Authors

Affiliations

1 Graduate University of Science and Technology, Vietnam Academy of Science and Technology; phanthimaihoa@humg.edu.vn

2 Hanoi University of Mining and Geology; tranhonghanh@humg.edu.vn; nguyenquocphi@humg.edu.vn; phamthithanhhoa@humg.edu.vn

*Corresponding author: tranhonghanh@humg.edu.vn; Tel.: +84–988150099

Abstracts

Ha Quang District, situated within the Non Nuoc Cao Bang Geopark, is an area of significant geological, ecological, and cultural value and has been recognized by UNESCO as a member of the Global Geoparks Network. However, the region is also prone to various geological hazards, with landslides representing a primary concern. This study aims to apply the Dempster-Shafer (DS) theory and Certainty Factor (CF) to analyze landslide susceptibility in the study area using a Geographic Information System (GIS). A total of 196 landslides were documented using historical records, Google Earth imagery, and field surveys to create a comprehensive inventory map. Seven conditioning factors, including slope, Topographic Roughness Index (TRI), Topographic Wetness Index (TWI), Stream Power Index (SPI), Mass Balance Index (MBI), Normalized Difference Vegetation Index (NDVI), and rainfall, were integrated as thematic layers for analysis. The belief map, representing the most reliable integrated landslide susceptibility model, was assessed using receiver operating characteristic (ROC) analysis and area under the curve (AUC). The evaluation revealed that the model achieved an overall accuracy of 74.5%. To compare performance, the Certainty Factor (CF) model was also applied, obtaining a success rate of 67%. The results indicated that the Dempster-Shafer (DS) theory demonstrated superior predictive capability over the CF model. It addresses a critical gap in landslide susceptibility research by improving predictive accuracy compared to traditional GIS, particularly in handling uncertainty through the Dempster-Shafer theory. These findings are crucial for developing effective landslide risk mitigation strategies and optimizing land-use planning to enhance infrastructure protection and sustainable development.

Keywords

Cite this paper

Hoa, P.T.M.; Hanh, T.H.; Phi, N.Q.; Hoa, P.T.T. Integrating Dempster-Shafer theory, certainty factors and topographic indices for landslide susceptibility analysis in Ha Quang district, Cao Bang province. J. Hydro-Meteorol. 2025, 23, 72-87.

References

1. Kumar, P. Social and economic impact in the landslide prone zones and related policies. Landslides in the Himalayan Region: Risk Assessment and Mitigation Strategy for Sustainable Management. Springer Nature Singapore, 2024, pp. 499-529.

2. Tangestani, M.H. A comparative study of dempster-shafer and fuzzy models for landslide susceptibility mapping using a GIS: an experience from Zagros Mountains, SW Iran. J. Asian Earth Sci. 2009, 35(1), 66–73.

3. Sana, E.; Kumar, A.; Robson, E.; Prasanna, R.; Kala, U.; Toll, D.G. Preliminary assessment of series of landslides and related damage by heavy rainfall in Himachal Pradesh, India, during July 2023. Landslides 2024, 21, 919–931.

4. Chen, W.; Pourghasemi, H.R.; Panahi, M.; Kornejady, A.; Wang, J.; Xie, X.; Cao, S. Spatial prediction of landslide susceptibility using an adaptive neuro-fuzzy inference system combined with frequency ratio, generalized additive model, and support vector machine techniques. Geomorphology 2017, 297, 6985.

5. Zhang, T.; Wang, D.; Lu, Y. Machine Learning-Enabled Regional Multi-Hazards Risk Assessment Considering Social Vulnerability. Sci. Rep. 2023, 13(1), 13405.

6. Moayedi, H.; Mehrabi, M.; Mosallanezhad, M.; Rashid, A.S.A.; Pradhan, B. Modification of landslide susceptibility mapping using optimized PSO-ANN technique. Eng. Comput. 2019, 35, 967–984.

7. Teng, F.; Mao, Y.; Li, Y.; Qian, S.; Nanehkaran, Y. A. Comparative models of support-vector machine, multilayer perceptron, and decision tree‎ predication approaches for landslide‎ susceptibility analysis. Open Geosci. 2024, 16(1), 20220642.

8. Lamichhane, S.; Kansakar, A.R.; Devkota, N.; Dahal, B.K. Integrating dynamic factors for predicting future landslide susceptibility. Environ. Earth Sci. 2025, 84(3), 89.

9. Agboola, G.; Beni, L.H.; Elbayoumi, T.; Thompson, G. Optimizing landslide susceptibility mapping using machine learning and geospatial techniques. Ecol. Inf. 202481, 102583.

10. Qiu, H.; Xu, Y.; Tang, B.; Su, L.; Li, Y.; Yang, D.; Ullah, M. Interpretable landslide susceptibility evaluation based on model optimization. Land 202413(5), 639.

11. Sentz, K.; Ferson, S. Combination of evidence in Dempster-Shafer theory, Citeseer 2002, pp. 1-96.

12. Yang, Q.; Yunjun, Z.; Wang, Y.; Aoki, Y.; Wang, R. Monitoring landslides along the Jinsha river basin based on dempster-shafer evidence theory with multi-source INSAR time series. IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, 2024.

13. Park, N.W. Application of Dempster-Shafer theory of evidence to GIS-based landslide susceptibility analysis. Environ. Earth Sci. 201162, 367–376.

14. Pourghasemi, H.; Pradhan, B.; Gokceoglu, C.; Moezzi, K.D. A comparative assessment of prediction capabilities of Dempster–Shafer and weights-of-evidence models in landslide susceptibility mapping using GIS. Geomatics Nat. Hazards Risk 20134(2), 93–118.

15. Chen, W.; Pourghasemi, H.R.; Zhao, Z. A GIS-based comparative study of Dempster-Shafer, logistic regression and artificial neural network models for landslide susceptibility mapping. Geocarto Int. 201732(4), 367–385.

16. Gudiyangada Nachappa, T.; Tavakkoli Piralilou, S.; Ghorbanzadeh, O.; Shahabi, H.; Blaschke, T. Landslide susceptibility mapping for Austria using geons and optimization with the Dempster-Shafer theory. Appl. Sci. 20199(24), 5393.

17. Ishola, K.S.; Bakare, M.O.; Hamid-Mosaku, A.I.; Okolie, C.J.; Olagunju, K.T.; Oshikoya, O.M. Fusion of GIS, remote sensing, geophysics and Dempster Shafer theory of evidence for mapping groundwater prospectivity: A case study of the central parts of Lagos State, Nigeria. Solid Earth Sci. 20249(3), 100196.

18. General Statistics Office. Online available: https://www.gso.gov.vn/.

19. USGS. Online available: https://earthexplorer.usgs.gov/

20. Pradhan, A.M.S.; Kim, Y.T. Spatial data analysis and application of evidential belief functions to shallow landslide susceptibility mapping at Mt. Umyeon, Seoul, Korea. Bull. Eng. Geol. Environ. 2017, 76, 1263–1279.

21. Guo, W.; Ye, J.; Liu, C.; Lv, Y.; Zeng, Q.; Huang, X. An approach for predicting landslide susceptibility and evaluating predisposing factors. Int. J. Appl. Earth Obs. Geoinf. 2024, 135, 104217.

22. Wang, G.; Chen, X.; Chen, W. Spatial prediction of landslide susceptibility based on GIS and discriminant functions. ISPRS Int. J. Geo-Inf. 2020, 9(3), 144.

23. Moore, I.D.; Grayson, R.B.; Ladson, A.R. Digital terrain modelling: A review of hydrological, geomorphological, and biological applications. Hydrol. Processes 19915(1), 3-30.

24. Riley, S.; Degloria, S.; Elliot, S.D. A Terrain Ruggedness Index that Quantifies Topographic Heterogeneity. Int. J. Sci. 1999, 5, 23–27.

25. Beven, K.J.; Kirkby, M.J. A physically based, variable contributing area model of basin hydrology. Hydrol. Sci. Bull. 197924(1), 43–69.

26. Möller, M.; Volk, M.; Friedrich, K.; Lymburner, L. Placing soil‐genesis and transport processes into a landscape context: a multiscale terrain‐analysis approach. J. Plant Nutr. Soil Sci. 2008171(3), 419–430.

27. Fei, L.; Li, T.; Ding, W. Dempster–Shafer theory-based information fusion for natural disaster emergency management: A systematic literature review. Inf. Fusion 2024, 112, 102585.

28. Dempster, A.P. Upper and lower probabilities induced by a multivalued mapping. Ann. Math. Stat. 1967, 38(2), 325–339.

29. Chung, C.J.F.; Fabbri, A.G. The representation of geoscience information for data integration. Nonrenewable Resour. 1993, 2, 122–139.

30. Oke, J.; Akinkunmi, W.B.; Etebefia, S.O. Use of correlation, tolerance, and variance inflation factor for multicollinearity test. Global Sci. J. 2019, 7(5), 652–659.

31. Pradhan, B. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Comput. Geosci. 2013, 51, 350–365.

32. Qiu, H.; Cui, Y.; Hu, S.; Yang, D.; Pei, Y.; Ma, S.; Liu, Z. Size distribution and size of loess slides in response to slope height and slope gradient based on field survey data. Geomatics Nat. Hazards Risk 2019, 10(1), 1443–1458.