Research on weather forecast based on neural networks

被引：0

作者：

Yuan, Q ^{[1
]}

Lu, YC ^{[1
]}

机构：

[1] Tsing Hua Univ, State Key Lab Intelligent Technol & Syst, Comp Sci & Technol Dept, Beijing 100084, Peoples R China

来源：

PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5 | 2000年

关键词：

neural networks; weather forecast; atmosphere pattern; data mining;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The traditional method based on aerodynamics and expertise for weather forecast is focus on the present data, but the historical database is not utilized This paper presents research on weather forecast through the historical database. Because the atmosphere pattern is a complex, nonlinear system, the traditional method is not an effective method. The multilayer neural network is a potent method to resolve this problem. With the back propagation neural networks (BP) the atmosphere pattern is divided into five patterns based on the rainfall. The comments of this method and an especial atmosphere pattern are given at the end of this paper.

引用

页码：1069 / 1072

页数：4