###
气象:2015,41(1):98-104
本文二维码信息
码上扫一扫!
KNN数据挖掘算法在北京地区霾等级预报中的应用
熊亚军1,2, 廖晓农1,2, 李梓铭1,2, 张小玲1,2, 孙兆彬1,2, 赵秀娟1,2, 赵普生1,2, 马小会1,2, 蒲维维1,2
(1.京津冀环境气象预报预警中心,北京 100089;2.中国气象局北京城市气象研究所,北京 100089)
Application of KNN Data Mining Algorithm to Haze Grade Forecasting in Beijing
XIONG Yajun1,2, LIAO Xiaonong1,2, LI Ziming1,2, ZHANG Xiaoling1,2, SUN Zhaobin1,2, ZHAO Xiujuan1,2, ZHAO Pusheng1,2, MA Xiaohui1,2, PU Weiwei1,2
(1.The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089;2.Institute of Urban Meteorology, CMA, Beijing 100089)
摘要
图/表
参考文献
相似文献
本文已被:浏览 2066次   下载 1080
投稿时间:2014-09-04    修订日期:2014-11-18
中文摘要: 利用北京地区2013年气象数据以及PM2.5浓度数据与能见度数据进行对比分析,结果发现气温、气压、相对湿度、露点温度、地面U风、地面V风以及PM2.5小时浓度这7个要素是影响北京地区霾等级的关键因素。利用气温、地面气压、相对湿度、露点温度、U风、V风分量以及PM2.5浓度作为7个属性特征,以霾等级做为标志量构建训练样本集,结合KNN(K Nearest Neighbor)数据挖掘算法构建霾等级预报分类器,并开展霾等级客观识别实验。结果表明K=3时该分类器的分类预报效果最佳,其13个站点的分类准确率高达88.2%。基于该算法构建的KNN模型预报无霾时的漏报概率很小,准确率高达91.8%;预报有轻度霾、中度霾以及重度霾时,空报的概率仅分别为4.7%、1.4%和2.6%。2014年8月29日至9月2日北京地区一次霾天气过程的预报结果表明:南郊观象台、密云和延庆3站的预报准确率分别达到74%、64%和84%,但霾等级的精度方面还有待于进一步提高。
Abstract:Based on meteorological data and PM2.5 concentration data of 2013, the statistical analysis shows that temperature, pressure, relative humidity, dew point temperature, surface wind, U wind, V wind and PM2.5 hourly concentration are the 7 key factors affecting the haze grade of Beijing Area. The attribute vectors of KNN training sample set are the above 7 factors and the label vector is haze grade. The classifier can be established combining KNN Data Mining Algorithm and its best value is parameter K=3. The classification accuracy of the 13 meteorological stations is 88.2%. The forecasting model based on KNN Algorithm has good accuracy. When it predicts no haze, the accuracy rate is 91.8% and missing forecast chance is very small. When mild, moderate or severe haze is predicted, the probability of empty forecast is only 4.7%, 1.4% and 2.6%, respectively. There was one frog haze weather process from 29 August to 2 September 2014 in Beijing Area. Its prediction results show the forecast accuracy of Nanjiao, Miyun and Yanqing is 74%, 64% and 84% respectively, but the accuracy of the haze grade remains to be further improved.
文章编号:     中图分类号:    文献标志码:
基金项目:中央级公益性科研院所专项基金(IUMKY201303PP0103)、国家科技支撑计划项目(2014ABC16B04)、北京市科技计划项目(Z131100006113013)和首都蓝天行动培育专项(Z141100001014013)共同资助
Author NameAffiliation
XIONG Yajun The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
LIAO Xiaonong The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
LI Ziming The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
ZHANG Xiaoling The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
SUN Zhaobin The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
ZHAO Xiujuan The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
ZHAO Pusheng The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
MA Xiaohui The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
PU Weiwei The Beijing Tianjin Hebei Environmental Meteorological Forecasting and Warning Center, Beijing 100089
Institute of Urban Meteorology, CMA, Beijing 100089 
引用文本:
熊亚军,廖晓农,李梓铭,张小玲,孙兆彬,赵秀娟,赵普生,马小会,蒲维维,2015.KNN数据挖掘算法在北京地区霾等级预报中的应用[J].气象,41(1):98-104.
XIONG Yajun,LIAO Xiaonong,LI Ziming,ZHANG Xiaoling,SUN Zhaobin,ZHAO Xiujuan,ZHAO Pusheng,MA Xiaohui,PU Weiwei,2015.Application of KNN Data Mining Algorithm to Haze Grade Forecasting in Beijing[J].Meteor Mon,41(1):98-104.