Estimating the daily PM2.5 concentration in the Beijing-Tianjin-Hebei region using a random forest model with a 0.01° × 0.01° spatial resolution

Optimizing air quality monitoring spatial layout by maximizing the coverage of the population in Beijing-Tianjin-Hebei and surrounding areas

The spatial layout of the air quality monitoring network (AQMN) is crucial for objective, accurate, and comprehensive air quality assessment. The current technical standard specified the minimum quantity requirements for air quality monitoring sites, but there were no standards to specify the spatial of monitoring sites. This study proposed a novel framework to evaluate and optimize the spatial layout of AQMN. First, this study proposed three indicators to evaluate the performance of the current AQMN. They were monitoring area repetition rate, population coverage rate, and correlations. The assessment of AQMN in Beijing-Tianjin-Hebei and surroundings areas (BTHs) showed the overall monitoring area repetition rate and population coverage rate was 81.07 % and 35.5 %, respectively, which means the current AQMN in BTHs has very high monitoring repeatability and limited population coverage. Secondly, a large-scale linear programming model was built to optimize the spatial layout and determine the spatial location of 279 newly added monitoring sites in BTHs according to the Environmental Monitoring 14th Five-Year Plan of China. The optimization results showed that the optimized AQMN covered 97 million additional people, and the population coverage rate increased to 49.5 %. The proposed framework provided a valuable tool to evaluate and optimize AQMN and could be a potential solution for developing new technical standards of AQMN.

High-Resolution Spatiotemporal Modeling for PM2.5 Major Components in the Pearl River Delta and Its Implications for Epidemiological Studies

Distinguishing the effects of different fine particulate matter components (PMCs) is crucial for mitigating their effects on human health. However, the sparse distribution of locations where PM is collected for component analysis makes it challenging to investigate the relevant health effects. This study aimed to investigate the agreement between data-fusion-enhanced exposure assessment and site monitoring data in estimating the effects of PMCs on gestational diabetes mellitus (GDM). We first improved the spatial resolution and accuracy of exposure assessment for five major PMCs (EC, OM, NO3-, NH4+, and SO42-) in the Pearl River Delta region by a data fusion model that combined inputs from multiple sources using a random forest model (10-fold cross-validation R2: 0.52 to 0.61; root mean square error: 0.55 to 2.26 μg/m3). Next, we compared the associations between exposures to PMCs during pregnancy and GDM in a hospital-based cohort of 1148 pregnant women in Heshan, China, using both site monitoring data and data-fusion model estimates. The comparative analysis showed that the data-fusion-based exposure generated stronger estimates of identifying statistical disparities. This study suggests that data-fusion-enhanced estimates can improve exposure assessment and potentially mitigate the misclassification of population exposure arising from the utilization of site monitoring data.

A hybrid multi-scale fusion paradigm for AQI prediction based on the secondary decomposition

With rapid industrialization and urbanization, air pollution has become an increasingly severe problem. As a key indicator of air quality, accurate prediction of the air quality index (AQI) is essential for policymakers to establish effective early warning management mechanisms and adjust living plans. In this work, a hybrid multi-scale fusion prediction paradigm is proposed for the complex AQI time series prediction. First, an initial decomposition and integration of the original data is performed by combining the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and sample entropy (SE). Then, the subsequences, divided into high-frequency and low-frequency groups, are applied to different processing methods. Among them, the variational mode decomposition (VMD) is chosen to perform a secondary decomposition of the high-frequency sequence groups and integrated by using K-means clustering with sample entropy. Finally, multi-scale fusion training of sequence prediction results with different frequencies by using long short-term memory (LSTM) yields more accurate results with R2 of 0.9715, RMSE of 2.0327, MAE of 0.0154, and MAPE of 0.0488. Furthermore, validation of the AQI datasets acquired from four different cities demonstrates that the new paradigm is more robust and generalizable as compared to other baseline methods. Therefore, this model not only holds potential value in developing AQI prediction models but also serves as a valuable reference for future research on AQI control strategies.

Reconstructing annual XCO2 at a 1 km×1 km spatial resolution across China from 2012 to 2019 based on a spatial CatBoost method

Long-time-series, high-resolution datasets of the column-averaged dry-air mole fraction of carbon dioxide (XCO2) have great practical importance for mitigating the greenhouse effect, assessing carbon emissions and implementing a low-carbon cycle. However, the mainstream XCO2 datasets obtained from satellite observations have coarse spatial resolutions and are inadequate for supporting research applications with different precision requirements. Here, we developed a new spatial machine learning model by fusing spatial information with CatBoost, called SCatBoost, to fill the above gap based on existing global land-mapped 1° XCO2 data (GLM-XCO2). The 1-km-spatial-resolution dataset containing XCO2 values in China from 2012 to 2019 reconstructed by SCatBoost has stronger and more stable predictive power (confirmed with a cross-validation (R2 = 0.88 and RSME = 0.20 ppm)) than other traditional models. According to the estimated dataset, the overall national XCO2 showed an increasing trend, with the annual mean concentration rising from 392.65 ppm to 410.36 ppm. In addition, the spatial distribution of XCO2 concentrations in China reflects significantly higher concentrations in the eastern coastal areas than in the western inland areas. The contributions of this study can be summarized as follows: (1) It proposes SCatBoost, integrating the advantages of machine learning methods and spatial characteristics with a high prediction accuracy; (2) It presents a dataset of fine-scale and high resolution XCO2 over China from 2012 to 2019 by the model of SCatBoost; (3) Based on the generated data, we identify the spatiotemporal trends of XCO2 in the scale of nation and city agglomeration. These long-term and high resolution XCO2 data help understand the spatiotemporal variations in XCO2, thereby improving policy decisions and planning about carbon reduction.

Developing PM2.5 and PM10 prediction models on a national and regional scale using open-source remote sensing data

Clean air is the precursor to a healthy life. Air quality is an issue that has been getting under its well-deserved spotlight in the last few years. From a remote sensing point of view, the first Copernicus mission with the main purpose of monitoring the atmosphere and tracking air pollutants, the Sentinel-5P TROPOMI mission, has been widely used worldwide. Particulate matter of a diameter smaller than 2.5 and 10 μm (PM_2.5 and PM₁₀) significantly determines air quality. Still, there are no available satellite sensors that allow us to track them remotely with high accuracy, but only using ground stations. This research aims to estimate PM_2.5 and PM₁₀ using Sentinel-5P and other open-source remote sensing data available on the Google Earth Engine (GEE) platform for heating (December 2021, January, and February 2022) and non-heating seasons (June, July, and August 2021) on the territory of the Republic of Croatia. Ground stations of the National Network for Continuous Air Quality Monitoring were used as a starting point and as ground truth data. Raw hourly data were matched to remote sensing data, and seasonal models were trained at the national and regional scale using machine learning. The proposed approach uses a random forest algorithm with a percentage split of 70% and gives moderate to high accuracy regarding the temporal frame of the data. The mapping gives us visual insight between the ground and remote sensing data and shows the seasonal variations of PM_2.5 and PM₁₀. The results showed that the proposed approach and models could efficiently estimate air quality.

Air pollution as a substantial threat to the improvement of agricultural total factor productivity: Global evidence

OBJECTIVE

This study aims to provide empirical evidence about whether and to what extent air pollution affects the global agricultural total factor productivity (TFP).

METHODS

The research sample covers 146 countries all over the world during 2010-2019. Two-way fixed effects panel regression models are used to estimate air pollution's impacts. A random forest analysis is conducted to assess the relative importance of independent variables.

RESULTS

The results show that, on average, a 1% increase in fine particulate matter (PM_2.5) and tropospheric ozone (O₃) concentration would cause the agricultural TFP to decline by 0.104% and 0.207%, respectively. Air pollution's adverse impact widely exists in various countries with different development levels, pollution degrees, and industrial structures. This study also finds that temperature has a moderating effect on the relationship between PM_2.5 and agricultural TFP. PM_2.5 pollution's detrimental impact is weaker (stronger) in a warmer (cooler) climate. In addition, the random forest analysis confirms that air pollution is among the most crucial predictors of agricultural productivity.

CONCLUSIONS

Air pollution is a substantial threat to the improvement of global agricultural TFP. Worldwide actions should be taken to ameliorate air quality, for the sake of agricultural sustainability and global food security.

Spatial Differentiation of PM2.5 Concentration and Analysis of Atmospheric Health Patterns in the Xiamen-Zhangzhou-QuanZhou Urban Agglomeration

Exploring the spatial differentiation of PM2.5 concentrations in typical urban agglomerations and analyzing their atmospheric health patterns are necessary for building high-quality urban agglomerations. Taking the Xiamen-Zhangzhou-Quanzhou urban agglomeration as an example, and based on exploratory data analysis and mathematical statistics, we explore the PM2.5 spatial distribution patterns and characteristics and use hierarchical analysis to construct an atmospheric health evaluation system consisting of exposure-response degree, regional vulnerability, and regional adaptation, and then identify the spatial differentiation characteristics and critical causes of the atmospheric health pattern. This study shows the following: (1) The average annual PM2.5 value of the area in 2020 was 19.16 μg/m3, which was lower than China's mean annual quality concentration limit, and the overall performance was clean. (2) The spatial distribution patterns of the components of the atmospheric health evaluation system are different, with the overall cleanliness benefit showing a "north-central-south depression, the rest of the region is mixed," the regional vulnerability showing a coastal to inland decay, and the regional adaptability showing a "high north, low south, high east, low west" spatial divergence pattern. (3) The high-value area of the air health pattern of the area is an "F-shaped" spatial distribution; the low-value area shows a pattern of "north-middle-south" peaks standing side by side. The assessment of health patterns in the aforementioned areas can provide theoretical references for pollution prevention and control and the construction of healthy cities.

Contributors to reductions of PM2.5-bound heavy metal concentrations and health risks in a Chinese megacity during 2013, 2016 and 2019: An advanced method to quantify source-specific risks from various directions

PM_2.5-bound heavy metals were measured in a Chinese megacity (Tianjin) in 2013, 2016 and 2019, and analyzed by a new RSDA method (source directional apportionment of risks). Through combining the receptor model, cluster analysis of back trajectories, and risk assessment, the RSDA was developed in this work to quantify source-specific risks from each direction. Concentrations of PM_2.5 and most species (especially for heavy metals) underwent various reductions, and the incremental lifetime cancer risk (ILCR) and non-cancer risk (HQ) declined by more than 80% from 2013 to 2019. Pb was the highest contributor to the reduction of HMs mass concentration (58.6%), while Cr (85.5% for cancer risk) and As (26.0% for non-cancer risk) were more prominent for the reduction of HM risks. The coal combustion and industrial emissions were vital contributors to the reduction of both PM_2.5 mass concentrations (contributed 34.0% and 7.8% to the reduction respectively) and health risks (contributed 36.1% and 25.7% to the cancer risk reduction respectively). Although the percentage mass contribution of traffic emissions increased (7.7% in 2013 and 21.9% in 2019), the associated risks decreased (contributed 26.8% to the cancer risk reduction). Furthermore, the results of RSDA consistently implied that coal combustion, industrial emissions and traffic emissions controls in the northeast/north-northeast, south and southwest of the studied area played important roles in the risk reductions, which mainly due to the risk reduction of air masses from NE/NNE, S and SW, and their strong influence to Tianjin. The RSDA method can quantify the health risks from different sources and directions, and the evaluation of contributors to the reductions of risks in this work would provide a meaningful reference for policy maker to control PM_2.5 emissions and protect population health.

Long-term exposure to ozone and cardiovascular mortality in a large Chinese cohort

BACKGROUND

Evidence for the association between long-term exposure to ozone (O₃) and cause-specific cardiovascular disease (CVD) mortality is inconclusive, and this association has rarely been evaluated at high O₃ concentrations.

OBJECTIVES

We aim to evaluate the associations between long-term O₃ exposure and cause-specific CVD mortality in a Chinese population.

METHODS

From 2009 to 2018, 744,882 subjects (median follow-up of 7.72 years) were included in the CHinese Electronic health Records Research in Yinzhou (CHERRY) study. The annual average concentrations of O₃ and fine particulate matter (PM_2.5), which were estimated using grids with a resolution up to 1 × 1 km, were assigned to the community address for each subject. The outcomes were deaths from CVD, ischemic heart disease (IHD), myocardial infarction (MI), stroke, and hemorrhagic/ischemic stroke. Time-varying Cox model adjusted for PM_2.5 and individual-level covariates was used.

RESULTS

The mean of annual average O₃ concentrations was 68.05 μg/m³. The adjusted hazard ratio per 10 μg/m³ O₃ increase was 1.22 (95% confidence interval [CI]: 1.13-1.33) for overall CVD mortality, 1.08 (0.91-1.29) for IHD, 1.21 (0.90-1.63) for MI, 1.28 (1.15-1.43) for overall stroke, 1.39 (1.16-1.67) for hemorrhagic stroke and 1.22 (1.00-1.49) for ischemic stroke, respectively. The study showed that subjects without hypertension had a higher risk for CVD mortality associated with long-term O₃ exposure (1.66 vs. 1.15, p = 0.01).

CONCLUSIONS

We observed the association between long-term exposure to high O₃ concentrations and cause-specific CVD mortality in China, independent of PM_2.5 and other CVD risk factors. This suggested an urgent need to control O₃ pollution, especially in developing countries.

ZIP Code-Level Estimation of Air Quality and Health Risk Due to Particulate Matter Pollution in New York City

Exposure to PM_2.5 is associated with hundreds of premature mortalities every year in New York City (NYC). Current air quality and health impact assessment tools provide county-wide estimates but are inadequate for assessing health benefits at neighborhood scales, especially for evaluating policy options related to energy efficiency or climate goals. We developed a new ZIP Code-Level Air Pollution Policy Assessment (ZAPPA) tool for NYC by integrating two reduced form models─Community Air Quality Tools (C-TOOLS) and the Co-Benefits Risk Assessment Health Impacts Screening and Mapping Tool (COBRA)─that propagate emissions changes to estimate air pollution exposures and health benefits. ZAPPA leverages custom higher resolution inputs for emissions, health incidences, and population. It, then, enables rapid policy evaluation with localized ZIP code tabulation area (ZCTA)-level analysis of potential health and monetary benefits stemming from air quality management decisions. We evaluated the modeled 2016 PM_2.5 values against observed values at EPA and NYCCAS monitors, finding good model performance (FAC2, 1; NMSE, 0.05). We, then, applied ZAPPA to assess PM_2.5 reduction-related health benefits from five illustrative policy scenarios in NYC focused on (1) commercial cooking, (2) residential and commercial building fuel regulations, (3) fleet electrification, (4) congestion pricing in Manhattan, and (5) these four combined as a "citywide sustainable policy implementation" scenario. The citywide scenario estimates an average reduction in PM_2.5 of 0.9 μg/m³. This change translates to avoiding 210-475 deaths, 340 asthma emergency department visits, and monetized health benefits worth $2B to $5B annually, with significant variation across NYC's 192 ZCTAs. ZCTA-level assessments can help prioritize interventions in neighborhoods that would see the most health benefits from air pollution reduction. ZAPPA can provide quantitative insights on health and monetary benefits for future sustainability policy development in NYC.

Spatio-Temporal Characteristics of PM2.5 Concentrations in China Based on Multiple Sources of Data and LUR-GBM during 2016-2021

Fine particulate matter (PM2.5) has a continuing impact on the environment, climate change and human health. In order to improve the accuracy of PM2.5 estimation and obtain a continuous spatial distribution of PM2.5 concentration, this paper proposes a LUR-GBM model based on land-use regression (LUR), the Kriging method and LightGBM (light gradient boosting machine). Firstly, this study modelled the spatial distribution of PM2.5 in the Chinese region by obtaining PM2.5 concentration data from monitoring stations in the Chinese study region and established a PM2.5 mass concentration estimation method based on the LUR-GBM model by combining data on land use type, meteorology, topography, vegetation index, population density, traffic and pollution sources. Secondly, the performance of the LUR-GBM model was evaluated by a ten-fold cross-validation method based on samples, stations and time. Finally, the results of the model proposed in this paper are compared with those of the back propagation neural network (BPNN), deep neural network (DNN), random forest (RF), XGBoost and LightGBM models. The results show that the prediction accuracy of the LUR-GBM model is better than other models, with the R2 of the model reaching 0.964 (spring), 0.91 (summer), 0.967 (autumn), 0.98 (winter) and 0.976 (average for 2016-2021) for each season and annual average, respectively. It can be seen that the LUR-GBM model has good applicability in simulating the spatial distribution of PM2.5 concentrations in China. The spatial distribution of PM2.5 concentrations in the Chinese region shows a clear characteristic of high in the east and low in the west, and the spatial distribution is strongly influenced by topographical factors. The seasonal variation in mean concentration values is marked by low summer and high winter values. The results of this study can provide a scientific basis for the prevention and control of regional PM2.5 pollution in China and can also provide new ideas for the acquisition of data on the spatial distribution of PM2.5 concentrations within cities.

Machine learning driven by environmental covariates to estimate high-resolution PM2.5 in data-poor regions

PM_2.5, which refers to fine particles with an equivalent aerodynamic diameter of less than or equal to 2.5 µm, can not only affect air quality but also endanger public health. Nevertheless, the spatial distribution of PM_2.5 is not well understood in data-poor regions where monitoring stations are scarce. Therefore, we constructed a random forest (RF) model and a bagging algorithm model based on ground-monitored PM_2.5 data, aerosol optical depth (AOD) and meteorological data, and auxiliary geographical variables to accurately estimate the spatial distribution of PM_2.5 concentrations in Xinjiang during 2015-2020 at a resolution of 1 km. Through 10-fold cross-validation (CV), the RF model and bagging algorithm model were verified and compared. The results showed the following: (1) The RF model achieved better model performance and thus can be used to estimate the PM_2.5 concentration at a relatively high resolution. (2) The PM_2.5 concentrations were high in southern Xinjiang and low in northern Xinjiang. The high values were concentrated mainly in the Tarim Basin, while most areas of northern Xinjiang maintained low PM_2.5 levels year-round. (3) The PM_2.5 values in Xinjiang showed significant seasonality, with the seasonally averaged concentrations decreasing as follows: winter (71.95 µg m^-3) > spring (64.76 µg m^-3) > autumn (46.01 µg m^-3) > summer (43.40 µg m^-3). Our model provides a way to monitor air quality in data-scarce places, thereby advancing efforts to achieve sustainable development in the future.

Temporal and spatial variations of air pollution across China from 2015 to 2018

This study investigated concentrations of PM_2.5, PM₁₀, SO₂, NO₂, CO and O₃, and air quality index (AQI) values across 368 cities in mainland China during 2015-2018. The study further examined relationships of air pollution status with local industrial capacities and vehicle possessions. Strong correlations were found between industrial capacities (coal, pig iron, crude steel and rolled steel) and air pollution levels. Although statistical and significant reductions of PM_2.5, PM₁₀, SO₂, NO₂, CO and AQI values were observed in response to various laws and regulations in industrial sectors, both particle and gaseous pollutants still had annual average concentrations above recommended limits. In order to further reduce air pollution, more efforts can be done to control traffic emissions caused by minicars and heavy trucks, which was revealed after investigating 16 vehicle types. This was also consistent with the apparent air quality improvement during the COVID-19 lockdown period in China in 2020, despite industrial operations being still active at full capacities.

Obtaining vertical distribution of PM2.5 from CALIOP data and machine learning algorithms

Aerosol optical depth (AOD) has been widely used to estimate the near-surface PM_2.5 (fine particulate matter with particle size less than 2.5 μm). However, the total-column AOD obtained by passive remote sensing instruments can neither distinguish the contribution of AOD in various altitude layers nor obtain the vertical PM_2.5 concentration. In this study, we compared several AOD-PM_2.5 models including Extra Trees (ET), Random Forest (RF), Deep Neural Network (DNN), and Gradient Boosting Regression Tree (GBRT), and analyzed the corresponding results using AOD of different altitudes and auxiliary data from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP). The results indicate that the ET model performs best in terms of the model effectiveness and feature interpretation on the training dataset. We conclude that the feature importance of the bottom layer AOD is higher than that of the upper and total column AOD. The results showed that regional differences existed in the optimal height of the AOD-PM_2.5 correlation in study area. The results of cross-validation indicate that ET manages the most appealing overall performance with an R² (RMSE) of 0.85 (17.77 μg/m³). Regarding the 729 sites involved in this study, 73% had R² > 0.7, and the region or season with higher AOD feature importance achieves better model performance. The results of the AOD-PM_2.5 model in each layer were corrected using the AOD weight, to obtained the PM_2.5 vertical concentrations from 2015 to 2019. The results highlight that the high PM_2.5 concentration area is primarily near the ground and decreases with height. Additionally, the PM_2.5 vertical concentration in Beijing-Tianjin-Hebei (-1.80 μg/m³, P < 0.001), Central China (-1.62 μg/m³, P < 0.001), and Pearl River Delta (-0.66 μg/m³, P < 0.001) show an apparent downward trend. We believe that the vertical distribution analysis of PM_2.5 can provide meaningful information for studying air pollution.

Exposure assessment of PM2.5 using smart spatial interpolation on regulatory air quality stations with clustering of densely-deployed microsensors

Accurate mapping of air pollutants is essential for epidemiological studies and environmental risk assessments. Concentrations measured by air quality monitoring stations (AQMS) have primarily been used to assess the exposure of PM_2.5. However, the low coverage and amount of monitoring stations affect the errors of spatial interpolation or geostatistical estimates. In contrast to other integrated approaches developed for improved air pollution estimates, this study utilizes data from low-cost microsensors densely deployed in Taiwan to improve the popular spatial interpolation approach called inverse distance weighting (IDW). A large dataset from thousands of low-cost sensors could improve spatial interpolation by describing the distribution of PM_2.5 in detail. Therefore, this study presents a clustering-based method to assess the distribution of PM_2.5. Then, a smarter IDW is performed based on correlated observations from the selected air quality stations. The publicly available data chosen for this investigation pertained to Taiwan, which has deployed 74 monitoring stations and more than 11,000 low-cost sensors since December 2020. The results of leave-one-out cross-validation indicate that there are fewer PM_2.5 estimation errors in the developed approach than in estimations that use kriging across almost all of the months and sampled dates of 2019 and 2020, particularly those with higher PM_2.5 spatial heterogeneities. Spatial heterogeneities could result in more significant estimation errors in mainstream approaches. The root mean square error of the monthly average estimate for PM_2.5 ranged from 1.17 to 3.86 μg/m³. We also found that the clustering of one month characterizing the pattern of PM_2.5 distribution could perform well in spatial interpolations based on historical data from monitoring stations. According to the information on the openaq platform, low-cost sensors are in demand in cities and areas. This trend might pave the way for the application of the proposed approach in other areas for superior exposure assessments.

Estimation of the PM2.5 and PM10 Mass Concentration over Land from FY-4A Aerosol Optical Depth Data

The purpose of this study is to estimate the particulate matter (PM2.5 and PM10) in China using the improved geographically and temporally weighted regression (IGTWR) model and Fengyun (FY-4A) aerosol optical depth (AOD) data. Based on the IGTWR model, the boundary layer height (BLH), relative humidity (RH), AOD, time, space, and normalized difference vegetation index (NDVI) data are employed to estimate the PM2.5 and PM10. The main processes of this study are as follows: firstly, the feasibility of the AOD data from FY-4A in estimating PM2.5 and PM10 mass concentrations were analysed and confirmed by randomly selecting 5–6 and 9–10 June 2020 as an example. Secondly, hourly concentrations of PM2.5 and PM10 are estimated between 00:00 and 09:00 (UTC) each day. Specifically, the model estimates that the correlation coefficient R2 of PM2.5 is 0.909 and the root mean squared error (RMSE) is 5.802 μg/m3, while the estimated R2 of PM10 is 0.915, and the RMSE is 12.939 μg/m3. Our high temporal resolution results reveal the spatial and temporal characteristics of hourly PM2.5 and PM10 concentrations on the day. The results indicate that the use of data from the FY-4A satellite and an improved time–geographically weighted regression model for estimating PM2.5 and PM10 is feasible, and replacing land use classification data with NDVI facilitates model improvement.

An interpretable self-adaptive deep neural network for estimating daily spatially-continuous PM2.5 concentrations across China

Accurate estimation of daily spatially-continuous PM_2.5 (fine particulate matter) concentration is a prerequisite to address environmental public health issues, and satellite-based aerosol optical depth (AOD) products have been widely used to estimate PM_2.5 concentrations using statistical-based or machine learning-based models. However, statistical-based models oversimplify the AOD-PM_2.5 relationships, whereas complex machine learning technologies ignore the spatiotemporal heterogeneity of the predictors and demonstrate shortage in interpretation. Besides, large AOD data gaps resulting in PM_2.5 estimation biases have been seldom imputed in previous studies, especially at national scales. To fill the above research gaps, this study attempts to present a feasible methodology to estimate daily spatially-continuous PM_2.5 concentrations in China. The AOD data gaps across China were first imputed via a random forest (RF) model. Then, an interpretable self-adaptive deep neural network (SADNN) model, incorporating AOD, meteorological and other auxiliary predictors, was developed to estimate daily spatially-continuous PM_2.5 concentrations from 2017 to 2018. Five-fold sample (site)-based cross-validation results showed a high accuracy of the SADNN model, with coefficient of determination and root mean square error values equal to 0.86 (0.84) and 13.07 (14.30) μg/m³, respectively, outperforming the standard DNN and the RF model. Furthermore, the SADNN model identified the spatiotemporal patterns of predictor importance, and demonstrated that the boundary layer height, elevation and AOD were the most important predictors both spatially and temporally. And the predictor importance in the Qinghai-Tibet Plateau was different from that in the rest of China. These results enhance our understanding of AOD-PM_2.5 relationships and elucidate the estimated PM_2.5 datasets with complete coverage are applicable for related air pollution studies and epidemiological cohort studies. Moreover, considering the effective nonlinear model capability and interpretability, the SADNN model is beneficial for not only PM_2.5 estimation but also other earth data and scenarios.

Random forest model based fine scale spatiotemporal O3 trends in the Beijing-Tianjin-Hebei region in China, 2010 to 2017

Ambient ozone (O₃) concentrations have shown an upward trend in China and its health hazards have also been recognized in recent years. High-resolution exposure data based on statistical models are needed. Our study aimed to build high-performance random forest (RF) models based on training data from 2013 to 2017 in the Beijing-Tianjin-Hebei (BTH) region in China at a 0.01 ° × 0.01 ° resolution, and estimated daily maximum 8h average O₃ (O₃-8hmax) concentration, daily average O₃ (O₃-mean) concentration, and daily maximum 1h O₃ (O₃-1hmax) concentration from 2010 to 2017. Model features included meteorological variables, chemical transport model output variables, geographic variables, and population data. The test-R² of sample-based O₃-8hmax, O₃-mean and O₃-1hmax models were all greater than 0.80, while the R² of site-based and date-based model were 0.68-0.87. From 2010 to 2017, O₃-8hmax, O₃-mean, and O₃-1hmax concentrations in the BTH region increased by 4.18 μg/m³, 0.11 μg/m³, and 4.71 μg/m³, especially in more developed regions. Due to the influence of weather conditions, which showed high contribution to the model, the long-term spatial distribution of O₃ concentrations indicated a similar pattern as altitude, where high concentration levels were distributed in regions with higher altitude.

Constructing a spatiotemporally coherent long-term PM2.5 concentration dataset over China during 1980-2019 using a machine learning approach

The lack of long-term observations and satellite retrievals of health-damaging fine particulate matter in China has demanded the estimates of historical PM_2.5 (particulate matter less than 2.5 μm in diameter) concentrations. This study constructs a gridded near-surface PM_2.5 concentration dataset across China covering 1980-2019 using the space-time random forest model with atmospheric visibility observations and other auxiliary data. The modeled daily PM_2.5 concentrations are in excellent agreement with ground measurements, with a coefficient of determination of 0.95 and mean relative error of 12%. Besides the atmospheric visibility which explains 30% of total importance of variables in the model, emissions and meteorological conditions are also key factors affecting PM_2.5 predictions. From 1980 to 2014, the model-predicted PM_2.5 concentrations increased constantly with the maximum growth rate of 5-10 μg/m³/decade over eastern China. Due to the clean air actions, PM_2.5 concentrations have decreased effectively at a rate over 50 μg/m³/decade in the North China Plain and 20-50 μg/m³/decade over many regions of China during 2014-2019. The newly generated dataset of 1-degree gridded PM_2.5 concentrations for the past 40 years across China provides a useful means for investigating interannual and decadal environmental and climate impacts related to aerosols.

Estimating the Daily NO2 Concentration with High Spatial Resolution in the Beijing–Tianjin–Hebei Region Using an Ensemble Learning Model

Nitrogen dioxide (NO2) is an important pollutant related to human activities, which has short-term and long-term effects on human health. An ensemble learning model was constructed and applied to estimate daily NO2 concentrations in the Beijing–Tianjin–Hebei region between 2010 and 2016. A variety of predictive variables included satellite-based troposphere NO2 vertical column concentration, meteorology, elevation, gross domestic product (GDP), population, land-use variables, and road network. The ensemble learning model achieved two things: a 0.01° × 0.01° grid resolution and the estimation of historical data for the years 2010–2013. The ensemble model showed good performance, whereby the R2 of tenfold cross-validation was 0.72 and the R2 of test validation was 0.71. Meteorological hysteretic effects were incorporated into the model, where the one-day lagged boundary layer height contributed the most. The annual NO2 estimation showed little change from 2010 to 2016. The seasonal NO2 estimation from highest to lowest occurred in winter, autumn, spring, and summer. In the annual maps and seasonal maps, the NO2 estimations in the northwest region were lower than those in the southeast region, and there was a heavily polluted band in the south of the Taihang Mountains. In coastal areas, the annual NO2 estimations were higher than the NO2 monitored values. The drawback of the model is underestimation at high values and overestimation at low values. This study indicates that the ensemble learning model has excellent performance in the simulation of NO2 with high spatial and temporal resolution. Furthermore, the research framework in this study can be a generally applied for drawing implications for other regions, especially for other cities in China.

Estimating PM2.5 Concentrations Using Spatially Local Xgboost Based on Full-Covered SARA AOD at the Urban Scale

The adverse effects caused by PM2.5 have drawn extensive concern and it is of great significance to identify its spatial distribution. Satellite-derived aerosol optical depth (AOD) has been widely used for PM2.5 estimation. However, the coarse spatial resolution and the gaps caused by data deficiency impede its better application at the urban scale. Additionally, obtaining accurate results in unsampled spatial areas when PM2.5 ground sites are insufficient and distribute sparsely is also a challenging issue for PM2.5 spatial distribution estimation. This paper aimed to develop a model, i.e., spatially local extreme gradient boosting (SL-XGB), combining the powerful fitting ability of machine learning and optimal bandwidths of local models, to better estimate PM2.5 concentration at the urban scale by using Beijing as the study area. This paper adopted simplified high-resolution MODIS aerosol retrieval algorithm (SARA) AOD at 500 m resolution as the major independent variable, hence, ensuring the estimation can be operated at a fine scale. Moreover, the extreme gradient boosting (XGBoost) model was adopted to fill the gaps in SARA AOD, thus improving its availability. Then, based on full-covered SARA AOD and other multisource data, the SL-XGB model, integrating multiple local XGBoost models and particular optimal bandwidths, was trained to estimate PM2.5 concentration. For comparison, SL-XGB and two other models, XGBoost and geographically weighted regression (GWR), were evaluated by 10-fold cross validation (CV). The sample-based CV results reveal that the SL-XGB performed the best as assessed through R2 (0.88), root mean square error (RMSE = 24.08 μg/m3) and mean prediction error (MPE = 16.90 μg/m3). Additionally, SL-XGB also performed the best in the site-based CV with a R2 of 0.86, a RMSE of 26.15 μg/m3 and a MPE of 17.97 μg/m3, which shows its good spatial generalization ability. These results demonstrate that SL-XGB can better simultaneously handle non-linear and spatial heterogeneity issues despite spatially limited data at the urban scale. As far as the PM2.5 concentration distribution was concerned, it presented a gradient increase in PM2.5 concentrations from the northwest to the southeast in Beijing, with abundant spatial details. Overall, the proposed approach for PM2.5 estimation showed outstanding performance and can support preventive pollution control and mitigation at the urban scale.

Estimating PM2.5 concentrations in Yangtze River Delta region of China using random forest model and the Top-of-Atmosphere reflectance

Previous studies that have used remote sensing data to estimate the PM_2.5 concentrations mainly focused on the retrieval of aerosol optical depth (AOD) with moderate-to-low spatial resolution. However, the complex process of retrieving AOD from satellite Top-of-Atmosphere (TOA) reflectance always generates the missingness of AOD values due to the limitation of AOD retrieval algorithms. This study validated the possibility of using satellite TOA reflectance for estimating PM_2.5 concentrations, rather than using conventional AOD products retrieved from remote sensing imageries. Given that the TOA-PM_2.5 relationship cannot be accurately expressed by simple linear correlation, we developed a random forest model that integrated satellite TOA reflectance from Moderate Resolution Imaging Spectroradiometer (MODIS) Level 1B product, meteorological fields and land-use variables to estimate the ground-level PM_2.5 concentrations. The highly-polluted Yangtze River Delta (YRD) region of eastern China was employed as our study case. The results showed that our model performed well with a site-based and a time-based CV R² of 0.92 and 0.88, respectively. The derived annual and seasonal distributions of PM_2.5 concentrations exhibited high PM_2.5 values in northern YRD region (i.e., Jiangsu province) and relatively low values in southern region (i.e., Zhejiang province), which shared a similar distribution trend with the observed PM_2.5 concentrations. This study demonstrated the outstanding performance of random forest model using satellite TOA reflectance, and also provided an effective method for remotely sensed PM_2.5 estimation in regions where AOD retrievals are unavailable.

The changing PM2.5 dynamics of global megacities based on long-term remotely sensed observations

Satellite observations show that the rapid urbanization and emergence of megacities with 10 million or more residents have raised PM2.5 concentrations across the globe during the past few decades. This study examines PM2.5 dynamics for the 33 cities included on the UN list of megacities published in 2018. These megacities were classified into densely (>1500 residents per km²), moderately (300-1500 residents per km²) and sparsely (<300 residents per km²) populated areas to examine the effect of human population density on PM2.5 concentrations in these areas during the period 1998-2016. We found that: (1) the higher population density areas experienced higher PM2.5 concentrations; and (2) the megacities with high PM2.5 concentrations in these areas had higher concentrations than those in the moderately and sparsely populated areas of other megacities as well. The numbers of residents experiencing poor air quality is substantial: approximately 452 and 163 million experienced average annual PM2.5 levels exceeding 10 and 35 μg/m³, respectively in 2016. We also examined PM2.5 trends during the past 18 years and predict that high PM2.5 levels will likely continue in many of these megacities in the future without substantial changes in their economies and/or pollution abatement practices. There will be more megacities in the highest PM2.5 pollution class and the number of megacities in the lowest PM2.5 pollution class will likely not change. Finally, we analyzed how the PM2.5 pollution burden varies geographically and ranked the 33 megacities in terms of PM2.5 pollution in 2016. The most polluted regions are China, India, and South Asia and the least polluted regions are Europe and Japan. None of the 33 megacities currently fall in the WHO's PM2.5 attainment class (<10 μg/m³) while 9 megacities fall into the PM2.5 non-attainment class (>35 μg/m³). In 2016, the least polluted megacity was New York and most polluted megacity was Delhi whose average annual PM2.5 concentration of 110 μg/m³ is nearly three times the WHO's non-attainment threshold.

Spatiotemporal variation and determinants of population's PM2.5 exposure risk in China, 1998-2017: a case study of the Beijing-Tianjin-Hebei region

PM2.5 pollution has emerged as a global human health risk. The best measure of its impact is a population's PM2.5 exposure (PPM2.5E), an index that simultaneously considers PM2.5 concentrations and population spatial density. The spatiotemporal variation of PPM2.5E over the Beijing-Tianjin-Hebei (BTH) region, which is the national capital region of China, was investigated using a Bayesian space-time model, and the influence patterns of the anthropic and geographical factors were identified using the GeoDetector model and Pearson correlation analysis. The spatial pattern of PPM2.5E maintained a stable structure over the BTH region's distinct terrain, which has been described as "high in the northwest, low in the southeast". The spatial difference of PPM2.5E intensified annually. An overall increase of 6.192 (95% CI 6.186, 6.203) ×103 μg/m3 ∙ persons/km2 per year occurred over the BTH region from 1998 to 2017. The evolution of PPM2.5E in the region can be described as "high value, high increase" and "low value, low increase", since human activities related to gross domestic product (GDP) and energy consumption (EC) were the main factors in its occurrence. GDP had the strongest explanatory power of 76% (P < 0.01), followed by EC and elevation (EL), which accounted for 61% (P < 0.01) and 40% (P < 0.01), respectively. There were four factors, proportion of secondary industry (PSI), normalized differential vegetation index (NDVI), relief amplitude (RA), and EL, associated negatively with PPM2.5E and four factors, GDP, EC, annual precipitation (AP), and annual average temperature (AAT), associated positively with PPM2.5E. Remarkably, the interaction of GDP and NDVI, which was 90%, had the greatest explanatory power for PPM2.5E ' s diffusion and impact on the BTH region.