Improving Landslide Susceptibility Mapping via Non-Landslide Sampling Strategies
Received: 3 September 2025 | Revised: 11 October 2025, 22 October 2025, 25 October 2025, 28 October 2025, and 29 October 2025 | Accepted: 1 November 2025 | Online: 4 December 2025
Corresponding author: Mastura Azmi
Abstract
This study assesses the impact of non-landslide sample selection on landslide susceptibility mapping. Two strategies were compared: (i) randomly selecting negatives outside buffers around mapped landslides (S1) and (ii) a targeted, threshold-and-buffer method (S2). A dataset from Sulaymaniyah Governorate, Iraq, including 148 landslides and 434 non-landslide points, was modeled using Logistic Regression (LG) with 14 conditioning factors derived in ArcGIS. Factors were ranked using the Frequency Ratio (FR). The five most influential ones—slope, Topographic Wetness Index (TWI), soil, Normalized Difference Vegetation Index (NDVI), and Land Use Land Cover (LULC)—were binary-reclassified to delineate safe zones. Additionally, S2-negative samples were collected within a 500–750 m annulus. Performance was evaluated using confusion matrices and Receiver Operating Characteristic – Area Under the Curve (ROC–AUC) on a 75/25 split. S2 achieved accuracy of 89.6%, precision of 77.5%, and AUC of 93.7%, outperforming S1 (85.4%, 70.0%, 91.2%). When validation was limited to landslide points, S1 exhibited a slightly higher AUC (88.4% vs. 85.3%), indicating greater sensitivity but lower precision. Results show that threshold-guided, proximity-constrained negatives enhance class separation and lower false positives without altering the learning algorithm, supporting their application for more reliable susceptibility mapping.
Keywords:
landslide susceptibility, logistic regression, non-landslide point selection, random selection, targeted selection, accuracy, precisionDownloads
References
R. Kumar and J. Singh, "Application of the RUSLE Modeling Tool for Quantification of Soil Erosion towards Sustainable Planning: The Case of Kosi River Basin, Bihar, India," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19910–19916, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9088
M. Ado et al., "Landslide Susceptibility Mapping Using Machine Learning: A Literature Survey," Remote Sensing, vol. 14, no. 13, Jan. 2022, Art. no. 3029. DOI: https://doi.org/10.3390/rs14133029
C. Xi et al., "Effectiveness of Newmark-based sampling strategy for coseismic landslide susceptibility mapping using deep learning, support vector machine, and logistic regression," Bulletin of Engineering Geology and the Environment, vol. 81, no. 5, Apr. 2022, Art. no. 174. DOI: https://doi.org/10.1007/s10064-022-02664-5
T. Gu, P. Duan, M. Wang, J. Li, and Y. Zhang, "Effects of non-landslide sampling strategies on machine learning models in landslide susceptibility mapping," Scientific Reports, vol. 14, no. 1, Mar. 2024, Art. no. 7201. DOI: https://doi.org/10.1038/s41598-024-57964-5
E. Bueechi, J. Klimeš, H. Frey, C. Huggel, T. Strozzi, and A. Cochachin, "Regional-scale landslide susceptibility modelling in the Cordillera Blanca, Peru—a comparison of different approaches," Landslides, vol. 16, no. 2, pp. 395–407, Feb. 2019. DOI: https://doi.org/10.1007/s10346-018-1090-1
M. Azarafza, M. Azarafza, H. Akgün, P. M. Atkinson, and R. Derakhshani, "Deep learning-based landslide susceptibility mapping," Scientific Reports, vol. 11, no. 1, Dec. 2021, Art. no. 24112. DOI: https://doi.org/10.1038/s41598-021-03585-1
K. Okalp and H. Akgün, "National level landslide susceptibility assessment of Turkey utilizing public domain dataset," Environmental Earth Sciences, vol. 75, no. 9, May 2016, Art. no. 847. DOI: https://doi.org/10.1007/s12665-016-5640-3
L.-L. Liu, S.-L. Zhao, C. Yang, and W. Zhang, "Quantifying uncertainty in landslide susceptibility mapping due to sampling randomness," International Journal of Disaster Risk Reduction, vol. 114, Nov. 2024, Art. no. 104966. DOI: https://doi.org/10.1016/j.ijdrr.2024.104966
F. Huang, K. Yin, J. Huang, L. Gui, and P. Wang, "Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine," Engineering Geology, vol. 223, pp. 11–22, June 2017. DOI: https://doi.org/10.1016/j.enggeo.2017.04.013
W. Jiang, L. Li, and R. Niu, "Impact of Non-Landslide Sample Sampling Strategies and Model Selection on Landslide Susceptibility Mapping," Applied Sciences, vol. 15, no. 4, Jan. 2025, Art. no. 2132. DOI: https://doi.org/10.3390/app15042132
A.-X. Zhu et al., "A similarity-based approach to sampling absence data for landslide susceptibility mapping using data-driven methods," CATENA, vol. 183, Dec. 2019, Art. no. 104188. DOI: https://doi.org/10.1016/j.catena.2019.104188
Z. Guo, B. Tian, Y. Zhu, J. He, and T. Zhang, "How do the landslide and non-landslide sampling strategies impact landslide susceptibility assessment? — A catchment-scale case study from China," Journal of Rock Mechanics and Geotechnical Engineering, vol. 16, no. 3, pp. 877–894, Mar. 2024. DOI: https://doi.org/10.1016/j.jrmge.2023.07.026
T. Kavzoglu, E. K. Sahin, and I. Colkesen, "Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression," Landslides, vol. 11, no. 3, pp. 425–439, June 2014. DOI: https://doi.org/10.1007/s10346-013-0391-7
L. V. Lucchese, G. G. de Oliveira, and O. C. Pedrollo, "Investigation of the influence of nonoccurrence sampling on landslide susceptibility assessment using Artificial Neural Networks," CATENA, vol. 198, Mar. 2021, Art. no. 105067. DOI: https://doi.org/10.1016/j.catena.2020.105067
K. Okalp and H. Akgün, "Landslide susceptibility assessment in medium-scale: case studies from the major drainage basins of Turkey," Environmental Earth Sciences, vol. 81, no. 8, Apr. 2022, Art. no. 244. DOI: https://doi.org/10.1007/s12665-022-10355-3
Z. Chang, J. Huang, F. Huang, K. Bhuyan, S. R. Meena, and F. Catani, "Uncertainty analysis of non-landslide sample selection in landslide susceptibility prediction using slope unit-based machine learning models," Gondwana Research, vol. 117, pp. 307–320, May 2023. DOI: https://doi.org/10.1016/j.gr.2023.02.007
X. Liu, S. Shao, and S. Shao, "Landslide susceptibility prediction and mapping in Loess Plateau based on different machine learning algorithms by hybrid factors screening: Case study of Xunyi County, Shaanxi Province, China," Advances in Space Research, vol. 74, no. 1, pp. 192–210, July 2024. DOI: https://doi.org/10.1016/j.asr.2024.03.074
Y. Zhang et al., "Comparison of LR, 5-CV SVM, GA SVM, and PSO SVM for landslide susceptibility assessment in Tibetan Plateau area, China," Journal of Mountain Science, vol. 20, no. 4, pp. 979–995, Apr. 2023. DOI: https://doi.org/10.1007/s11629-022-7685-y
D. Anil and S. H. Manjula, "High-Precision Landslide Susceptibility Mapping Using CNN-LSTM-Attention Models," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25486–25491, Aug. 2025. DOI: https://doi.org/10.48084/etasr.11505
N. F. Naser, I. F. Ibraheem, M. AlHadithi, and F. J. Yosief, "Estimation of land surface temperature based on GIS and remote sensing data in Dahuk city," Geodesy and Cartography, vol. 51, no. 2, pp. 61–66, May 2025. DOI: https://doi.org/10.3846/gac.2025.21047
N. F. Naser, I. F. Ibraheem, and M. AlHadithi, "Integrated index analysis for monitoring urban growth based on GIS and remote sensing data in Karbala province, Iraq," Geodesy and Cartography, vol. 51, no. 3, pp. 131–140, Aug. 2025. DOI: https://doi.org/10.3846/gac.2025.19884
I. F. Ibraheem and M. Al-Hadithi, "Application of remote sensing and GIS techniques in integrated management of changes in LULC and effective community participation in Baghdad-Aldora," AIP Conference Proceedings, vol. 3105, no. 1, Aug. 2024, Art. no. 050092. DOI: https://doi.org/10.1063/5.0212230
D. Anil and S. H. Manjula, "Assessing Land Use and Land Cover Changes in Karnataka’s Western Ghats Using the GeoML-LULC Framework," Journal of The Institution of Engineers (India): Series A, vol. 106, no. 3, pp. 749–762, Sept. 2025. DOI: https://doi.org/10.1007/s40030-025-00898-6
Y. Fu et al., "The Influence of Non-Landslide Sample Selection Methods on Landslide Susceptibility Prediction," Land, vol. 14, no. 4, Apr. 2025, Art. no. 722. DOI: https://doi.org/10.3390/land14040722
Downloads
How to Cite
License
Copyright (c) 2025 Israa Fadhil Ibraheem, Mastura Azmia, Muhammad Wafiy Adli Ramli
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
