Abstract
This study analyzed the landslide susceptibility using a statistical decision-tree model in the Baichi watershed (120 km2) in Taiwan. A decision tree is advantageous in that estimation process and order of important explanatory variables are explicitly represented by the tree structures. The purpose of this study is to reveal the relationship among shallow landslide, geomorphology, and geology in the Baichi watershed.
Results show that overall correctness of the decision-tree model by a 10-fold cross-validation is as large as 78.3 %. The tree-structure indicates that shallow landslides occurred in a specific location where mean slope angle exceeds 34 degree, and dominant geology is not the Shihti Formation.
