主办单位:中国气象局沈阳大气环境研究所
国际刊号:ISSN 1673-503X
国内刊号:CN 21-1531/P

气象与环境学报 ›› 2016, Vol. 32 ›› Issue (1): 60-65.doi: 10.11927/j.issn.1673-503X.2016.01.009

• 论文 • 上一篇    下一篇

基于小波神经网络法的海南地区逐时太阳总辐射预测研究

黄海静1, 张京红1, 覃文娜2, 张明洁1, 邢彩盈1   

  1. 1. 海南省气候中心, 海南海口 570203;
    2. 海南省气象服务中心, 海南海口 570203
  • 收稿日期:2015-01-27 修回日期:2015-06-02 出版日期:2016-02-28 发布日期:2016-02-28
  • 通讯作者: 张京红,E-mail:331287312@qq.com。 E-mail:331287312@qq.com
  • 作者简介:黄海静,男,1985年生,助理工程师,主要从事气候变化与应用气象研究,E-mail:huanghai8815@163.com。
  • 基金资助:
    国家自然科学基金项目(41265007);中国气象局气候变化专项(CCSF201307)和海南省气象局科技创新项目(HN2013MS06)共同资助。

Forecast of hourly total solar radiation based on a wavelet back propagation neural network method in Hainan province

HUANG Hai-jing1, ZHANG Jing-hong1, QIN Wen-na2, ZHANG Ming-jie1, XING Cai-ying1   

  1. 1. Hainan Climate Center, Haikou 570203, China;
    2. Meteorological Service Center of Hainan, Haikou 570203, China
  • Received:2015-01-27 Revised:2015-06-02 Online:2016-02-28 Published:2016-02-28

摘要: 利用2003-2012年海口市气象站不同季节逐时太阳总辐射观测资料与对应气象参数,建立基于小波BP神经网络法逐时太阳总辐射的预测模型,并利用2013年太阳总辐射数据对模型进行检验,且与建立的逐步回归模型进行对比。结果表明:小波神经网络法建立的逐时太阳总辐射预测模型精度较高,但不同季节模型预测精度存在差异,冬季预测精度最高,夏季预测精度最差,天气类型指数有利于不同季节模型预测精度的提高。春季、夏季、秋季和冬季加入天气类型指数神经网络模型的逐时太阳总辐射预测值与观测值的回归估计标准误差分别为0.32、0.47、0.35 MJ·m-2及0.23 MJ·m-2,比逐步回归模型的预报精度分别提高了28.8%、16.3%、17.9%和20.4%,说明基于小波神经网络法建立的预测模型可为海南地区逐时太阳总辐射预测提供参考。

关键词: 小波神经网络, 逐步回归, 逐时太阳总辐射, 预测

Abstract: Hourly total solar radiation data has become the basic requirements of the meteorological service for multi-industry.However, radiation observation sites in China are sparse.Using hourly total solar radiation data in different seasons and corresponding meteorological data from 2003 to 2012 in Haikou weather station, an hourly total solar radiation prediction model based on a wavelet back propagation (BP) neural network method was developed.The model was tested using observed data in 2013 and compared with that based on a stepwise statistical regression model developed by the same data.The results indicate that the model based on the wavelet BP neural network method has higher accuracy, but the level of accuracy is different in different seasons.The accuracy is the highest in winter and lowest in summer.The index of weather type is favorable to enhance the forecast accuracy in different seasons.The root means squared error (RMSE) between predicted and observed total solar radiation for the wavelet BP neural network model with index of weather type are 0.32 MJ·m-2 in spring, 0.47 MJ·m-2 in summer, 0.35 MJ·m-2 in autumn and MJ·m-2 in winter, and its forecast accuracy increases by 28.8%, 16.3%, 17.9% and 20.4% respectively compared with that for the stepwise regression model.It suggests that the model based the wavelet BP neural network method is suitable in Hainan.

Key words: Wavelet neural network, Stepwise regression, Hourly total solar radiation, Prediction

中图分类号: