Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Verification of a developed artificial neural network based model in producing landslide susceptibility hazard map for southwest of Sweden
2019 (English)Report (Other academic)
Abstract [en]

Landslides as a morphodynamic processes is one of the major geo-hazard concern in Sweden which is able to harm and affect nearby environments, socio-economy, people and industrial developments. Therefore, landslide susceptibility analysis will be a useful tool for engineers and planners to find safer areas not only for development schemes but also for hazard mitigation. In the current paper, landslide susceptibility map has been assessed for an extended surrounding area around the Göta River in southwest of Sweden by means of integrated an artificial neural networks (ANNs) based model and geographic information system (GIS). A wide range of effective parameters on slope instability were collected and classified into four groups including topographic and geomorphologic features, geological factors, hydrology and hydrogeology parameters as well as land use data. The thematic data were mainly derived from processed satellite images, aerial photographs and digital elevation model (DEM) as well as documentary data to construct the spatial database using GIS. The location of landslides to produce the inventory map of study area also has been identified from documentary, monitored and interpretation of aerial photographs. The weights of involving condition factors in provided susceptibility map was analyzed using the landslides occurrence factors by the ANN model and then validated using by both previous studies and location of experienced landslides in selected area. The high achieved accuracy using ANN model demonstrated a reliable criterion for future studies in landslide susceptibility zonation in this area.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2019. , p. 18
Series
Trafikverkets forskningsportföljer
Keywords [en]
Landslide, Sweden, artificial neural network, susceptibility map, condition factors
National Category
Geotechnical Engineering and Engineering Geology
Research subject
FOI-portföljer, Bygga
Identifiers
URN: urn:nbn:se:trafikverket:diva-12089Archive number: TRV 2016/107272OAI: oai:DiVA.org:trafikverket-12089DiVA, id: diva2:1747459
Projects
Bedömning av skredrisk med artificiella neuronnät
Funder
Swedish Transport Administration, TRV 2016/107272Available from: 2023-03-30 Created: 2023-03-30 Last updated: 2025-09-04

Open Access in DiVA

Verification of a developed artificial neural network based model in producing landslide susceptibility hazard map for southwest of Sweden(3098 kB)253 downloads
File information
File name FULLTEXT01.pdfFile size 3098 kBChecksum SHA-512
d4f45d05e6e6715d357248d69c132dc0559ca80f922ef9f0aacd71b780cfe92bfe145b72f9764734e3e2985224a20a79c8dbbaedfbc2cd3418de21af582baa81
Type fulltextMimetype application/pdf

Geotechnical Engineering and Engineering Geology

Search outside of DiVA

GoogleGoogle Scholar
Total: 254 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 424 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf