Evaluating landslide susceptibility and landscape changes due to road expansion using optimized machine learning

Saeed Alqadhi (), Hoang Thi Hang (), Javed Mallick () and Abdullah Faiz Saeed Al Asmari ()
Additional contact information
Saeed Alqadhi: King Khalid University
Hoang Thi Hang: Jamia Millia Islamia
Javed Mallick: King Khalid University
Abdullah Faiz Saeed Al Asmari: King Khalid University

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2024, vol. 120, issue 13, No 9, 11713-11741

Abstract: Abstract The Garhwal and Kumaun regions of the Himalayas of India have experienced rapid urbanisation due to the expansion of the national highway (NH-58) in Uttarakhand, which has a significant impact on the frequency and intensity of landslides. Therefore, this study assesses the impact of road expansion on landslide susceptibility in the Himalayas by examining landscape changes within 1 km, 2 km, and 3 km buffer zones around a major highway. Land use and land cover (LULC) from the years 2000 and 2023 were classified using Random Forest (RF) modelling to assess landslide susceptibility due to landscape change. Twelve key parameters were selected for susceptibility modeling and colinearity was tested by multicollinearity analysis to ensure robustness. The RF models were optimised using particle swarm optimisation (PSO) to model landslide susceptibility with higher precision, and their effectiveness was confirmed by receiver operating characteristic (ROC) and precision-recall curves. In addition, a polynomial regression analysis was used to investigate the complex relationships between landscape changes and landslide susceptibility. The susceptibility models showed high accuracy with area under the curve (AUC) values of 0.9083 and 0.9068. The results showed significant landscape changes affecting landslide susceptibility: The forest area decreased by 15.74 km² from 2000 to 2023, while the built-up area increased by 15.41 km². In particular, the zone with very low susceptibility to landslides within the 1 km buffer decreased by 5.569 km² and the zone with high susceptibility within the 3 km buffer increased by 4.972 km². The polynomial regression analysis showed that the built-up areas near the motorway decreased the most by 1.260 km², while the forest areas further away from the corridor increased by up to 4.585 km². This analysis illustrates the significant influence of road proximity on landscape dynamics and landslide risk and provides important insights for policy and land use planning in the rapidly developing Himalayan regions.

Keywords: Road network; Urbanization; Landslide susceptibility; Machine learning; Particle swarm optimization; Himalayas (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-024-06652-8 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:120:y:2024:i:13:d:10.1007_s11069-024-06652-8

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-024-06652-8

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().