Number of the records: 1
Application of novel ensemble models to improve landslide susceptibility mapping reliability
- 1.
SYSNO ASEP 0573977 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Application of novel ensemble models to improve landslide susceptibility mapping reliability Author(s) Tong, Z. (CN)
Guan, Q. (CN)
Arabameri, A. (IR)
Loche, Marco (USMH-B) ORCID, RID
Scaringi, G. (CZ)Article number 309 Source Title Bulletin of Engineering Geology and the Environment. - : Springer - ISSN 1435-9529
Roč. 82, č. 8 (2023)Number of pages 21 s. Language eng - English Country DE - Germany Keywords Landslide susceptibility maps ; Landslide inventory ; Machine learning ; Statistical modeling Subject RIV DB - Geology ; Mineralogy OECD category Geology Method of publishing Limited access Institutional support USMH-B - RVO:67985891 UT WOS 001027857000001 EID SCOPUS 85165221970 DOI https://doi.org/10.1007/s10064-023-03328-8 Annotation Most landslides in the Eastern Golestan province in Iran occur in the Doji watershed. Their number, however, lies at the lower limit for reliable statistical analyses. By selecting a statistical sample in an area with rather homogeneous conditions (thereby reducing the number of meaningful covariates), significant insights can nevertheless be obtained. We relied on an inventory of 145 landslides which discerns between types of movement and implemented six machine learning algorithms (Decorate, DE-REPTree, Random Subspace, RS-REPTree, Dagging, and DA-REPTree) to produce landslide susceptibility maps. This allowed us to evaluate the relative importance and the effect of covariates in the models and identify factors that are consistently associated with the presence of landslides. Our results demonstrate that, even for a small landslide inventory, reliable susceptibility maps can be produced for homogeneous landscapes. We discuss that our approach could be used to assess the reliability of statistical approaches at small scales, where a distinctive trigger is lacking. Workplace Institute of Rock Structure and Mechanics Contact Iva Švihálková, svihalkova@irsm.cas.cz, Tel.: 266 009 216 Year of Publishing 2024 Electronic address https://doi.org/10.1007/s10064-023-03328-8
Number of the records: 1