| 贵州导线覆冰的分区域预报 |
| |
| 引用本文： | 冯丽莎,吴巍巍,向卫国. 贵州导线覆冰的分区域预报[J]. 成都信息工程学院学报, 2013, 0(6): 659-664 |
| |
| 作者姓名： | 冯丽莎 吴巍巍 向卫国 |
| |
| 作者单位： | [1]成都信息工程学院大气科学学院,四川成都610225;中国科学院大气物理研究所北京100029 [2]广东省江门市气象局,广东江门529000 [3]成都信息工程学院大气科学学院,四川成都610225;成都信息工程学院高原大气与环境研究中心四川成都610225 |
| |
| 基金项目： | 公益性行业（气象）科研专项资助项目（GYHY201006033） |
| |
| 摘 要： | 针对贵州冬季凝冻天气中导线覆冰难以定量预报的问题,探索导线覆冰预报新的思路和方法,利用2007～2012年6年间12月到次年2月气象数据,运用逐步回归及BP人工神经网络方法,对贵州省分5个区域建立导线覆冰厚度预报模型,并进行了检验和试预报.结果表明：BP人工神经网络模型的拟合效果优于逐步回归模型,但在试预报中,两种模型的预报效果相差不大.
|
| 关 键 词： | 大气科学 气象与气候 覆冰预报 逐步回归 人工神经网络 |
Zoning Forecast of Guizhou Province Wire Icing |
| |
| FENG Li-sha,WU Wei-wei,XIANG Wei-guo. Zoning Forecast of Guizhou Province Wire Icing[J]. Journal of Chengdu University of Information Technology, 2013, 0(6): 659-664 |
| |
| Authors: | FENG Li-sha WU Wei-wei XIANG Wei-guo |
| |
| Affiliation: | 1. School of Atmospheric Sciences, CULT, Chengdu 610225, China; 2. Institute of Atmospheric Physics, CAS, Belling 100029, Chi ha;3. Center for Plateau Atmospheric and Environmental Research, Chengdu University of Information Technology, Chengdu 610225, Chi na; 4. Jiangmen Meteorological Bureau, Jiangmen 529000, China) |
| |
| Abstract: | To address the problem of the wire icing quantitative prediction and in order to investigate new ways o{ thinking and methods of the wire icing prediction, this paper uses weather data from the 6 time periods each chosen from December of one of the years 2007 -2012 to the subsequeiat February to analysis. By applying either the Step- wise Regression method or the BP Artificial Neural Network （BPANN） method, a model is established to predict the wire icing in each of the 5 parts of Guizhou Province. Both models are tested and used to make tentative prediction. The results show that the BPANN is better than the Stepwise Regression method. However, in the tentative predic- tion the two models give similar results. |
| |
| Keywords: | atmospheric sciences meteorology and climatology icing forecast stepwise regression artificial neural networks |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
