Abstract
This research dissertation presents a new decision tree induction method, called co-location-based decision tree (CL-DT),
to extract exposed carbonate rocks in karst rocky desertification area. The proposed algorithm utilizes co-location
characteristics of multiple feature parameters, including landmarks spectral attribute, vegetation fraction, land surface
temperature and soil moisture content, etc., and spatial attributes of various landmarks in desertification area. This paper
first presented multiple feature parameters co-location mining algorithm, including attributes data selection,
determination of rough candidate co-locations, determination of co-locations, pruning non-prevalent co-locations, and
inducing co-location rules, and then focused on developing the algorithm of co-location decision tree, which including
non-spatial attributes data selection, multiple feature parameters co-location modeling, node merging criteria, and colocation
decision tree induction. The paper uses Landsat-5 TM images covering the whole Du‟an city in China as the data
to verify the proposed method. The experimental results demonstrated that (1) Compared to traditional decision tree, the
proposed multiattribute co-location decision tree has higher accuracy and can make better decision; (2) The training data
can be fully played roles in contribution to decision tree induction.
