| 基于iLME+Geoi-RF模型的四川省PM2.5浓度估算 |
| 摘要点击 1817 全文点击 510 投稿时间：2021-02-05 修订日期：2021-05-27 |
| 查看HTML全文
查看全文 查看/发表评论 下载PDF阅读器 |
| 中文关键词 PM2.5 Himawari-8 AOD 重采样 共线性诊断 iLME+Geoi-RF模型 时空变化 |
| 英文关键词 PM2.5 Himawari-8 AOD resampling collinearity diagnosis iLME+Geoi-RF model temporal and spatial changes |
|
| 中文摘要 |
| 高分辨率PM2.5空间分布数据对动态监测和控制PM2.5污染具有重要意义.选取Himawari-8气溶胶光学厚度（AOD）、ERA5气象再分析资料、DEM、土地利用数据、夜光遥感数据、增强型植被指数和人口数据等作为估算变量，使用改进的重采样法进行数据匹配，并提出改进的线性混合模型（iLME）结合地理智能随机森林（Geoi-RF）构建组合模型估算PM2.5浓度.结果表明：①在选取的估算变量中，气溶胶光学厚度、气压、温度、相对湿度和边界层高度是影响2016年四川省PM2.5浓度的重要因素，其相关系数分别为0.65、0.58、0.55、0.54和0.35.②iLME+Geoi-RF模型精度相较其他模型有较大提升，模型拟合R2、RMSR和MAE分别为0.98、3.25 μg·m-3和1.98 μg·m-3，交叉验证R2、RMSR和MAE分别为0.89、7.95 μg·m-3和4.81 μg·m-3.该模型可获取更高精度的四川省PM2.5时空分布特征，为区域空气质量评估、人体暴露风险评价和环境污染治理提供更加合理地科学参考.③2016年四川省PM2.5浓度存在显著的季节性差异，各季节PM2.5浓度大小关系为：冬季 > 秋季 > 春季 > 夏季.2016年四川省月均PM2.5浓度总体上呈先降后升的"V"型趋势，最小值在6月，最大值在12月，8月和11月有微小起伏.在空间分布上四川省PM2.5浓度总体上呈东高西低和局部污染程度较高的特点，高值区主要分布在城市快速发展和人口密集的东部地区，低值区主要分布在经济发展落后和人口稀疏的西部地区.④虽然不同模型估算出的PM2.5浓度整体分布基本一致，但iLME+Geoi-RF模型能更准确有效地估算本研究区污染的空间分布. |
| 英文摘要 |
| High-resolution PM2.5 spatial distribution data is of great significance for the dynamic monitoring and control of PM2.5 pollution. Himawari-8 AOD data, ERA5 meteorological reanalysis data, DEM, land-use data, and luminous remote-sensing data were selected as estimating variables, using an improved resampling method for data matching and an improved linear mixed model (iLME) combined with a Geo-intelligent random forest model to build the combined model for estimating PM2.5 concentration. The results showed that:① Among the estimated variables selected, AOD, SP, TEMP, RH, and BLH were important factors affecting the PM2.5 concentration of Sichuan Province in 2016, and their correlation coefficients were 0.65, 0.58, 0.55, 0.54, and 0.35, respectively. ② The prediction accuracy of the iLME+Geoi-RF model was greatly improved compared to that of other models. The model-fitted R2, RMSR, and MAE were 0.94, 5.72 μg·m-3, and 3.92 μg·m-3, and the cross-validated R2, RMSR, and MAE were 0.82, 10.20 μg·m-3, and 6.44 μg·m-3, respectively. The model can obtain more accurate spatial and temporal distribution characteristics of PM2.5 in Sichuan Province and provide a more reasonable scientific reference for regional air quality assessment, human exposure risk assessment, and environmental pollution control. ③ There was a significant seasonal difference in PM2.5 concentration in Sichuan Province, with the highest concentration of PM2.5 in winter, followed by spring and autumn, with the concentration of PM2.5 in summer being the lowest. In 2016, the monthly average PM2.5 concentration in Sichuan Province showed a V shape that first decreased and then increased, with the minimum value in June, the maximum value in December, and slight fluctuations in August and November. In terms of spatial distribution, the PM2.5 concentration in the eastern area of Sichuan Province was generally higher than that in the west, and the local pollution level was relatively high. The high-valued areas were mainly distributed in the eastern region, where the cities have been developing rapidly and the population was densely distributed, whereas the low-valued areas were mainly distributed in the western region, where it is sparsely populated with backward economic development. ④ Although the overall distribution of PM2.5 concentration estimated by the different models was essentially the same, the iLME+Geoi-RF model could more accurately and effectively estimate the spatial distribution of pollution in this study area. |
|
|
|
