自组织特征映射神经网络在厄尔尼诺事件检验中的应用
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
厄尔尼诺事件多因素成因进行了分析。利用自组织特征映射(SOFM)神经网络方法对1973~1994年的全球7级以上地震次数、日食条件、海温距平数据建立了SOFM网络检验模型。对1995~2000年厄尔尼诺事件进行了检验,检验的准确率为83.3%。
The causes of the El Nino events was analyzed.The self-organizing feature map(SOFM) neural network forecasting model was built up according to the numbers of the earthquakes,the conditions of solar-eclipses and average of sea-temperature in 1973~1994 with the method of the SOFM network and examines the El Nino events happened in 1995~2000.Its accuracy rate is 83.3%.
引文
[1]林振山,赵佩章,赵文桐.日食-厄尔尼诺系数及其应用[J].地球物理学报,1999,42(6):732 737.LIN Zhen-shan,ZHAO Pei-zhang,ZHAO Wen-tong.The solar eclipse-nino coefficients and its application[J].Chinese Journal of Geophysics,1999,42(6):732737.
    [2]占志明.厄尔尼诺和拉尼娜事件及其对南中国海和华南地区的气候异常影响[D].广州:中山大学,2001:1634.ZHAN Zhi-ming.The El Nino and La Nina events,andinfluence to climatic anomalies of the South China Seaand the Southren China[D].Guangzhou:Sun Yat-senUniversity,2001:16 34.
    [3]Kohonen T.Self-organized formation of topologicallycorrect feature maps[J].Biological Cybernetics,1982,43:59 69.
    [4]Kohonen T.Self-organizing maps.2nd ed[M].Ber-lin:Springer-Verlag,1997.
    [5]Haykin S.神经网络原理[M].叶世伟,史忠植,译.北京:机械工业出版社,2004.Haykin S.Neural networks:A comprehensive founda-tion[M].Translated by Ye Shi-wei,Shi Zhong-zhi.Beijing:China Machinery Press,2004.
    [6]蔡煜东,杨兵,汤军彪.自组织人工神经网络在煤层对比判别中的应用[J].物探化探计算技术,1995,17(4):81 87.CAI Yu-dong,YANG Bing,TANG Jun-biao.Appli-cation of the Self-organizing Artificial Neural Networkto the correlation and discrimination of coalbeds[J].Computing Techniques for Geophysical and Geochemi-cal Exploration,1995,17(4):81 87.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心