高级检索
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[J]. 大气科学, 2001, 25(5): 650-660. DOI: 10.3878/j.issn.1006-9895.2001.05.07
引用本文: 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[J]. 大气科学, 2001, 25(5): 650-660. DOI: 10.3878/j.issn.1006-9895.2001.05.07
Zhang Ren. A Diagnosis/ Prediction of the Movement of the Western Pacific Subtropical High Based on the Neural Network Approximation with Forth-Propagation Style[J]. Chinese Journal of Atmospheric Sciences, 2001, 25(5): 650-660. DOI: 10.3878/j.issn.1006-9895.2001.05.07
Citation: Zhang Ren. A Diagnosis/ Prediction of the Movement of the Western Pacific Subtropical High Based on the Neural Network Approximation with Forth-Propagation Style[J]. Chinese Journal of Atmospheric Sciences, 2001, 25(5): 650-660. DOI: 10.3878/j.issn.1006-9895.2001.05.07

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

A Diagnosis/ Prediction of the Movement of the Western Pacific Subtropical High Based on the Neural Network Approximation with Forth-Propagation Style

  • 摘要: 基于前传式神经网络BP算法(BackpropagationNeuralNetwork)和回归模型,探讨了西太平洋副高面积指数同赤道东太平洋海温及赤道纬向风之间非线性分类和映射逼近的建模方法和效果比较.结果表明,前传式网络,特别是回归网络预报模型具有较好拟合精度和预报效果及比较实用的预报时效.

     

/

返回文章
返回