BP网络框架下MODIS气溶胶光学厚度产品估算中国东部PM2.5

近年来随着中国经济的快速发展,中国区域的大气污染情况日趋严重,大气污染监测与治理已刻不容缓.由于卫星遥感具有较广的空间覆盖、成本低等优点,卫星遥感反演气溶胶光学厚度(AOD)产品被普遍认为是地面PM2.5浓度的重要指标,且已被广泛地应用于地面PM2.5遥感监测.利用2007～2008年的MODIS/Terra气溶胶光学厚度产品,考虑中国东部地区5个大气成分站点风速、风向、温度、湿度和边界层高度等气象数据,构建后向(BP)神经网络,提出了基于MODIS AOD产品估算PM2.5的模型.利用5个大气成分站点PM2.5观测数据对模型进行散点拟合和时间序列拟合验证,结果表明:①从PM2.5观测值与估算值的散点回归分析来看,PM2.5估算值与观测值相关系数最好的为庐山站(R=0.6),其它4个站次之,但其相关系数均在0.4(中强相关)以上;②从PM2.5观测值与估算值的时间序列比对分析来看,PM2.5估算值和观测值差值随时间变化而变化,且存在明显的日际振荡现象,但经相邻5 d滑动平均处理,5个站点的PM2.5估算值与观测值相关系数得到普遍提升,滑动后的相关系数RMA均在0.7以上(除郑州外),庐山RMA达到0.83.结果表明在BP网络框架下,基于MODIS AOD产品估算PM2.5的模型能较好地应用于PM2.5监测.

Estimation of PM2.5 over Eastern China from MODIS Aerosol Optical Depth Using the Back Propagation Neural Network

With the fast economic development in China in recent years, air pollutions are becoming increasingly serious. It is, therefore, imperative to develop new technology to solve this issue. Due to the wide spatial coverage of satellite remote sensing, along with the relatively lower cost compared to ground-based in situ aerosol measurements, satellite retrieved aerosol optical depth (AOD) is widely recognized as a good surrogate of surface PM_2.5 concentrations. In this study, two years (2007-2008) of AOD data from moderate resolution imaging spectroradiometer (MODIS) onboard Terra at five observational sites of China (Benxi, Zhengzhou, Lushan, Nanning, Guilin), combined with five meteorological factors such as wind speed, wind direction, temperature humidity and planetary boundary height, were used as important input to establish the Back Propagation (BP) neural networks model, which was applied to estimate PM_2.5. Afterwards, the model estimated PM_2.5 was validated by in situ PM_2.5 measurements from the five sites. Specially, scatter analysis showed that the linear correlation coefficient (R) between ground PM_2.5 observation and model estimated PM_2.5 at Lushan was the highest (R=0.6), whereas the R values at the four other sites were lower, ranging from 0.43 to 0.49.Time series validations were performed as well, indicating that the R value significantly varied from day to day. However, the R value could be significantly improved by fitting the five-day moving average ground observation values against the model estimated PM_2.5 data. Also, the R value at Lushan was the highest (R=0.83), suggesting that MODIS AOD can be used to monitor PM_2.5 by the BP networks model developed in this study.