Landslide hazard assessments using computational models, such as artificial neural network (ANN) and frequency ratio (FR), were carried out covering one of the important mountain highways in the Central Himalaya of Indian Himalayan Region (IHR). Landslide influencing factors were either calculated or extracted from spatial databases including recent remote sensing data of LANDSAT TM, CARTOSAT digital elevation model (DEM) and Tropical Rainfall Measuring Mission (TRMM) satellite for rainfall data. ANN was implemented using the multi-layered feed forward architecture with different input, output and hidden layers. This model based on back propagation algorithm derived weights for all possible parameters of landslides and causative factors considered. The training sites for landslide prone and non-prone areas were identified and verified through details gathered from remote sensing and other sources. Frequency Ratio (FR) models are based on observed relationships between the distribution of landslides and each landslide related factor. FR model implementation proved useful for assessing the spatial relationships between landslide locations and factors contributing to its occurrence. Above computational models generated respective susceptibility maps of landslide hazard for the study area. This further allowed the simulation of landslide hazard maps on a medium scale using GIS platform and remote sensing data. Upon validation and accuracy checks, it was observed that both models produced good results with FR having some edge over ANN based mapping. Such statistical and functional models led to better understanding of relationships between the landslides and preparatory factors as well as ensuring lesser levels of subjectivity compared to qualitative approaches.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.