Landslide susceptibility maps comparing frequency ratio and artificial neural networks: a case study from the Nepal Himalaya
| Autor: | Chandong Chang, Saro Lee, Hyun-Joo Oh, Chandra Prakash Poudyal |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Global and Planetary Change
Geographic information system Artificial neural network business.industry Frequency ratio Soil Science Geology Landslide Landslide susceptibility Pollution Aerial photography Slope stability Environmental Chemistry business Spatial analysis Cartography Earth-Surface Processes Water Science and Technology |
| Zdroj: | Environmental Earth Sciences. 61:1049-1064 |
| ISSN: | 1866-6299 1866-6280 |
| DOI: | 10.1007/s12665-009-0426-5 |
| Popis: | This study considers landslide susceptibility mapping by means of frequency ratio and artificial neural network approaches using geographic information system (GIS) techniques as a basic analysis tool. The selected study area was that of the Panchthar district, Nepal. GIS was used for the management and manipulation of spatial data. Landslide locations were identified from field survey and aerial photographic interpretation was used for location of lineaments. Ten factors in total are related to the occurrence of landslides. Based on the same set of factors, landslide susceptibility maps were produced from frequency ratio and neural network models, and were then compared and evaluated. The weights of each factor were determined using the back-propagation training method. Landslide susceptibility maps were produced from frequency ratio and neural network models, and they were then compared by means of their checking. The landslide location data were used for checking the results with the landslide susceptibility maps. The accuracy of the landslide susceptibility maps produced by the frequency ratio and neural networks is 82.21 and 78.25%, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink