ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Landslide Susceptible Locations in Western Ghats: Prediction through openModeller

Ramachandra, TV and Kumar, Uttam and Aithal, Bharath H and Diwakar, PG and Joshi, NV (2010) Landslide Susceptible Locations in Western Ghats: Prediction through openModeller. In: Proceedings of the 26th Annual In-House Symposium on Space Science and Technology, 28-29 January 2010., 28-29 January 2010, IISc Bangalore.

[img] PDF
Landslide.pdf - Published Version
Restricted to Registered users only

Download (1316Kb) | Request a copy
Official URL: http://www.ces.iisc.ernet.in/energy/paper/Landslid...

Abstract

Many shallow landslides are triggered by heavy rainfall on hill slopes resulting in enormous casualties and huge economic losses in mountainous regions. Hill slope failure usually occurs as soil resistance deteriorates in the presence of the acting stress developed due to a number of reasons such as increased soil moisture content, change in land use causing slope instability, etc. Landslides triggered by rainfall can possibly be foreseen in real time by jointly using rainfall intensity-duration and information related to land surface susceptibility. Terrain analysis applications using spatial data such as aspect, slope, flow direction, compound topographic index, etc. along with information derived from remotely sensed data such as land cover / land use maps permit us to quantify and characterise the physical processes governing the landslide occurrence phenomenon. In this work, the probable landslide prone areas are predicted using two different algorithms – GARP (Genetic Algorithm for Rule-set Prediction) and Support Vector Machine (SVM) in a free and open source software package - openModeller. Several environmental layers such as aspect, digital elevation data, flow accumulation, flow direction, slope, land cover, compound topographic index, and precipitation data were used in modelling. A comparison of the simulated outputs, validated by overlaying the actual landslide occurrence points showed 92% accuracy with GARP and 96% accuracy with SVM in predicting landslide prone areas considering precipitation in the wettest month whereas 91% and 94% accuracy were obtained from GARP and SVM considering precipitation in the wettest quarter of the year.

Item Type: Conference Paper
Additional Information: Copyright 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords: Landslide;GARP;SVM;openModeller
Department/Centre: Division of Biological Sciences > Centre for Ecological Sciences
Division of Mechanical Sciences > Centre for Sustainable Technologies (formerly ASTRA)
Date Deposited: 10 Oct 2011 09:08
Last Modified: 10 Oct 2011 09:08
URI: http://eprints.iisc.ernet.in/id/eprint/41274

Actions (login required)

View Item View Item