Application of Self-organizing Feature Maps Neural Network on Hydrographic Zones Partitioning

Abstract

Hydrographic zones partitioning is the critical issue in hydrological station network planning and a hydrographic zones partition method that can divide the hydrographic zones objectively is desirable for any region. As a kind of pattern classification problem, the hydrographic zones partitioning of Shandong province is achieved by the self-organizing feature map neural network (SOFM network) which has been successfully applied to pattern classification problems. Based on 50 hydrological stations and 8 basic factors which reflect the land surface and hydroclimate characteristics, Shandong province is automatically divided into 2 hydrographic zones by SOFM network. The average watershed characteristics of each sub-zone are consistent with the local terrain and surface conditions. And based on the partitioning results of SOFM network method, the maximum peak flow and the accuracy are analyzed which are proved reasonable and achieve pass rate of 82%. Which indicate that it is an effective method to use SOFM neural network to divide the hydrographic zones.