| 基于时空XGBoost模型的关中地区小时级PM2.5质量浓度估算 |
| 摘要点击 1653 全文点击 201 投稿时间：2024-12-24 修订日期：2025-04-07 |
| 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 Himawari-8表观反射率 PM2.5 STXGBoost模型 时空分布 卫星遥感 |
| 英文关键词 Himawari-8 apparent reflectance PM2.5 STXGBoost model spatio-temporal distribution satellite remote sensing |
| DOI 10.13227/j.hjkx.20260201 |
|
| 中文摘要 |
| 为提高模型估算精度并获取小时级PM2.5浓度数据，以Himawari-8表观反射率小时数据、PM2.5站点数据、气象数据、人口数据、DEM数据和森林覆盖率数据为基础，提出一种考虑数据时空异质性的STXGBoost模型来估算关中地区2022年小时级PM2.5浓度，并分析其时空分布特征. 结果表明：①与SVM、RF和XGBoost模型相比，STXGBoost模型估算精度最高，模型泛化能力较强，模型在全数据集上的十折交叉验证结果R2为0.96，RMSE和MAE分别为7.17 μg·m-3和3.82 μg·m-3，在小时尺度估算上STXGBoost模型亦表现出较高的估算精度，模型稳定性较强，适用于关中地区PM2.5浓度估算；②关中地区08：00~17：00年均PM2.5浓度呈现出“M”的趋势，季节变化趋势明显，冬季PM2.5浓度最高，污染最为严重且呈现出“早高晚低”的趋势；③在空间分布上，关中地区PM2.5浓度高值区域主要集中于关中腹地，西部、北部和南部山区PM2.5浓度较低. |
| 英文摘要 |
| To improve model estimation accuracy and obtain hourly-scale PM2.5 concentration data， a spatiotemporal XGBoost （STXGBoost） model incorporating data heterogeneity was developed， integrating multi-source datasets including Himawari-8 hourly apparent reflectance， ground-level PM2.5 measurements， meteorological variables， population density， DEM， and forest coverage. The model was applied to estimate hourly PM2.5 concentrations across the Guanzhong region in 2022 and analyze their spatiotemporal characteristics. The results showed that： ① The STXGBoost model demonstrated superior estimation accuracy and generalization capability compared to the SVM， RF， and XGBoost models. Ten-fold cross-validation on the full dataset achieved an R2 of 0.96， with RMSE and MAE values of 7.17 μg·m-3 and 3.82 μg·m-3， respectively. The model exhibited robust hourly-scale estimation precision and stability， confirming its applicability for PM2.5 monitoring in the Guanzhong region. ② Annual PM2.5 concentrations from 08：00 to 17：00 local time displayed an “M-shaped” diurnal curve. Seasonal variations were pronounced， with winter exhibiting the highest pollution levels （characterized by a “morning-peak， evening-trough” diurnal pattern） and the most severe air quality degradation. ③ Spatially， elevated PM2.5 concentrations clustered predominantly in the central Guanzhong Plain， while lower values prevailed in the western， northern， and southern mountainous areas. |
