Assessing the accuracy of machine learning models in landslide susceptibility zoning

rostamizad, ghobad; shirani, kourosh; abdollahi, Zahra; Shademan, hasan

doi:10.61882/jeer.16.2.3

year 16, Issue 2 (Summer 2026) E.E.R. 2026, 16(2): 131-153 | Back to browse issues page

‎ 10.61882/jeer.16.2.3

Mendeley

Zotero

RefWorks

rostamizad G, shirani K, abdollahi Z, Shademan H. Assessing the accuracy of machine learning models in landslide susceptibility zoning. E.E.R. 2026; 16 (2) :131-153
URL: http://magazine.hormozgan.ac.ir/article-1-912-en.html

Assessing the accuracy of machine learning models in landslide susceptibility zoning

Ghobad Rostamizad ^*

, Kourosh Shirani

, Zahra Abdollahi

, Hasan Shademan

Soil Conservation and Watershed Management Research Department, Zanjan Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Zanjan, Iran. , rostamizad60@gmail.com

Abstract: (333 Views)

Landslides are natural disasters that cause destructive effects on infrastructure and the environment. The main objective of this study is to evaluate the accuracy and reliability of various machine learning models—including Maximum Entropy, Random Forest, and Support Vector Machines—in predicting landslide occurrence using 16 influential factors in the Chesb watershed of Zanjan province. Using 70% of landslide occurrences for training and 30% for validation, the models' accuracies were assessed. The Maximum Entropy model results showed that 49.83% of the area falls into very low and low susceptibility classes, 30.17% in the moderate susceptibility class, and 20% in the high and very high susceptibility classes, with an area under the ROC curve (AUC) of 0.911, indicating good model performance. The Random Forest model indicated that 74.31% of the area belongs to the very low and low susceptibility classes, 12.94% to the moderate class, and 12.76% to the high and very high susceptibility classes, with an AUC of 0.934. Likewise, the Support Vector Machine model provided similar results, with 73.05% of the area in very low and low susceptibility classes, 8.15% in the moderate class, and 18.83% in the high and very high classes, with an AUC of 0.873. Based on these evaluations, the Random Forest model was identified as the best model, offering high accuracy in predicting landslide hazards and strong alignment with the real conditions of the region.

Keywords: Chesb watershed, landslide, landslide susceptibility, machine learning models, risk

Full-Text [PDF 843 kb] (29 Downloads)

Received: 2025/10/6 | Published: 2026/08/16

References

1. Asgari, Sh., & Shirani, K. (2026). Zoning and assessing the sensitivity of gully erosion using the maximum entropy model in the Ilam watershed, Environmental Erosion Researches, 15(4), 124-148. (in Persian).

2. Badola, S., Mishra, V. N., & Parkash, S. (2023). Landslide susceptibility mapping using XGBoost machine learning method. In 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS) (pp. 1-4). IEEE. [DOI:10.1109/MIGARS57353.2023.10064496]

3. Chen, X., & Chen, W. (2021). GIS-based landslide susceptibility assessment using optimized hybrid machine learning methods. Catena, 196, 104833. [DOI:10.1016/j.catena.2020.104833]

4. Convertino, M., Troccoli, A., & Catani, F. (2013). Detecting fingerprints of landslide drivers: A MaxEnt model. Journal of Geophysical Research: Earth Surface, 118(3), 1367-1386. [DOI:10.1002/jgrf.20096]

5. Dastrang, A., & Karimi Sangchini, E. (2022). Prediction of landslide susceptibility using the maximum entropy machine learning algorithm (Bar Neyshabur watershed). Earth Science Research, 13(3), 76-96. [DOI:10.30495/researth.2022.19643.1598 (in Persian).]

6. Dastranj A, Vakili tajareh F., Noor H. Evaluation of Hazard Landslide Zonation Using Fuzzy Logic Method in Binalood Mountain. jwmseir 2021; 15 (53) :12-22(in Persian).

7. Davies, T. (2015). Landslide hazards, risks, and disasters: Introduction. In T. Davies (Ed.), Landslide hazards, risks, and disasters (pp. 1-16). Elsevier. https://doi.org/10.1016/B978-0-12-396452-6.00001-X [DOI:10.1016/B978-0-12-396452-6.00001-2]

8. Gao, J., Shi, X., Li, L., Zhou, Z., & Wang, J. (2022). Assessment of landslide susceptibility using different machine learning methods in Longnan City, China. Sustainability, 14(24), 16716. [DOI:10.3390/su142416716]

9. Gopi, B., Premalatha, J., Kalaivani, R., & Ravikumar, D. (2023). Cloud-based landslide detection and alerting nearby people by using IoT technology. In 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS) (pp. 1287-1292). IEEE. [DOI:10.1109/ICAIS56108.2023.10073723]

10. Hallaji, M., Zanganeh Asadi, M. A., & Amirahmadi, A. (2020). Evaluation of the efficiency of landslide susceptibility prediction models in the Bar Neyshabur watershed. Watershed Management Research Journal, 33(2), 20-30. [DOI:10.29252/jwmr.33.2.20 (in Persian)]

11. Hart, A. (2024). Landslides. In G. R. Ciottone (Ed.), Ciottone's disaster medicine (3rd ed., pp. 640-643). Elsevier. https://doi.org/10.1016/B978-0-323-80932-0.00104-X [DOI:10.1016/B978-0-323-80932-0.00097-8]

12. Hong, H., Pradhan, B., Xu, C., & Bui, D. T. (2015). Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines. Catena, 133, 266-281. [DOI:10.1016/j.catena.2015.05.019]

13. Kim, H. G., Lee, D. K., & Park, C. (2018). Assessing the cost of damage and effect of adaptation to landslides considering climate change. Sustainability, 10(5), 1628. [DOI:10.3390/su10051628]

14. Koohpayma, A. (2016). Susceptibility zoning, landslide risk assessment, and management (Case study: Lethyan watershed) [Doctoral dissertation, University of Tehran]. (in Persian)

15. Kornejady, A. (2017). Assessing potential, danger, risk, and preparation of a landslide strategic management plan for Oghan watershed, Golestan Province, Iran [Doctoral dissertation, Gorgan University of Agricultural Sciences and Natural Resources]. (in Persian)

16. Kornejady, A., & Pourghasemi, H. R. (2019). Landslide susceptibility assessment using data mining models: A case study of Chehel-Chai Basin. Journal of Watershed Engineering and Management, 11(1), 28-42. [DOI:10.22092/ijwmse.2019.118436 (in Persian)]

17. Kornejady, A., Ownegh, M., Pourghasemi, H. R., Bahremand, A., & Motamedi, M. (2020). Landslide susceptibility prediction using the coupled Mahalanobis distance and machine learning models (Case study: Owghan watershed, Golestan Province). Earth Science Research, 11(2), 1-18. https://doi.org/10.52547/esrj.11.2.1 [DOI:10.52547/esrj.11.2.1 (in Persian)]

18. Kornejady, A., Pourghasemi, H. R., & Afzali, S. F. (2019). Presentation of RFFR new ensemble model for landslide susceptibility assessment in Iran. In S. Pradhan (Ed.), Landslides: Theory, practice and modelling (pp. 123-143). Springer. https://doi.org/10.1007/978-3-319-77377-3_6 [DOI:10.1007/978-3-319-77377-3_6 (in Persian).]

19. Kornezhadi, A. (2018). Assessment of susceptibility, hazard, and preparation of a strategic landslide management plan for the Oghan watershed, Golestan Province [Doctoral dissertation, Gorgan University of Agricultural Sciences and Natural Resources]. (in Persian)

20. Kornezhadi, A., Ownegh, M., & Saadoddin, A. (2015). Zonation of landslide hazard and damage (Case study: Ziarat watershed, Golestan Province). Crisis Management Quarterly, 7, 51-62. (in Persian)

21. Kunwar, B. B., Muensit, N., Techato, K., & Gyawali, S. (2023). Landslide susceptibility mapping of Phewa watershed, Kaski, Nepal. Research Square. [DOI:10.21203/rs.3.rs-2860742/v1]

22. Kwon, S., Pan, L., Kim, Y., Lee, S. I., Kweon, H., Lee, K., Yeom, K., & Seo, J. I. (2023). Empirical comparison of supervised learning methods for assessing the stability of slopes adjacent to military operation roads. Forests, 14(6), 1237. [DOI:10.3390/f14061237]

23. Kyaw Htun, Cho Thae Oo, Tun Naing Zaw, & Day Wa Aung. (2019). Landslide hazard in Chin State: A case study in Hakha and its environs. In T. Kaneko, S. Ma, & T. Kaneko (Eds.), Population, development, and the environment (pp. 195-213). Springer Nature. https://doi.org/10.1007/978-981-13-2101-6_12 [DOI:10.1007/978-981-13-2101-6_12.]

24. Negahban, S., Merhamat, M., & Alinejad, H., (2015). Landslide susceptibility assessment and zoning with machine learning algorithms (case study of Margoon watershed, Zagros, Fars). Quantitative Geomorphology Research, 14(2), 42-61(in Persian).

25. Lee, S., Hong, S.-M., & Jung, H.-S. (2017). A support vector machine for landslide susceptibility mapping in Gangwon Province, Korea. Sustainability, 9(1), 48. [DOI:10.3390/su9010048]

26. Maodin, M. A., Faryansah, Ariadi, S. D., Verlandi, G. S., & Alpiana, Hidayati. (2023). Analysis of andesite rock slope stability with Bishop method. IOP Conference Series: Earth and Environmental Science, 1175, 012007. [DOI:10.1088/1755-1315/1175/1/012007]

27. Mas, J.-F., Soares Filho, B., Pontius, R. G., Jr., Farfán Gutiérrez, M., & Rodrigues, H. (2013). A suite of tools for ROC analysis of spatial models. ISPRS International Journal of Geo-Information, 2(3), 869-887. [DOI:10.3390/ijgi2030869]

28. May Thu, N., Mar Mar Aye, & Kyaw Lwin, O. (2022). Rainfall and landslide susceptibility in Hakha environ in Northern Chin State, Myanmar. British Journal of Arts and Humanities, 4(4), 1-14. [DOI:10.34104/bjah.02201014]

29. Mohammadi, M., & Pourghasemi, H. R. (2017). Prioritization of factors affecting landslide occurrence and preparation of its susceptibility map using the novel random forest algorithm (Case study: Part of Golestan Province). Watershed Management Research Journal, 8(15), 161-170. https://doi.org/10.29252/jwmr.8.15.161 [DOI:10.29252/jwmr.8.15.161 (in Persian)]

30. Mohammadi, M., & Pourghasemi, H. R. (2017). Prioritization of landslide-conditioning factors and landslide susceptibility mapping using the novel random forest algorithm (Case study: A part of Golestan Province). Watershed Management Research Journal, 8(15), 161-170. https://doi.org/10.29252/jwmr.8.15.161 [DOI:10.29252/jwmr.8.15.161 (in Persian)]

31. Peng, L., Niu, R., Huang, B., Wu, X., Zhao, Y., & Ye, R. (2014). Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China. Geomorphology, 204, 287-301. [DOI:10.1016/j.geomorph.2013.08.013]

32. Pham, B. T., Pradhan, B., Bui, D. T., Prakash, I., & Dholakia, M. B. (2016). A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India). Environmental Modelling & Software, 84, 240-250. [DOI:10.1016/j.envsoft.2016.07.005]

33. Phillips, S. J., Anderson, R. P., & Schapire, R. E. (2006). Maximum entropy modeling of species geographic distributions. Ecological Modelling, 190(3-4), 231-259. [DOI:10.1016/j.ecolmodel.2005.03.026]

34. Pourghasemi, H. R., & Rahmati, O. (2018). Prediction of the landslide susceptibility: Which algorithm, which precision? Catena, 162, 177-192. [DOI:10.1016/j.catena.2017.11.022]

35. Rahmati, O., Kornejady, A., & Deo, R. C. (2021). Spatial prediction of landslide susceptibility using random forest algorithm. In A. Sidhu, T. Singh, & J. P. Singh (Eds.), Intelligent data analytics for decision-support systems in hazard mitigation: Theory and practice of hazard mitigation (pp. 281-292). Springer. [DOI:10.1007/978-981-15-5772-9_15]

36. Schuster, R. L., & Wieczorek, G. F. (2018). Landslide triggers and types. In G. F. Wieczorek & J. C. Snyder (Eds.), Landslides (pp. 59-78). Routledge. https://doi.org/10.1201/9780203749197-4 [DOI:10.1201/9781351435833-4]

37. Shahabi, H., Ahmadi, R., Alizadeh, M., Hashim, M., Al-Ansari, N., Shirzadi, A., Wolf, I. D., & Ariffin, E. H. (2023). Landslide susceptibility mapping in a mountainous area using machine learning algorithms. Remote Sensing, 15(12), 3112. [DOI:10.3390/rs15123112]

38. Tabaraki, S., Zakeri Nejad, R., & Khosravi, I,. (1405). Assessment and prediction of landslide susceptibility using advanced machine learning algorithms (Study area: Alvand watershed). Geography and Environmental Planning, 35 (1).1-15(in Persian)Talebi, T., 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). Journal of Natural Environment Hazards, 7(16), 45-64. [DOI:10.22111/jneh.2018.5972 (in Persian)]

39. Thakur, N., & Sharma, S. (2022). Study of sustainable techniques for effective risk management and control: A review. International Journal of Research in Applied Science & Engineering Technology, 10(7), 1688-1696. [DOI:10.22214/ijraset.2022.45109]

40. Wang, H., Zhang, L., Yin, K., Luo, H., & Li, J. (2021). Landslide identification using machine learning. Geoscience Frontiers, 12(2), 351-364. [DOI:10.1016/j.gsf.2020.02.012]

41. Woodard, J. B., Mirus, B. B., Crawford, M. M., Or, D., Leshchinsky, B. A., Allstadt, K. E., & Wood, N. J. (2023). Mapping landslide susceptibility over large regions with limited data. Journal of Geophysical Research: Earth Surface, 128(3), e2022JF006810. [DOI:10.1029/2022JF006810]

42. Yamani, M., Ahmadabadi, A., & Zare, G. (2012). Application of support vector machine algorithm in landslide hazard zonation (Case study: Darakeh watershed). Geography and Environmental Hazards Journal, (7), 125-142. [DOI:10.22067/geoeh.v0i7.18416 (in Persian)]

43. Yarahmadi, J., Amini, A., & Rostamizad, G. (2023). Evaluation of the accuracy of pistachio climatic suitability map using the ROC curve. Journal of Environment and Water Engineering, 9(1), 127-140. [DOI:10.22034/jewe.2023.384054.1870 (in Persian)]

44. Yasukuni, O., & Soe, M. (2017). Report of life with landslides in Myanmar. [Publisher not specified].

45. Zhang, W., Li, H., Han, L., Chen, L., & Wang, L. (2022). Slope stability prediction using ensemble learning techniques: A case study in Yunyang County, Chongqing, China. Journal of Rock Mechanics and Geotechnical Engineering, 14(4), 1089-1099. [DOI:10.1016/j.jrmge.2021.12.011]

46. Zhou, C., Wang, Y., Cao, Y., Singh, R. P., Ahmed, B., Motagh, M., Wang, Y., & Chen, L. (2023). Non-landslide sampling and ensemble learning techniques to improve landslide susceptibility mapping. Natural Hazards and Earth System Sciences. [DOI:10.5194/nhess-2023-44]

47. Zhou, C., Yin, K., Cao, Y., Ahmed, B., Li, Y., Catani, F., & Pourghasemi, H. R. (2018). Landslide susceptibility modeling applying machine learning methods: A case study from Longju in the Three Gorges Reservoir area, China. Computers & Geosciences, 112, 23-37. [DOI:10.1016/j.cageo.2017.11.019]