Landslide Risk Zoning Using Machine Learning Algorithm Modeling Technique (Case Study: Izeh County)

Document Type : Applied Article

Authors

1 Department of Geography, Cha.C.Islamic Azad University, Chalous, Iran

2 Department of Geography, Mahs.C. Islamic Azad University, Mahshahr, Iran

10.22059/jhsci.2025.394488.879

Abstract

Objective:  Landslide risk zoning can be an effective reference for natural hazard reduction and land use planning, but the modeling process involves multidisciplinary knowledge, which leads to its complexity. This research aims to zoning landslide risk in Izeh County using the MLR machine learning algorithm modeling technique.
Method: In this study, modeling was applied by considering fourteen predictors. Thematic layers of all predictors and landslides were prepared in ArcMap 10.8, SAGA-GIS 9.0.1, Rstudio, ENVI 5.6, and mainly from DEM-based derivatives and field data to prepare predictor data layers.
Results: The modeling results showed that the MLR algorithm, with a kappa coefficient of 0.9711, RMSE of 0.0102, and R² of 0.9812, has a very accurate performance in predicting and explaining landslide risk. These figures indicate a high agreement between the actual and predicted values and a high explanatory power of the model. Among the identified effective factors, distance from roads (with an importance coefficient of 0.73), slope (0.62), geology (0.54), and distance from the river (0.42) had the greatest impact on the occurrence of landslides. Also, pressure from road construction, radiation direction, increasing slope, and the soft nature of Gachsaran rocks, marl, and Quaternary sediments were identified as factors that exacerbate slope instability. In contrast, faults, elevation, and topographic moisture index have shown a reducing or neutral effect on the occurrence of landslides. Based on the hazard zoning map produced by the MLR model, about 21.7 percent of the area (equivalent to 96,905 hectares) is in the "hazardous" class and 15.3 percent (20,338 hectares) is in the "very hazardous" class.
Conclusions:  This indicates that a significant part of the region, especially the southern regions, is highly susceptible to landslides, which doubles the need for preventive management measures

Keywords

References

  • ایلانلو، مریم؛ و ابراهیمی، لیلا (1۳۹۵). پهنه‌بندی خطر وقوع حرکات توده‌ای با استفاده از مدل‌های ارزش اطلاعاتی، تراکم سطح و LNRF در حوضة آبخیز زهره، مدیریت مخاطرات محیطی، ۳(2)، 141-153.
  • اصغری سراسکانرود، صیاد؛ محمدزاده شیشه‌گران، مریم؛ و اصغری سراسکانرود، صالح (1401). پهنه‌بندی و برآورد میزان حرکات دامنه‌ای و مخاطرات آن در شهرستان هشترود با استفاده از تداخل‌سنجی راداری و مدل MABAC، مدیریت مخاطرات محیطی، 9(2)، 133-150.
  • رئیسیان، میثم؛ ایلانلو، مریم؛ ابراهیمی، لیلا؛ و بزرگمهر، کیا (1۳۹۹). تحلیل جامع تاب‌آوری شهری در مواجهه با خطر وقوع زلزله (مطالعۀ موردی: شهر ساری)، مدیریت مخاطرات طبیعی، ۷(۴)، 383-400.
  • کشاورز، سیده ساناز؛ بیاتی اشکفتکی، جلال؛ و المدرسی، سیدرضا (1401). تحلیل مکانی مقدار زمین‌لغزش با استفاده از روش تداخل‌سنجی راداری به‌منظور کاهش مخاطرات (مطالعۀ موردی: منطقۀ سرباز در استان اصفهان)، مدیریت مخاطرات طبیعی، 9(3)، 271-288.
  • معماری، گلان؛ شهابی، هیمن؛ و زندی، جلال (1402). پهنه‌بندی خطر زمین‌لغزش در محور بوکان- سردشت با استفاده از مدل‌های شواهد وزنی و تابع شواهد قطعی، مدیریت مخاطرات طبیعی، 10(2)، 165-181.
  • Addis, A. (2023). GIS– based flood susceptibility mapping using frequency ratio and information value models in upper Abay River basin, Ethiopia. Natural Hazards Research, 12(3), 247–256.
  • Asghari Saraskanroud, S., Mohammadzadeh Shishegaran, M., & Asghari Saraskanroud, S. (2022). Zoning and estimation of slope movements and their hazards in Hashtroud County using radar interferometry and MABAC model. Environmental Hazards Management, 9(2), 133–150.(in Persian)
  • Asmare, D., & Tesfa, C. (2022). Application and validation of the evaluation using slope stability susceptibility evaluation parameter rating system to debre werk area (Northwest Ethiopia). Geotech. Eng. 24(40), 2475–2488.
  • Asmare, D., Tesfa, C., & Zewdie, M.M. (2023). A GIS-based landslide susceptibility assessment and mapping around the Aba Libanos area, Northwestern Ethiopia. Applied Geomatics 15(3), 265–280.
  • Bragagnolo, L., Rezende, R., da Silva, R.V., & Grzybowski,
    J.M.V. (2021). Convolutional neural networks applied to semantic segmentation of landslide scars, Catena, 201(5), 105189.
  • Baeza, C., Lantada, N. & Amorim, S. (2016). Statistical and spatial analysis of landslide susceptibility maps with different classification systems, Environ. Earth Sci. 75(2), 1318.
  • Chen, X., Zhao, C., Xi, J., Lu, Z., Ji, S., & Chen, L. (2022). Deep learning method of landslide inventory map with imbalanced samples in optical remote sensing, Remote Sens,14(21) 5517.
  • Chen, W. Li, W., Hou, E., Zhao, Z., Deng, N., Bai, H., & Wang, D. (2024). Landslide susceptibility mapping based on gis and information value model for the chencang district of baoji, China, Arab. J. Geosci. 7(2), 4499–4511.
  • Crozier, M.J., & Glade, T. (2025). Landslide hazard and risk: issues, concepts and approach. Landslide hazard and risk. 34(23), 1–40.
  • Guzzetti, F., Carrara, A., Cardinali, M., & Reichenbach, P. (2025). Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, Central Italy. Geomorphology, 12(31), 181–216.
  • Guo, , Tian, B., He, J., Xu, C., Zeng, T., Zhu, Y. (2023). Hazard assessment for regional typhoon-triggered landslides by using physically-based model – a case study from. southeastern China, Georisk, 17(4) 740–754.
  • Guo, , Torra, O., Hürlimann, M., Medina, V., & Puig-Polo, C. (2022). FSLAM: a QGIS plugin for fast regional susceptibility assessment of rainfall-induced landslides, Environ. Model. Software, 19(150), 105354.
  • Guo, Z. L. Chen, K. Yin, D.P. Shrestha, L. Zhang, (2020). Quantitative risk assessment of slow-moving landslides from the viewpoint of decision-making: a case study of the three gorges reservoir in China, Eng. Geol. 34(273), 105667
  • Ilanloo, M. (2011). A comparative study of fuzzy logic approach for landslide susceptibility mapping using GIS: An experience of Karaj dam basin in Iran, Procedia - Social and Behavioral Sciences, 22(19), 668-676
  • Keshavarz, S.S., Bayati Ashkaftaki, J., & Al-Modarresi, S.R. (2022). Spatial analysis of landslide magnitude using radar interferometry method for hazard reduction (Case study: Sarbaz area in Isfahan province). Natural Hazards Management, 9(3), 271–288. .(in Persian)
  • Ilanloo, M., & Ebrahimi, L. (2016). Landslide hazard zoning using information value, surface density, and LNRF models in the Zohreh watershed. Environmental Hazards Management, 3(2), 141–153.(in Persian)
  • Kim, , Lee, J. Park, H. & Heo, J. (2021). Assessment of temporal probability for rainfall-induced landslides based on nonstationary extreme value analysis, Eng. Geol. 76(29),4 106372.
  • Lombardo, L., Tanyas, H., & Nicu, I.C. (2020). Spatial modeling of multi-hazard threat to cultural heritage sites, Eng. Geol. 277(33), 105776.
  • Lu, P., Shi, W., Wang, Q., Li, Z., Qin, Y., & Fan, X. (2021). Co-seismic landslide mapping using sentinel-2 10-m fused nir narrow, red-edge, and swir bands, Landslides, 18(4). 2017–2037.
  • Medina, V. Hürlimann, M., Guo, Z., Lloret, A. & Vaunat, J. (2021). Fast physically-based model for rainfall-induced landslide susceptibility assessment at regional scale, Catena, 67(201), 105213
  • Pei, Y. H. Qiu, D. Yang, Z. Liu, S. Ma, J. Li, M. Cao, W. Wufuer, (2023). Increasing landslide activity in the taxkorgan river basin (eastern pamirs plateau, China) driven by climate change, Catena, 78(223), 106911
Environmental Management Hazards
Volume 12, Issue 1
April 2025
Pages 51-64

Files

Share

How to cite

Statistics