Factors Underlying Spatiotemporal Variations in Atmospheric PM2.5 Concentrations in Zhejiang Province, China

Spatiotemporal drivers of urban water pollution: Assessment of 102 cities across the Yangtze River Basin

Effective management of large basins necessitates pinpointing the spatial and temporal drivers of primary index exceedances and urban risk factors, offering crucial insights for basin administrators. Yet, comprehensive examinations of multiple pollutants within the Yangtze River Basin remain scarce. Here we introduce a pollution inventory for urban clusters surrounding the Yangtze River Basin, analyzing water quality data from 102 cities during 2018-2019. We assessed the exceedance rates for six pivotal indicators: dissolved oxygen (DO), ammonia nitrogen (NH3-N), chemical oxygen demand (COD), biochemical oxygen demand (BOD), total phosphorus (TP), and the permanganate index (CODMn) for each city. Employing random forest regression and SHapley Additive exPlanations (SHAP) analyses, we identified the spatiotemporal factors influencing these key indicators. Our results highlight agricultural activities as the primary contributors to the exceedance of all six indicators, thus pinpointing them as the leading pollution source in the basin. Additionally, forest coverage, livestock farming, chemical and pharmaceutical sectors, along with meteorological elements like precipitation and temperature, significantly impacted various indicators' exceedances. Furthermore, we delineate five core urban risk components through principal component analysis, which are (1) anthropogenic and industrial activities, (2) agricultural practices and forest extent, (3) climatic variables, (4) livestock rearing, and (5) principal polluting sectors. The cities were subsequently evaluated and categorized based on these risk components, incorporating policy interventions and administrative performance within each region. The comprehensive analysis advocates for a customized strategy in addressing the discerned risk factors, especially for cities presenting elevated risk levels.

High-resolution mapping of regional VOCs using the enhanced space-time extreme gradient boosting machine (XGBoost) in Shanghai

The accurate estimation of highly spatiotemporal volatile organic compounds (VOCs) is of great significance to establish advanced early warning systems and regulate air pollution control. However, the estimation of high spatiotemporal VOCs remains incomplete. Here, the space-time extreme gradient boost model (STXGB) was enhanced by integrating spatiotemporal information to obtain the spatial resolution and overall accuracy of VOCs. To this end, meteorological, topographical and pollutant emissions, was input to the STXGB model, and regional hourly 300 m VOCs maps for 2020 in Shanghai were produced. Our results show that the STXGB model achieve good hourly VOCs estimations performance (R2 = 0.73). A further analysis of SHapley Additive exPlanation (SHAP) regression indicate that local interpretations of the STXGB models demonstrate the strong contribution of emissions on mapping VOCs estimations, while acknowledging the important contribution of space and time term. The proposed approach outperforms many traditional machine learning models with a lower computational burden in terms of speed and memory.

Retrieval of hourly PM2.5 using top-of-atmosphere reflectance from geostationary ocean color imagers I and II

To produce real-time ground-level information on particulate matter with a diameter equal to or less than 2.5 μm (PM_2.5), many studies have explored the applicability of satellite data, particularly aerosol optical depth (AOD). However, many of the techniques used are computationally demanding; to overcome these challenges, machine learning(ML)-based research has been on the rise. Here, we used ML techniques to directly estimate ground-level PM_2.5 concentrations over South Korea using top-of-atmosphere (TOA) reflectance from the Geostationary Ocean Color Imager I (GOCI-I) and its next generation GOCI-II with improved spatial, spectral, and temporal resolutions. Three ML techniques were used to estimate ground-level PM_2.5 concentrations: random forest, light gradient boosting machine (LGBM), and artificial neural network. Three schemes were examined based on the input feature composition of the GOCI spectral bands: scheme 1 using all GOCI-I bands, scheme 2 using only GOCI-II bands that overlap with GOCI-I bands, and scheme 3 using all GOCI-II bands. The results showed that LGBM performed better than the other ML models. GOCI-II-based schemes 2 and 3 (determination of coefficient (R²) = 0.85 and 0.85 and root-mean-square-error (RMSE) = 7.69 and 7.82 μg/m³, respectively) performed slightly better than GOCI-I-based scheme 1 (R² = 0.83 and RMSE = 8.49 μg/m³). In particular, TOA reflectance at a new channel (380 nm) of GOCI-II was identified as the most contributing variable, given its high sensitivity to aerosols. The long-term estimation of PM_2.5 concentrations using the proposed models was examined for ground stations located in two major cities. GOCI-II-based models produced a more detailed spatial distribution of PM_2.5 concentrations owing to their higher spatial resolution (i.e., 250 m). The use of TOA reflectance data, instead of AOD and other aerosol products commonly used in previous studies, reduced the missing rate of the estimated ground-level PM_2.5 concentrations by up to 50%. Our results indicate that the proposed approach using TOA reflectance data from geostationary satellite sensors has great potential for estimating ground-level PM_2.5 concentrations for operational purposes.

Pixel level spatial variability modeling using SHAP reveals the relative importance of factors influencing LST

As an important indicator of the regional thermal environment, land surface temperature (LST) is closely related to community health and regional sustainability in general, and is influenced by multiple factors. Previous studies have paid scant attention to spatial heterogeneity in the relative contribution of factors underlying LST. In this study of Zhejiang Province, we investigated the key factors affecting daytime and nighttime annual mean LST and the spatial distribution of their respective contributions. The eXtreme Gradient Boosting tree (XGBoost) and Shapley Additive exPlanations algorithm (SHAP) approach were used in combination with three sampling strategies (Province-Urban Agglomeration -Gradients within Urban Agglomeration) to detect spatial variation. The results reveal heterogenous LST spatial distribution with lower LST in the southwestern mountainous region and higher temperatures in the urban center. Spatially explicit SHAP maps indicate that latitude and longitude (geographical locations) are the most important factors at the provincial level. In urban agglomerations, factors associated with elevation and nightlight are shown to positively impact daytime LST in lower altitude regions. In the urban centers, EVI and MNDWI are the most notable influencing factors on LST at night. Under different sampling strategies, EVI, MNDWI, NL, and NDBI affect LST more prominently at smaller spatial scales as compared to AOD, latitude and TOP. The SHAP method proposed in this paper offers a useful means for management authorities in addressing LST in a warming climate.

Retrieval of Fine-Grained PM2.5 Spatiotemporal Resolution Based on Multiple Machine Learning Models

Due to the country’s rapid economic growth, the problem of air pollution in China is becoming increasingly serious. In order to achieve a win-win situation for the environment and urban development, the government has issued many policies to strengthen environmental protection. PM2.5 is the primary particulate matter in air pollution, so an accurate estimation of PM2.5 distribution is of great significance. Although previous studies have attempted to retrieve PM2.5 using geostatistical or aerosol remote sensing retrieval methods, the current rough resolution and accuracy remain as limitations of such methods. This paper proposes a fine-grained spatiotemporal PM2.5 retrieval method that comprehensively considers various datasets, such as Landsat 8 satellite images, ground monitoring station data, and socio-economic data, to explore the applicability of different machine learning algorithms in PM2.5 retrieval. Six typical algorithms were used to train the multi-dimensional elements in a series of experiments. The characteristics of retrieval accuracy in different scenarios were clarified mainly according to the validation index, R2. The random forest algorithm was shown to have the best numerical and PM2.5-based air-quality-category accuracy, with a cross-validated R2 of 0.86 and a category retrieval accuracy of 0.83, while both maintained excellent retrieval accuracy and achieved a high spatiotemporal resolution. Based on this retrieval model, we evaluated the PM2.5 distribution characteristics and hourly variation in the sample area, as well as the functions of different input variables in the model. The PM2.5 retrieval method proposed in this paper provides a new model for fine-grained PM2.5 concentration estimation to determine the distribution laws of air pollutants and thereby specify more effective measures to realize the high-quality development of the city.