Spatial Prediction of Landslide Hazard Using Discriminant Analysis and GIS

Environmental attributes relevant for spatial prediction of landslides triggered by rain and snowmelt events were derived from digital elevation model (DEM). Those data in conjunction with statistics and geographic information system (GIS) provided a detailed basis for spatial prediction of landslide hazard. The spatial prediction of landslide hazard in this paper is based on discriminant analysis. Discriminant analysis is a multivariate technique that can be used to build rules that can classify elements or observations successfully between stable and unstable areas. The discriminant rule would show how to take into account the relative risks of making errors of misclassification. Those general rules allow managers to consider that errors in one direction may be much more costly than errors in the other direction.