安徽亳州地区大雾预报模型研究.doc

1 / 11 --------------------------------------------- 感谢观看本文------- 谢谢----------------------------------------------------------- [ 标签: 标题]2016 安徽亳州地区大雾预报模型研究摘要:该文根据 2002-2012 年亳州地区大雾资料,统计了大雾的时空分布特征和环流形势。结果表明:年平均大雾日数最多的地区集中在亳州中北部, 东南部最少。近 11a 来大雾日数总体上呈减少趋势, 但2010 年后雾日有所增加,其中水平能见度在 50~ 200m 的浓雾出现频次最多。雾日有明显的季节变化, 冬季最多、秋季次之、夏季最少;大雾持续时间大多在1~14h 。根据 2013 年亳州市探空观测、地面观测资料以及 EC 细网格、 T639 、日本细网格、 GRAPE S 数值模式产品,选取了 87种预报因子,使用支持向量机方法和中台,通过对训练样本进行交叉验证和模型核参数的逐渐逼近,建立了亳州市 24h 大雾支持向量机预报模型。关键词:大雾;时空特征;预报模型;亳州中图分类号 ; 文献标识码 A文章编号 1007-773101-81-04 Research on the Fog Forecast Model in Bozhou Area Huang Liping1 et al. 2 / 11 --------------------------------------------- 感谢观看本文------- 谢谢----------------------------------------------------------- [ 标签: 标题]2016 Abstract : In this paper , the temporal and spatial characteristics of fog and the atmospheric circulation were analyzed by using the fog data in Bozhou from year 2002 to2012. The results showed that , the most of the annual average fog areas were concentrated in the north and central of Bozhou , and the southeast area was the least. Generally , the fog days decreased in the past 11 years ,but it increased after 2010 year. The frequency of the visibility from 50 to200 meters had the maximum occurrence. The fog days had significant seasonal variation characteristics , that the winter maximum , autumn second , and summer minimum. The fog mostly lasted 1 to14 hours. According to the radiosonde data , observation data and EC fine mesh , T639 , Japan fine mesh , GRAPES numerical model products of Bozhou City in year 2013 ,87 predictors were selected. By using Support Vector Machinesand CMSVM application software platform , and through the cross-validation of the training samples and gradually approaching model nuclear parameters , the 24hour forecasting model of fog by Support Vector Machine in Bozhou was established. Key words : Fog ; Temporal and spatial 3 / 11 --------------------------------------------