In order to improve the efficiency of rendering terrain based on digital elevation model (DEM), a mesh simplification algorithm based on vertex importance and hierarchical clustering tree is presented. The vertexes of terrain blocks are firstly trained using K-means clustering analysis, and then we select representative vertexes of each cluster according to vertex importance. Secondly, coarse meshes are constructed on the basis of these representative vertexes. Thirdly, we seam all coarse meshes. Finally, repeat the above steps until we accomplish the whole simplification process. For the new insertion point, a hierarchical clustering tree is used to record intermediate results, which is applied to view dependent rendering for terrain. Experiment show that, the algorithm improves the efficiency and reduces memory consumption. At the same time, it maintains geometric characteristics of terrain.