EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Landslide Susceptibility Level Mapping in Kozhikode, Kerala, Using Machine Learning-Based Random Forest, Remote Sensing, and GIS Techniques

Pradeep Kumar Badapalli, Anusha Boya Nakkala, Raghu Babu Kottala, Sakram Gugulothu, Fahdah Falah Ben Hasher, Varun Narayan Mishra, Mohamed Zhran

Land · 12.07.2025 · 14 (7) · 1453

DOI: 10.3390/land14071453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Land, online erschienen am 12.07.2025. Verfasst von Pradeep Kumar Badapalli und 6 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Princess Nourah bint Abdulrahman University Researchers Supporting Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Landslides are among the most destructive natural hazards in the Western Ghats region of Kerala, driven by complex interactions between geological, hydrological, and anthropogenic factors. This study aims to generate a high-resolution Landslide Susceptibility Level Map (LSLM) using a machine learning (ML)-based Random Forest (RF) model integrated with Geographic Information Systems (GIS). A total of 231 historical landslide locations obtained from the Bhukosh portal were used as reference data. Eight predictive factors—Stream Order, Drainage Density, Slope, Aspect, Geology, Land Use/Land Cover (LULC), Normalized Difference Vegetation Index (NDVI), and Moisture Stress Index (MSI)—were derived from remote sensing and ancillary datasets, preprocessed, and reclassified for model input. The RF model was trained and validated using a 50:50 split of landslide and non-landslide points, with variable importance values derived to weight each predictive factor of the raster layer in ArcGIS. The resulting Landslide Susceptibility Index (LSI) was reclassified into five susceptibility zones: Very Low, Low, Moderate, High, and Very High. Results indicate that approximately 17.82% of the study area falls under high to very high susceptibility, predominantly in the steep, weathered, and high rainfall zones of the Western Ghats. Validation using Area Under the Curve–Receiver Operating Characteristic (AUC-ROC) analysis yielded an accuracy of 0.890, demonstrating excellent model performance. The output LSM provides valuable spatial insights for planners, disaster managers, and policymakers, enabling targeted mitigation strategies and sustainable land-use planning in landslide-prone regions.

Förderung

  • Princess Nourah bint Abdulrahman University Researchers Supporting Project

Zitieren

APA

Badapalli, P. K., Nakkala, A. B., Kottala, R. B., Gugulothu, S., Hasher, F. F. B., Mishra, V. N., & Zhran, M. (2025). Landslide Susceptibility Level Mapping in Kozhikode, Kerala, Using Machine Learning-Based Random Forest, Remote Sensing, and GIS Techniques. Land, 14(7), 1453. https://doi.org/10.3390/land14071453

Vancouver

Badapalli PK, Nakkala AB, Kottala RB, Gugulothu S, Hasher FFB, Mishra VN, et al. Landslide Susceptibility Level Mapping in Kozhikode, Kerala, Using Machine Learning-Based Random Forest, Remote Sensing, and GIS Techniques. Land. 2025;14(7):1453. doi:10.3390/land14071453

BibTeX
@article{Badapalli2025,
  author = {Badapalli, Pradeep Kumar and Nakkala, Anusha Boya and Kottala, Raghu Babu and Gugulothu, Sakram and Hasher, Fahdah Falah Ben and Mishra, Varun Narayan and Zhran, Mohamed},
  title = {Landslide Susceptibility Level Mapping in Kozhikode, Kerala, Using Machine Learning-Based Random Forest, Remote Sensing, and GIS Techniques},
  journal = {Land},
  year = {2025},
  volume = {14},
  number = {7},
  pages = {1453},
  doi = {10.3390/land14071453}
}
Kostenlos starten →