基于EBK-GWR方法的区域PM_(2.5)浓度估算  

Estimation of regional PM_(2.5) concentration based on EBK-GWR

作　　者：唐友兵 谢劭峰 潘梦清 魏朋志 张亚博 张继洪 TANG Youbing;XIE Shaofeng;PAN Mengqing;WEI Pengzhi;ZHANG Yabo;ZHANG Jihong(College of Geomatics and Geoinformation,Guilin University of Technology,Guilin 541006;Guilin Institute of Surveying and Mapping,Guilin 541100,China)

机构地区：[1]桂林理工大学测绘地理信息学院,广西桂林541006 [2]桂林市测绘研究院,广西桂林541100

出　　处：《桂林理工大学学报》2024年第3期489-494,共6页Journal of Guilin University of Technology

基　　金：国家自然科学基金项目(41864002)。

摘　　要：针对我国现有的空气监测站点数量有限且分布不均、获取连续的区域PM_(2.5)数据困难的问题,依据由两广地区气象站获取的气压(PRS)、温度(TEM)、相对湿度(RHU)以及所属和相邻探空站获取的大气可降水量(PWV)数据,通过反距离加权插值得到2019年两广地区不同季节的TEM、 PRS、 RHU和PWV数据,综合分析其与PM_(2.5)的相关性,进一步构建地理加权回归模型(GWR)和经验贝叶斯克里金-地理加权回归模型(EBK-GWR),对2019年两广地区PM_(2.5)浓度空间分布进行估算。结果表明:EBK-GWR模型在不同季节的PM_(2.5)浓度估算效果明显优于GWR模型,其中春、秋两季均方根误差RMSE和平均绝对误差MAE提升最为显著;相比于GWR模型,春季分别提升了16.67%和13.88%,秋季提升了14.13%和13.04%;夏、冬两季提升效果较春、秋两季有所降低,但较于GWR提升均保持在10%左右,且不同季节估算的RMSE和MAE均小于4μg/m3。In view of the limited number and uneven distribution of existing air monitoring stations in our country,it is difficult to obtain continuous regional PM_(2.5) data.On the basis of pressure(PRS),temperature(TEM),relative humidity(RHU)obtained from meteorological stations in Guangdong and Guangxi,and precipitable water vapor(PWV)data obtained from subordinate and adjacent radiosonde stations,the TEM,PRS,RHU and PWV data of different seasons in 2019 are acquired by inverse distance weighted interpolation.By comprehensively analyzing their correlation with PM_(2.5),the geographically weighted regression(GWR)and empirical Bayesian Kriging geographically weighted regression(EBK-GWR)are constructed to estimate the spatial distribution of PM_(2.5) concentrations.The results show that EBK-GWR model’s PM_(2.5) concentration estimation effect is significantly better than GWR model in different seasons,where the root mean square error(RMSE)and mean absolute error(MAE)improves most significantly in spring and autumn.Compared with GWR model,the estimation accuracy of RMSE and MAE improves 16.67%and 13.88%in spring,14.13%and 13.04%in autumn,respectively.The improvement effect in summer and winter is lower than in spring and autumn,but the improvement remains at about 10%compared with GWR model,and the RMSE and MAE estimated in different seasons are both less than 4μg/m^(3).

关 键 词：EBK-GWR GWR PM_(2.5)浓度 空间分布 广西 广东 

分 类 号：P237[天文地球—摄影测量与遥感] P951[天文地球—测绘科学与技术]