Zeng Liyue, Hang Jian, Wang Xuemei, Shao Min
School of Atmospheric Sciences, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, China; Key Laboratory of Tropical Atmosphere-Ocean System (Sun Yat-sen University), Ministry of Education, Zhuhai 519000, China; Guangdong Provincial Field Observation and Research Station for Climate Environment and Air Quality Change in the Pearl River Estuary, Guangzhou 510275, China.
School of Atmospheric Sciences, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, China; Key Laboratory of Tropical Atmosphere-Ocean System (Sun Yat-sen University), Ministry of Education, Zhuhai 519000, China; Guangdong Provincial Field Observation and Research Station for Climate Environment and Air Quality Change in the Pearl River Estuary, Guangzhou 510275, China.
J Environ Sci (China). 2022 Apr;114:485-502. doi: 10.1016/j.jes.2021.12.002. Epub 2021 Dec 21.
The intraurban distribution of PM concentration is influenced by various spatial, socioeconomic, and meteorological parameters. This study investigated the influence of 37 parameters on monthly average PM concentration at the subdistrict level with Pearson correlation analysis and land-use regression (LUR) using data from a subdistrict-level air pollution monitoring network in Shenzhen, China. Performance of LUR models is evaluated with leave-one-out-cross-validation (LOOCV) and holdout cross-validation (holdout CV). Pearson correlation analysis revealed that Normalized Difference Built-up Index, artificial land fraction, land surface temperature, and point-of-interest (POI) numbers of factories and industrial parks are significantly positively correlated with monthly average PM concentrations, while Normalized Difference Vegetation Index and Green View Factor show significant negative correlations. For the sparse national stations, robust LUR modelling may rely on a priori assumptions in direction of influence during the predictor selection process. The month-by-month spatial regression shows that RF models for both national stations and all stations show significantly inflated mean values of R compared with cross-validation results. For MLR models, inflation of both R and R was detected when using only national stations and may indicate the restricted ability to predict spatial distribution of PM levels. Inflated within-sample R also exist in the spatiotemporal LUR models developed with only national stations, although not as significant as spatial LUR models. Our results suggest that a denser subdistrict level air pollutant monitoring network may improve the accuracy and robustness in intraurban spatial/spatiotemporal prediction of PM concentrations.
城区内PM浓度的分布受多种空间、社会经济和气象参数的影响。本研究利用中国深圳一个街道级空气污染监测网络的数据，通过Pearson相关分析和土地利用回归（LUR），研究了37个参数对街道级月平均PM浓度的影响。LUR模型的性能通过留一法交叉验证（LOOCV）和留出法交叉验证（holdout CV）进行评估。Pearson相关分析表明，归一化差异建成指数、人工用地比例、地表温度以及工厂和工业园区的兴趣点（POI）数量与月平均PM浓度显著正相关，而归一化差异植被指数和绿视率则呈显著负相关。对于稀疏的国家站点，稳健的LUR建模在预测变量选择过程中可能依赖于影响方向的先验假设。逐月空间回归表明，与交叉验证结果相比，国家站点和所有站点的随机森林（RF）模型的R均值均显著夸大。对于多元线性回归（MLR）模型，仅使用国家站点时检测到R和调整后R²均存在膨胀，这可能表明其预测PM水平空间分布的能力有限。仅使用国家站点开发的时空LUR模型中也存在样本内R²膨胀的情况，尽管不如空间LUR模型那么显著。我们的结果表明，更密集的街道级空气污染物监测网络可能会提高城区内PM浓度空间/时空预测的准确性和稳健性。
