摘要:
|
针对WRF模式的数值模拟结果中的各种输出变量,运用BP神经网络方法,对大连站点的气温、风速等变量进行了初步的释用,与实况进行比较后发现,释用后的结果较模式直接输出结果有了很大的改进;同时,运用中低层云水混合比、气压、海平面高度层上的温度露点差等变量,对能见度进行了诊断释用,获得令人满意的结果。 |
The preliminary interpretation of simulation variables,such as temperature,wind speed and so on,from WRF model in Dalian station was carried out using the BP neural network method.The interpretation re-sults showed great improvement by comparing with the direct output of the model.The diagnostic analysis of vis-ibility was treated with the same approach according to some variables including cloud water mixing ratio in the lower and middle layers of the atmosphere,sea-level pressure,dew-point temperature,etc.The results were satis-factory too.It indicates that the method is useful to reduce the bias of the simulation. |
参考文献:
|
[1] 陈德辉,薛纪善.数值天气预报业务模式现状与展望[J].气象学报,2004,62(5):623-633. [2] 李永华,刘德,金龙.基于BP神经网络的汛期降水预测模型研究[J].气象科学,2002,22(4):461-467. [3] 金龙.各种最优定阶准则的自回归模型集成预报方法研究[J].预测,1996,15(6):57-59. [4] Jin Long,Lou Ying,Lin Zhenshan.Comparison of Long-term forecasting of June-August rainfall over Changjiang-Huaihe valley[J].Advances in Atmospheric Sciences.1997,14(1):87-92. [5] 周曾奎,韩贵荣,朱定真等.人工神经网络台风预报系统[J].气象,1996,22(1):18-21. [6] McCann D W.A neural network short-term forecast of significant thunderstorms[J].Weather and Forecasting,1992,7:525-534. [7] Baik L,Hwang H.Tropical cyclone intensity prediction using regression method and neural network[J].Journal of the Meteorology Society of Japan,1998,76(5):711-717. [8] Marzban C,Witt A.A bayesian neural network for severe hail size prediction[J].Weather and Forecasting.2000,16(5):600-610. [9] 金龙.神经网络气象预报建模理论方法与应用[M].北京:气象出版社,2005. |
服务与反馈:
|
【文章下载】【发表评论】【查看评论】【加入收藏】
|
|
|