混合递阶遗传径向基网络及其在副热带高压预报中的应用

刘科峰; 张韧; 洪梅; 余丹丹; 王彦磊; 高扬

混合递阶遗传径向基网络及其在副热带高压预报中的应用

1.
解放军理工大学气象学院海洋与空间环境系, 江苏, 南京, 211101;中国气象局广州热带海洋气象研究所, 广东, 广州, 510080
2.
解放军理工大学气象学院海洋与空间环境系, 江苏, 南京, 211101
3.
95140部队气象台, 广东, 广州, 516259

基金项目: 国家自然科学基金项目(40375019);热带海洋气象科学研究基金(200609)共同资助

计量
- 文章访问数: 760
- HTML全文浏览量: 0
- PDF下载量: 856
- 被引次数: 0
出版历程
- 收稿日期: 2007-03-12
- 修回日期: 2007-08-22

RBFNN BASED ON HYBRID HIERARCHY GENETIC ALGORITHM AND ITS APPLICATION IN SUBTROPICAL HIGH FORECAST

1.
Institute of Meteorology, PLA University of Science and Technology, Nanjing 211101, China;Guangzhou Insitute of Tropical and Marine Meteorology, CMA, Guangzhou 510080, China
2.
Institute of Meteorology, PLA University of Science and Technology, Nanjing 211101, China
3.
95140 Troops Weather Stations, Guangzhou 516259, China

摘要

摘要: 采用遗传算法与径向基网络结合的方法建立了副热带高压特征指数的预报优化模型。针对径向基网络结构和初始参数难以客观确定的不足,引入混合递阶遗传算法同时优化网络结构和参数。该优化方法结合了递阶遗传算法和最小二乘法的优点,具有较高的学习效率。将混合递阶遗传径向基网络用于副高数值预报产品的预报试验和效果比较,结果表明:混合递阶遗传算法优化的径向基网络模型具有较好的收敛效果和泛化能力,对副高指数的预报效果有较明显的改进和提高。
- 混合递阶遗传算法 /
- 径向基神经网络 /
- 副热带高压
Abstract: A forecasting model of subtropical high was constructed with RBF neural network. But,because of the difficulty of objective determination of the structure and initial parameter of RBF neural network,the hybrid hierarchy genetic algorithm was introduced to optimize network configuration and parameters. The optimization method,which combines the advantages of genetic algorithm and the least squares method,has high learning efficiency. Then,the model was used to forecast the subtropical high. Last,output results from the model were compared with the results of the T¹⁰⁶ and RBF network. The results show that the model with RBF neural network based on hybrid hierarchy genetic algorithm improves the subtropical high forecast results from T¹⁰⁶ by large margin.
- hybrid hierarchy genetic algorithm /
- RBF neural network /
- subtropical high

HTML全文

参考文献(8)

[1]	金龙.神经网络气象预报减模理论方法与应用[M].北京:气象出版社,2004:112-142.
[2]	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):649-660.
[3]	张韧,蒋国荣,余志豪,等.利用神经网络计算方法建立太平洋副高预报模型[J].应用气象学报,2000,11(4):474-483.
[4]	JIN Long,KUANG Xueyuan,HUANG Haihong,et al.Study on the overfiting of the Artificial neural network forecasting model[M].ACTA Meteorological Sinica,2005,19(2):216-225.
[5]	谷晓平,王长耀,袁淑杰.GA-BP神经网络模型在流域面雨量预报的应用研究[J].热带气象学报,2006,22(3):248-252.
[6]	石红瑞,刘勇,刘保坤,等.基于混合递阶遗传算法的径向基神经网络学习算法及其应用[J].控制理论与应用,2002,19(4):627-630.
[7]	MAN K F,TANG K S,KWONG S,et al.Genetic Algorithms for control and signal processing[M].Longdon:Springer_Verlag,1997:50-70.
[8]	王艳姣,张鹰,邓自旺,等.RBF神经网络的汛期旱涝预报方法研究[J].热带气象学报,2005,21(1):100-106.