EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluation of landslide susceptibility based on SMOTE-Tomek sampling and machine learning algorithm

Ming-Zhou Lv, Kun-Lun Li, Jia-Zeng Cai, Jun Mao, Jia-Jun Gao, Hui Xu iD

PLOS One · 21.05.2025 · 20 (5) · e0323487

DOI: 10.1371/journal.pone.0323487 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 21.05.2025. Verfasst von Ming-Zhou Lv und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil Engineering and Architecture, Zhejiang Sci-Tech University, Hangzhou, China. Hauptthemen laut MEDLINE: Machine Learning, Landslides. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: his research was funded by the National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Landslides are frequent and hazardous geological disasters, posing significant risks to human safety and infrastructure. Accurate assessments of landslide susceptibility are crucial for risk management and mitigation. However, geological surveys of landslide areas are typically conducted at the township level, have lowsample sizes, and rely on experience. This study proposes a framework for assessing landslide susceptibility in Taiping Township, Zhejiang Province, China, using data balancing, machine learning, and data from 1,325 slope units with nine slope characteristics. The dataset was balanced using the Synthetic Minority Oversampling Technique and the Tomek link undersampling method (SMOTE-Tomek). A comparative analysis of six machine learning models was performed, and the SHapley Additive exPlanation (SHAP) method was used to assess the influencing factors. The results indicate that the machine learning algorithms provide high accuracy, and the random forest (RF) algorithm achieves the optimum model accuracy (0.791, F1 = 0.723). The very low, low, medium, and high sensitivity zones account for 92.27%, 5.12%, 1.78%, and 0.83% of the area, respectively. The height of cut slopes has the most significant impact on landslide sensitivity, whereas the altitude has a minor impact. The proposed model accurately assesses landslide susceptibility at the township scale, providing valuable insights for risk management and mitigation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningLandslidesChinaHumansAlgorithms

Autor:innen und Institutionen

  • School of Civil Engineering and Architecture, Zhejiang Sci-Tech University, Hangzhou, China.
  • Zhenan Comprehensive Engineering Surveying and Mapping Institute, Lishui, China.
  • Hangzhou Guowei Construction Engineering Corporation Limited, Hangzhou, China.

ORCID-Profile: Hui Xu

Förderung

  • his research was funded by the National Natural Science Foundation of China

Zitieren

APA

Lv, M. Z., Li, K. L., Cai, J. Z., Mao, J., Gao, J. J., & Xu, H. (2025). Evaluation of landslide susceptibility based on SMOTE-Tomek sampling and machine learning algorithm. PLOS One, 20(5), e0323487. https://doi.org/10.1371/journal.pone.0323487

Vancouver

Lv MZ, Li KL, Cai JZ, Mao J, Gao JJ, Xu H. Evaluation of landslide susceptibility based on SMOTE-Tomek sampling and machine learning algorithm. PLOS One. 2025;20(5):e0323487. doi:10.1371/journal.pone.0323487

BibTeX
@article{Lv2025,
  author = {Lv, Ming-Zhou and Li, Kun-Lun and Cai, Jia-Zeng and Mao, Jun and Gao, Jia-Jun and Xu, Hui},
  title = {Evaluation of landslide susceptibility based on SMOTE-Tomek sampling and machine learning algorithm},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {5},
  pages = {e0323487},
  doi = {10.1371/journal.pone.0323487}
}
Kostenlos starten →