全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
大气科学  2005 

基于神经网络奇异谱分析的ENSO指数预测

DOI: 10.3878/j.issn.1006-9895.2005.04.13

Keywords: ENSO指数,神经网络,奇异谱分析,时间序列

Full-Text   Cite this paper   Add to My Lib

Abstract:

采用奇异谱分析方法研究了ENSO指数及相关序列,结果表明奇异谱分析能很好的对原始序列进行信噪分离,增大了ENSO指数的可预报性.在此基础上,提出了人工神经网络和奇异谱分析相结合的ENSO指数预测方法,进行了不同因子组合的预报试验,预报效果明显优于持续性预报,超前4季的Nio3区、Nio4区预报相关系数仍高于0.5.

References

[1]  Barnston A G, Ropelewski C F. Prediction of ENSO episodes using canonical correlation analysis. J.Climate, 1992, 5(11): 1316~1345
[2]  Barnston A G, Van den Dool H M, et al. Long-lead seasonal forecasts-Where do we stand? Bull. Amer. Meteor. Soc., 1994, 75: 2097~ 2114
[3]  翟盘茂, 江吉喜, 张人禾. ENSO监测和预测研究. 北京: 气象出版社, 2000. 108~114Zhai Panmao, Jiang Jixi, Zhang Renhe. Studies on ENSO Monitoring and Prediction (in Chinese). Beijing: China Meteorological Press, 2000. 108~114
[4]  金龙, 秦伟良, 姚华栋. 多步预测的小波神经网络预报模型. 大气科学, 2000, 24: 79~86Jing Long, Qin Weiliang, Yao Huadong. A multi-step prediction model of wavelet neural network. Chinese Journal of Atmospheric Sciences (in Chinese), 2000, 24: 79~86
[5]  张韧, 蒋国荣. 赤道东太平洋海温及El Nio/La Nia 的反演及预测. 解放军理工大学学报, 2000, 5: 7~12Zhang Ren, Jiang Guorong. Retrieve and prediction of equatorial East-Pacific SST and El Nio/La Nia. J. PLA Univer. Sci.Tech. (in Chinese), 2000, 5: 7~12
[6]  张韧. 基于前传式网络逼近的太平洋副热带高压活动的诊断预测. 大气科学, 2001, 25(5): 650~660Zhang Ren. A diagnosis/prediction of the movement of the western pacific subtropical high based on the neural networks approximation with forth-propagation style. Chinese Journal of Atmospheric Sciences (in Chinese), 2001, 25(5): 650~660
[7]  Hsieh W W, Tang Benyang. Applying neural network models to prediction and data analysis in meteorology and oceanography. Bull. Amer. Meteor. Soc., 1998, 79: 1855~1870
[8]  袁曾任. 人工神经元网络及其应用. 北京: 清华大学出版社, 1999. 1~27, 66~130Yuan Zengren. Artificial Neural Network and Its Application (in Chinese). Beijing: Tsinghua University Press, 1999. 1~27, 66~130
[9]  Tangang F T, Tang B, Monahan A H. Forecasting ENSO events: a neural network-extended EOF approach. Journal of Climate, 1998, 11: 29~41
[10]  Tangang F T, Hsieh W W, Tang B. Forecasting the equatorial Pacific sea surface temperatures by neural network models. Climate Dyn., 1997, 13: 135~147
[11]  Tangang F T, Hsieh W W, Tang B. Forecasting regional sea surface temperatures in the tropical Pacific by neural network models, with wind stress and sea level pressure as predictors. J. Geophys. Res., 1998, 103(C4): 7511~7522
[12]  丁裕国, 江志红. 气象数据时间序列信号处理, 北京: 气象出版社, 1998. 160~167Ding Yuguo, Jiang Zhihong. Signal Processing of Time Series in Meteorology (in Chinese). Beijing: China Meteorological Press, 1998. 160~167
[13]  Liu Jianwen, Dong Peiming. Short-range climate prediction experiment of the southern oscillation index based on the singular spectrum analysis. Adv. Atmos. Sci., 2001, 18: 873~881
[14]  Tang B Y, Hsieh W W, Monahan A H, et al. Skill comparisons between neural networks and canonical correlation analysis in predicting the equatorial Pacific sea surface temperatures. J. Climate, 2000, 13: 287~293

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133