引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
过刊浏览    高级检索
本文已被:浏览 75次   下载   
分享到: 微信 更多
太原市PM2.5预报统计修正模型及其应用检验
张岳军1, 张怀德1, 朱凌云1, 何俊琦2, 韩照宇1, 冯 坤3
1.山西省气象科学研究所;2.山西省气象干部培训学院;3.山西省环境监测中心站
摘要:
在华北区域环境气象数值预报系统(BREMPS)预报结果的基础上,结合多元线性回归(MR)、BP神经网络(BP)和多层递阶方法(MLR),分别建立10天的滚动修正模型,并对太原市2017年1月15日-4月15日PM2.5浓度值进行了修正.结果表明,三种方法对BREMPS预报的PM2.5小时值和日均值均有不同程度的改善,尤其是MLR修正结果在多项评价指标上明显优于多元线性回归和BP神经网络,其小时值的均方根误差由原来的42.46μg/m3缩小到了26.74μg/m3,日均值的均方根误差,在重污染和非重污染时段分别由未修正前的63.78、43.68μg/m3缩小到了28.52、21.27μg/m3,日均浓度修正结果的基础评分从0.65提高到了0.88,预报准确率由原来的66.18%提高到了86.74%.从三种修正方案的构建来看,MR和BP方法对系统平稳状态的修正具有一定的优势,而对系统大幅度变化的识别能力较弱,所以在天气变化时临界状态的修正结果误差较大,模型的稳定性较差.MLR模型本身具有一定的自适应能力,稳定性和修正结果的整体趋势明显优于前两种方法,因此,对太原市空气质量预报改进,重污染天气预警和大气污染防治等方面具有较大的应用价值.
关键词:  PM2.5  多元线性回归  BP神经网络  多层递阶  滚动修正
DOI:
分类号:X513
基金项目:科技部大气污染专项项目(2016YFC0203306);山西省气象局面上项目(SXKMSDQ20173516)
Implementation of Model Output Statistics on PM2.5 Forecast in Taiyuan
ZHAGN Yue-jun1, ZHANG Huai-de1, ZHU Lin-yun1, HE Jun-qi2, HAN Zhao-yu1, FENG Kun3
1.Shanxi Province Meteorological Science Research Institute;2.Shanxi Province Meteorological Cadre Training Institution;3.Shanxi Environmental Monitoring Center Station
Abstract:
Based on the forecasting products of BREMPS, Multiple linear regression (MR), BP neural network (BP) and multi-level recursive method (MLR) were used to correct the PM2.5 concentration in Taiyuan from January 15 to April 15, 2017. The results indicate that the hourly and daily PM2.5 of BREMPS forecast are optimized by three correction methods in varying degrees. In particular, the results of MLR correction are obviously superior to multiple linear regression and BP neural networks on multiple evaluation indicators, which the Root mean square error of hourly PM2.5 from 42.46μg/m3 down to 26.74μg/m3, and respectively the Root mean square error of daily PM2.5 in heavy and non-heavy pollution periods from 63.78, 43.68μg/m3 narrowed to 28.52, 21.27μg/m3. The basic score of the modified daily PM2.5 concentration has increased from 0.65 to 0.88, and the accuracy of the forecast is increased from 66.18% to 86.74%. From the construction of the three correction schemes, the MR and BP methods have certain advantages in correcting the stationary state of the system, but the ability to identify the strenuous changing system is weak. Therefore, the correction results of the critical state during the weather systems change and the stability of the MR and BP methods are weak. The MLR itself has a certain self-adaptive ability, which the overall trend and magnitude of MLR correction results are obviously superior to the MR and BP.
Key words:  PM2.5  multiple regression  back propagation  multi-level recursive  dynamic correction