赵阳阳,刘纪平,杨毅,石丽红,王梅

• 1:辽宁工程技术大学
• 2:中国测绘科学研究院
• 3:山东省诸城市国土资源局

摘要(Abstract)：

针对PM2.5浓度估算中时空特征考虑不足和样本量较少的问题,该文将协同训练和时空地理加权回归相结合,提出了协同时空地理加权回归。采用两个不同参数的时空地理加权回归模型作为回归器,利用一个回归器训练另一个回归器的未标注样本,选择最优结果作为标注样本加入标注样本,通过不断学习扩大标注样本量提升模型的回归性能。以京津冀地区2015年3-7月的PM2.5浓度数据为实验数据,利用气溶胶光学厚度产品、温度、风速和相对湿度进行建模,采用不同核函数的时空地理加权回归作为对比方法进行实验。结果显示,协同时空地理加权回归性能比基于Gauss核函数时空地理加权回归提升了10%,比基于bi-square核函数时空地理加权回归提升了6.25%,证明该文方法能够提升时空样本数量不足时的PM2.5浓度估算精度。

关键词(KeyWords)： 协同时空地理加权回归;协同训练;时空地理加权回归;PM2.5浓度

Abstract:

Keywords:

基金项目(Foundation): 公益性行业科研专项(201512032);; 国家重点研发计划课题项目(2016YFC0803108)

作者(Author): 赵阳阳,刘纪平,杨毅,石丽红,王梅

DOI: 10.16251/j.cnki.1009-2307.2016.12.035

参考文献(References)：

• [1]GUO J P,ZHANG X Y,CHE H Z.Correlation between PM concentrations and aerosol optical depth in eastern China[J].Atmospheric Environment,2009,43(37):5876-5886.
• [2]MEYTAR S H,KLOOG I,KOUTRAKIS P,et al.Assessment of PM2.5concentrations over bright surfaces using MODIS satellite observations[J].Remote Sensing of Environment,2015,163:180-185.
• [3]KAHN P,BANERJEE P,DUNCAN M.Sensitivity of multiangle imaging to natural mixtures of aerosols over ocean[J].Journal of Geophysical Research,2001,106(16):18219-18238.
• [4]LIU Y,SARNAT J A,KILARU V,et al.Estimating ground-level PM2.5in the eastern United States using satellite remote sensing[J].Environmental Science&Technology,2005,39(9):3269-3278.
• [5]LIU Y,FRANKLIN M,KAHN R,et al.Using aerosol optical thickness to predict ground-level PM2.5concentrations in the St.Louis area:a comparison between MISR and MODIS[J].Remote Sensing of Environment,2007,107(1/2):33-44.
• [6]HU X F,WALLER L A,AL-HAMDAN M Z,et al.Estimating ground-level PM2.5concentrations in the southeastern U.S.using geographically weighted regression[J].Environmental Research,2013,121(2):1-10.
• [7]SONG W Z,JIA H F,HUANG J F,et al.A satellitebased geographically weighted regression model for regional PM2.5estimation over the Pearl River Delta region in China[J].Remote Sensing of Environment,2014,154:1-7.
• [8]HU X F,WALLER L A,LYAPUSTIN A,et al.Estimating ground-level PM2.5 concentrations in the southeastern United States using MAIAC AOD retrievals and a two-stage model[J].Remote Sensing of Environment,2014,140(13):220-232.
• [9]HUANG B,WU B,BARRY M.Geographically and temporally weighted regression for modeling spatiotemporal variation in house prices[J].International Journal of Geographical Information Science,2010,24(3):383-401.
• [10]ZHOU Z H,LI M.Semi-supervised regression with cotraining style algorithms[J].IEEE Transacations on Knowledge and Data Engineering,2007,19(11):1479-1493.
• [11]张晨光,张艳.半监督学习[M].北京:中国农业科学技术出版社,2013.
• [12]黎明.单视图协同训练方法的研究[D].南京:南京大学,2008.
• [13]马蕾,汪西莉.基于支持向量机协同训练的半监督回归[J].计算机工程与应用,2011,47(3):177-180.
• [14]YANG Y,LIU J P,XU S H,et al.An extended semisupervised regression approach with co-training and geographical weighted regression:a case study of housing prices in Beijing[J].International Journal of Geo-Information,2016,5(4):1-12.
• [15]刘美玲.时空地理加权回归模型的统计诊断[D].西安:西安建筑科技大学,2013.
• [16]FOTHERINGHAM A S,BRUNSDON C,CHARLTON M.Geographically weighted regression,the analysis of spatially varying relationships[M].New York:John Wiley&Sons,Ltd.,2002:34-45.
• [17]覃文忠.地理加权回归基本理论与应用研究[D].上海:同济大学,2007.
• [18]WU B,LI R R,HUANG B.A geographically and temporally weighted autoregressive model with application to housing prices[J].International Journal of Geographical Information Science,2014,28(5):1186-1204.
• [19]周志华.基于分歧的半监督学习[J].自动化学报,2013,39(11):1871-1878.
• [20]LU B B,CHARLTON M,HARRIS P,et al.Geographically weighted regression with a non-euclidean distance metric:a case study using hedonic house price data[J].International Journal of Geographical Information Science,2014,28(4):660-681.