Napredna pretraga

Pregled bibliografske jedinice broj: 545754

Landslide Assessment of the Starča Basin (Croatia) Using Machine-Learning Algorithms


Marjanović, Miloš; Kovačević, Miloš; Bajat, Branislav; Mihalić, Snježana; Abolmasov, Biljana
Landslide Assessment of the Starča Basin (Croatia) Using Machine-Learning Algorithms // Acta Geotechnica Slovenica, 2011 (2011), 2; 45-55 (međunarodna recenzija, članak, znanstveni)


Naslov
Landslide Assessment of the Starča Basin (Croatia) Using Machine-Learning Algorithms

Autori
Marjanović, Miloš ; Kovačević, Miloš ; Bajat, Branislav ; Mihalić, Snježana ; Abolmasov, Biljana

Izvornik
Acta Geotechnica Slovenica (1854-0171) 2011 (2011), 2; 45-55

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Landslides; support vector machines; decision trees classifier; Starča Basin

Sažetak
In this research, machine-learning algorithms were compared in a landslide-susceptibility assessment. Given the input set of GIS layers for the Starča Basin, which included geological, hydrogeological, morphometric, and environmental data, a classification task was performed to classify the grid cells to: (i) landslide and non-landslide cases, (ii) different landslide types (dormant and abandoned, stabilized and suspended, reactivated). After finding the optimal parameters, C4.5 decision trees and Support Vector Machines were compared using kappa statistics. The obtained results showed that classifiers were able to distinguish between the different landslide types better than between the landslide and non-landslide instances. In addition, the Support Vector Machines classifier performed slightly better than the C4.5 in all the experiments. Promising results were achieved when classifying the grid cells into different landslide types using 20% of all the available landslide data for the model creation, reaching kappa values of about 0.65 for both algorithms.

Izvorni jezik
Engleski

Znanstvena područja
Rudarstvo, nafta i geološko inženjerstvo



POVEZANOST RADA


Projekt / tema
195-1951825-1507 - Razvoj sustava upravljanja geotehničkim podacima za procjenu prirodnih hazarda (Predrag Kvasnička, )

Ustanove
Rudarsko-geološko-naftni fakultet, Zagreb

Autor s matičnim brojem:
Snježana Mihalić Arbanas, (205022)

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Uključenost u ostale bibliografske baze podataka:


  • GeoRef
  • ICONDA (International Construction Database)
  • SCIE - Science Citation Index Expanded
  • JCR – Journal Citation Reports / Science Edition