster risk reduction. Landslides, 20, 2031–2037. https://doi.org/10.1007/s10346-023-02120-6

4. Asadi, M. (2025). Comparison of CMIP5 and CMIP6 outputs on the trend of climatic parameters affecting almond growth (Case study: Birjand County). Geography and Planning, 29(92), 313–332. https://doi.org/10.22034/gp.2024.61686.3262 (In Persian)

5. Asghari, S., & Foroutan, M. (2025). Evaluating the accuracy of machine learning algorithms in landslide hazard zonation of Samian Watershed. Quantitative Geomorphological Research. Advance online publication. https://doi.org/10.22034/gmpj.2025.551301.1583 (In Persian)

6. Atashafrooz,N and safaee,M . (2021). Landslide Micro-Zoning Using DEMATEL Technique and Fuzzy AHP (Case Study: the County of Dehdez in Khuzestan Province). (In Persian). Journal of Sustainable Urban & Regional Development Studies (JSURDS), 2(2), 61-81. https://www.srds.ir/article_134524.html?lang=en

7. Babarabi, N., Lorestani, G., & Esmaeili, R. (2025). Zoning of landslide risk occurrence using Random Forest and Support Vector Machine models (Case study: Talar Watershed). Researches in Earth Sciences, 16(1), 152–168. (In Persian)

8. Chang, M., Dou, X., Zhu, X., & Ma, Y. (2024). Integrated risk assessment of landslide in karst terrains: Advancing landslide management in Beiliu City, China. International Journal of Applied Earth Observation and Geoinformation, 132, 104046. https://doi.org/10.1016/j.jag.2024.104046

9. Dai, X., Chen, J., Zhang, T., & Xue, C. (2025). Integrated landslide risk assessment via a landslide susceptibility model based on intelligent optimization algorithms. Remote Sensing, 17(3), 545. https://doi.org/10.3390/rs17030545

10. Gilanipour, A., Motevalli, S., & Darafshi, K. (2025). Evaluation of landslide susceptibility and determination of effective factors using Random Forest algorithm (Case study: Galandrood Watershed). Geography and Environmental Hazards, 14(1), 247–274. (In Persian)

11. Heydarifar,M R , Solimani rad,E and Hosseinisiahgoli,M . (2020). Investigating the Role of Natural Hazards and Crisis Management in Land Management (Case Study: Kermanshah Province). (In Persian). Journal of Sustainable Urban & Regional Development Studies (JSURDS), 1(1), 55-76. https://www.srds.ir/article_122918.html?lang=en

12. Huang, W., Ding, M., Li, Z., Zhuang, J., Yang, J., Li, X., Meng, L. E., Zhang, H., & Dong, Y. (2022). An efficient user-friendly integration tool for landslide susceptibility mapping based on support vector machines: SVM-LSM toolbox. Remote Sensing, 14(14), 3408. https://doi.org/10.3390/rs14143408

13. Janizadeh, S., Bateni, S. M., Jun, C., Pal, S. C., Band, S. S., Chowdhuri, I., Saha, A., Tiefenbacher, J. P., & Mosavi, A. (2023). Potential impacts of future climate on the spatio-temporal variability of landslide susceptibility in Iran using machine learning algorithms and CMIP6 climate-change scenarios. Gondwana Research, 124, 1–17. https://doi.org/10.1016/j.gr.2023.05.009

14. Jemec Auflič, M., Bezak, N., Šegina, E., Frantar, P., Gariano, S. L., Medved, A., & Peternel, T. (2023). Climate change increases the number of landslides at the juncture of the Alpine, Pannonian and Mediterranean regions. Scientific Reports, 13, 23085. https://doi.org/10.1038/s41598-023-50102-7

15. Jiang, Z., Wang, M., & Liu, K. (2023). Comparisons of convolutional neural network and other machine learning methods in landslide susceptibility assessment: A case study in Pingwu. Remote Sensing, 15, 798. https://doi.org/10.3390/rs15030798

16. Khaledi,S , Farahmand,G and Ali Bakhshi,A . (2021). Vulnerability analysis and zoning of natural geomorphological hazards (Flood and earthquake) of Kermanshah province. Journal of Sustainable Urban & Regional Development Studies (JSURDS), 2(1), 17-36. (In Persian)https://www.srds.ir/article_132471.html?lang=en

17. Moavi, M., Entezari, M., & Elmizadeh, H. (2025). Investigating the effect of geomorphological characteristics on landslide patterns using the Random Forest algorithm (Study area: Shahid Abbaspour Dam Watershed). Environmental Hazards. Advance online publication. (In Persian). https://doi.org/10.22111/jneh.2025.51425.2107

18. Moghim, H., & Nejabat, M. (2019). Technical report: Efficiency comparison of modified Nilson and relative effect models in landslide hazard zonation of Parsian Dam Watershed, Fars Province. Watershed Engineering and Management, 11(1), 264–272. (In Persian)

19. Negahban, S., Marhamat, M., & Alinejad, H. (2025). Evaluation and susceptibility zonation of landslides using machine learning algorithms (Case study: Margoon Watershed, Fars Zagros). Quantitative Geomorphology, 14(2). https://doi.org/10.22034/gmpj.2025.474854.1519 (In Persian)

20. Sadati, S. H., Mousavi, S. R., Vahabzadeh Kebria, G., & Roshan, S. H. (2025). Evaluation of Random Forest and Support Vector Machine models in mapping landslide susceptibility (Case study: Tajan Watershed, Mazandaran Province). Environmental Hazards, 14(45), 133–154. (In Persian)

21. Sepehrvand, A., & Beiranvand, N. (2024). Landslide susceptibility mapping using machine learning algorithms (Study area: A part of Haraz Watershed). Water and Soil Modeling and Management, 4(2), 261–278. (In Persian)

22. Sharifi, Z. (2025). Analysis and assessment of landslide risk using Analytic Network Process (ANP) model (Case study: Siahrood Watershed, Guilan Province). Studies of Urban and Regional Sustainable Development. https://www.srds.ir/article_226425.html (In Persian)

23. Tian, N., & Lan, H. (2023). The indispensable role of resilience in rational landslide risk management for social sustainability. Geography and Sustainability, 4, 70–83. https://doi.org/10.1016/j.geosus.2022.12.003

24. Wang, X., Wang, Y., Lin, Q., & Yang, X. (2023). Assessing global landslide casualty risk under moderate climate change based on multiple GCM projections. International Journal of Disaster Risk Science, 14, 751–767. https://doi.org/10.1007/s13753-023-00473-0

25. Zhang, Z., & Sun, J. (2024). Regional landslide susceptibility assessment and model adaptability research. Remote Sensing, 16, 2305. https://doi.org/10.3390/rs16122305