This paper analyzes the character of the complex canal network

and imports the dynamic segmentation theory to organize the canal network data and its spatial knowledge. A method based on grid to detect the network density is put forward and the result show it is better than other method. And also a canal network selection model is set up based on decision of spatial knowledge. This model integrates five factors of the canal selection such as the attribute

length

link condition

spatial relation between canals and network density. Then

utilizes the multiple criteria decision to evaluate each canal by these five factors

and make alternated selection to preserve the whole network character