欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2007, Vol. 24 ›› Issue (1): 81-85.DOI: 10.7523/j.issn.2095-6134.2007.1.012

• 论文 • 上一篇    下一篇

基于BP网络的降雨-水位预报模型应用研究

占玉林 王长耀 牛 铮   

  1. 中国科学院遥感应用研究所 遥感科学国家重点实验室
  • 收稿日期:1900-01-01 修回日期:1900-01-01 发布日期:2007-01-15

An Application Research of Rainfall-Water level Forecast Model Based on BP Network

ZHAN Yu-Lin, WANG Chang-Yao, NIU Zheng   

  1. State Key Laboratory of Remote Sensing Sciences, Institute of Remote Sensing Applications, Chinese Academy of Science
  • Received:1900-01-01 Revised:1900-01-01 Published:2007-01-15

摘要: 本文改进了BP网络的学习率和动量项的自适应调整算法,阐述了洪水预报BP网络模型的构造和数据处理方法,建立了降雨~水位预报BP网络模型,实现了洪水水位的直接预报,同时还提出了以点雨量作为模型输入的建模方案,有效地改善了BP网络的模拟性能。

关键词: 网络, 降雨~水位模拟, 点雨量

Abstract:

In this paper, the momentum and learning rate adaptive adjustment algorithm is improved in BP Network. The structure of BP network and the data processing method of flood forecast mode are discussed. In order to predict the flood water level directly, the rainfall-water level forecast model is built. Furthermore, a new modeling scheme, in which the point rainfall data are used as the model input, is proposed, and the accuracy of BP network is improved.

Key words: BP Network, Rainfall-Water Level Modeling, Point Rainfall

中图分类号: