Estimating PM2.5 concentrations via random forest method using satellite, auxiliary, and ground-level station dataset at multiple temporal scales across China in 2017

Towards cleaner air in urban areas: The dual influence of urban built environment factors and regional transport

Exposure to air pollution significantly elevates the risk of disease among urban populations. Improving city air quality requires not only traditional emission reduction strategies but also a focus on the intricate impacts of the urban built environment and meteorological elements. The complexity and diversity of factors within the urban built environment pose significant challenges to pollution control. This study employs machine learning to predict the spatial distribution of inhalable particulate matter (PM10) and fine particulate matter (PM2.5), integrating the clustering of pollutant-emitting enterprises and prevailing wind direction to trace pollutant sources. The results indicate that, compared to the multiple linear regression model, the R2 of the PM10 random forest prediction model improved from 0.64 to 0.88, while the RMSE decreased from 48.63 to 27.34. Similarly, the R2 of the PM2.5 increased from 0.70 to 0.92, and the RMSE decreased from 30.85 to 15.31. High concentrations of PM10 and PM2.5 in Xi'an are primarily concentrated in the northeast and southwest of the central urban area. By integrating a kernel density analysis of polluting enterprises with the analysis of prevailing wind patterns, it is evident that particulate matter in Xi'an is substantially influenced by regional urban transport. Therefore, pollution control efforts must be enhanced through coordinated regional governance. According to the analysis results of the partial dependence plot, reducing winter temperature proves beneficial in reducing PM10 and PM2.5 levels. Effective measures encompass sprinkling and humidifying, reducing traffic emissions, and controlling various dust sources to lower PM10. Enhancing ventilation, increasing green spaces, and regulating vehicle and industrial emissions effectively reduce PM2.5. The study's findings offer a scientific foundation for administrative authorities to craft pollution reduction management policies and create adaptable territorial spatial planning. Moreover, they contribute to diminishing public exposure to pollution and improving the quality of public environmental health.

Exploring the association of PM2.5 with lung cancer incidence under different climate zones and socioeconomic conditions from 2006 to 2016 in China

Air pollution generated by urbanization and industrialization poses a significant negative impact on public health. Particularly, fine particulate matter (PM2.5) has become one of the leading causes of lung cancer mortality worldwide. The relationship between air pollutants and lung cancer has aroused global widespread concerns. Currently, the spatial agglomeration dynamic of lung cancer incidence (LCI) has been seldom discussed, and the spatial heterogeneity of lung cancer's influential factors has been ignored. Moreover, it is still unclear whether different socioeconomic levels and climate zones exhibit modification effects on the relationship between PM2.5 and LCI. In the present work, spatial autocorrelation was adopted to reveal the spatial aggregation dynamic of LCI, the emerging hot spot analysis was introduced to indicate the hot spot changes of LCI, and the geographically and temporally weighted regression (GTWR) model was used to determine the affecting factors of LCI and their spatial heterogeneity. Then, the modification effects of PM2.5 on the LCI under different socioeconomic levels and climatic zones were explored. Some findings were obtained. The LCI demonstrated a significant spatial autocorrelation, and the hot spots of LCI were mainly concentrated in eastern China. The affecting factors of LCI revealed an obvious spatial heterogeneity. PM2.5 concentration, nighttime light data, 2 m temperature, and 10 m u-component of wind represented significant positive effects on LCI, while education-related POI exhibited significant negative effects on LCI. The LCI in areas with low urbanization rates, low education levels, and extreme climate conditions was more easily affected by PM2.5 than in other areas. The results can provide a scientific basis for the prevention and control of lung cancer and related epidemics.

Application of machine learning (individual vs stacking) models on MERRA-2 data to predict surface PM2.5 concentrations over India

The spatial coverage of PM2.5 monitoring is non-uniform across India due to the limited number of ground monitoring stations. Alternatively, Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2), is an atmospheric reanalysis data used for estimating PM2.5. MERRA-2 does not explicitly measure PM2.5 but rather follows an empirical model. MERRA-2 data were spatiotemporally collocated with ground observation for validation across India. Significant underestimation in MERRA-2 prediction of PM2.5 was observed over many monitoring stations ranging from -20 to 60 μg m-3. The utility of Machine Learning (ML) models to overcome this challenge was assessed. MERRA-2 aerosol and meteorological parameters were the input features used to train and test the individual ML models and compare them with the stacking technique. Initially, with 10% of randomly selected data, individual model performance was assessed to identify the best model. XGBoost (XGB) was the best model (r2 = 0.73) compared to Random Forest (RF) and LightGBM (LGBM). Stacking was then applied by keeping XGB as a meta-regressor. Stacked model results (r2 = 0.77) outperformed the best standalone estimate of XGB. Stacking technique was used to predict hourly and daily PM2.5 in different regions across India and each monitoring station. The eastern region exhibited the best hourly prediction (r2 = 0.80) and substantial reduction in Mean Bias (MB = -0.03 μg m-3), followed by the northern region (r2 = 0.63 and MB = -0.10 μg m-3), which showed better output due to the frequent observation of PM2.5 >100 μg m-3. Due to sparse data availability to train the ML models, the lowest performance was for the central region (r2 = 0.46 and MB = -0.60 μg m-3). Overall, India's PM2.5 prediction was good on an hourly basis compared to a daily basis using the ML stacking technique.

Unmasking air quality: A novel image-based approach to align public perception with pollution levels

In the quest to reconcile public perception of air pollution with scientific measurements, our study introduced a pioneering method involving a gradient boost-regression tree model integrating PM2.5 concentration, visibility, and image-based data. Traditional stationary monitoring often falls short of accurately capturing public air quality perceptions, prompting the need for alternative strategies. Leveraging an extensive dataset of over 20,000 public visibility perception evaluations and over 8,000 stationary images, our models effectively quantify diverse air quality perceptions. The predictive prowess of our models was validated by strong performance metrics for perceived visibility (R = 0.98, RMSE = 0.19), all-day PM2.5 concentrations (R: 0.77-0.78, RMSE: 8.31-9.40), and Central Weather Bureau visibility records (R = 0.82, RMSE = 9.00). Interestingly, image contrast and light intensity hold greater importance than scenery clarity in the visibility perception model. However, clarity is prioritized in PM2.5 and Central Weather Bureau models. Our research also unveiled spatial limitations in stationary monitoring and outlined the variations in predictive image features between near and far stations. Crucially, all models benefit from the characterization of atmospheric light sources through defogging techniques. The image-based insights highlight the disparity between public perception of air pollution and current policy implementation. In other words, policymakers should shift from solely emphasizing the reduction of PM2.5 levels to also incorporating the public's perception of visibility into their strategies. Our findings have broad implications for air quality evaluation, image mining in specific areas, and formulating air quality management strategies that account for public perception.

72-hour real-time forecasting of ambient PM2.5 by hybrid graph deep neural network with aggregated neighborhood spatiotemporal information

The observation-based air pollution forecasting method has high computational efficiency over traditional numerical models, but a poor ability in long-term (after 6 h) forecasting due to a lack of detailed representation of atmospheric processes associated with the pollution transport. To address such limitation, here we propose a novel real-time air pollution forecasting model that applies a hybrid graph deep neural network (GNN_LSTM) to dynamically capture the spatiotemporal correlations among neighborhood monitoring sites to better represent the physical mechanism of pollutant transport across the space with the graph structure which is established with features (angle, wind speed, and wind direction) of neighborhood sites to quantify their interactions. Such design substantially improves the model performance in 72-hour PM_2.5 forecasting over the whole Beijing-Tianjin-Hebei region (overall R² increases from 0.6 to 0.79), particularly for polluted episodes (PM_2.5 concentration > 55 µg/m³) with pronounced regional transport to be captured by GNN_LSTM model. The inclusion of the AOD feature further enhances the model performance in predicting PM_2.5 over the sites where the AOD can inform additional aloft PM_2.5 pollution features related to regional transport. The importance of neighborhood site (particularly for those in the upwind flow pathway of the target area) features for long-term PM_2.5 forecast is demonstrated by the increased performance in predicting PM_2.5 in the target city (Beijing) with the inclusion of additional 128 neighborhood sites. Moreover, the newly developed GNN_LSTM model also implies the "source"-receptor relationship, as impacts from distanced sites associated with regional transport grow along with the forecasting time (from 0% to 38% in 72 h) following the wind flow. Such results suggest the great potential of GNN_LSTM in long-term air quality forecasting and air pollution prevention.

Socio-demographic characteristics and inequality in exposure to PM2.5: A case study in the Sichuan basin, China

The Chengyu Metropolitan Area (CYMA), located in the Sichuan Basin, is an unevenly developed region with high PM_2.5 concentrations and a population of approximately 100 million. Although exposure inequality in air pollution has received increasing concern, no related research has been carried out in the CYMA to date. In this work, we used the concentration index to assess inequality of PM_2.5 population-weighted exposure in the CYMA among different subgroups, including age, education, gender, occupation and GDP per capita in the city of residence. Our findings revealed that the non-disadvantaged subgroups (people aged 15-64, people with senior and higher education, people with high-income occupations and residents of cities with high GDP per capita) had a higher PM_2.5 exposure in the CYMA, with the concentration indices of -0.03 (95% CI: 0.064, -0.001), -0.14 (95% CI: 0.221, -0.059), -0.15 (95% CI: 0.238, -0.056) and -0.27 (95% CI: 0.556, 0.012), opposite to previous studies in developed countries such as the United States and France. In addition, exposure differences among cities were much larger than those among populations in the CYMA. These findings may benefit the government in identifying disproportionately exposed subgroups in developing regions, and suggest that related measures should initially be carried out for cities exposed to high PM_2.5 concentrations rather than for populations exposed to high PM_2.5 concentrations.

A Computational Framework for Design and Optimization of Risk-Based Soil and Groundwater Remediation Strategies

Soil and groundwater systems have natural attenuation potential to degrade or detoxify contaminants due to biogeochemical processes. However, such potential is rarely incorporated into active remediation strategies, leading to over-remediation at many remediation sites. Here, we propose a framework for designing and searching optimal remediation strategies that fully consider the combined effects of active remediation strategies and natural attenuation potentials. The framework integrates machine-learning and process-based models for expediting the optimization process with its applicability demonstrated at a field site contaminated with arsenic (As). The process-based model was employed in the framework to simulate the evolution of As concentrations by integrating geochemical and biogeochemical processes in soil and groundwater systems under various scenarios of remedial activities. The simulation results of As concentration evolution, remedial activities, and associated remediation costs were used to train a machine learning model, random forest regression, with a goal to establish a relationship between the remediation inputs, outcomes, and associated cost. The relationship was then used to search for optimal (low cost) remedial strategies that meet remediation constraints. The strategy was successfully applied at the field site, and the framework provides an effective way to search for optimal remediation strategies at other remediation sites.

Study on the spatiotemporal dynamic of ground-level ozone concentrations on multiple scales across China during the blue sky protection campaign

Surface ozone (O₃), one of the harmful air pollutants, generated significantly negative effects on human health and plants. Existing O₃ datasets with coarse spatiotemporal resolution and limited coverage, and the uncertainties of O₃ influential factors seriously restrain related epidemiology and air pollution studies. To tackle above issues, we proposed a novel scheme to estimate daily O₃ concentrations on a fine grid scale (1 km × 1 km) from 2018 to 2020 across China based on machine learning methods using hourly observed ground-level pollutant concentrations data, meteorological data, satellite data, and auxiliary data including digital elevation model (DEM), land use data (LUD), normalized difference vegetation index (NDVI), population (POP), and nighttime light images (NTL), and to identify the difference of influential factors of O₃ on diverse urbanization and topography conditions. Some findings were achieved. The correlation coefficients (R²) between O₃ concentrations and surface net solar radiation (SNSR), boundary layer height (BLH), 2 m temperature (T2M), 10 m v-component (MVW), and NDVI were 0.80, 0.40, 0.35, 0.30, and 0.20, respectively. The random forest (RF) demonstrated the highest validation R² (0.86) and lowest validation RMSE (13.74 μg/m³) in estimating O₃ concentrations, followed by support vector machine (SVM) (R² = 0.75, RMSE = 18.39 μg/m³), backpropagation neural network (BP) (R² = 0.74, RMSE = 19.26 μg/m³), and multiple linear regression (MLR) (R² = 0.52, RMSE = 25.99 μg/m³). Our China High-Resolution O₃ Dataset (CHROD) exhibited an acceptable accuracy at different spatial-temporal scales. Additionally, O₃ concentrations showed decreasing trend and represented obviously spatiotemporal heterogeneity across China from 2018 to 2020. Overall, O₃ was mainly affected by human activities in higher urbanization regions, while O₃ was mainly controlled by meteorological factors, vegetation coverage, and elevation in lower urbanization regions. The scheme of this study is useful and valuable in understanding the mechanism of O₃ formation and improving the quality of the O₃ dataset.

The Canadian Optimized Statistical Smoke Exposure Model (CanOSSEM): A machine learning approach to estimate national daily fine particulate matter (PM2.5) exposure

Exposure to biomass smoke has been associated with a wide range of acute and chronic health outcomes. Over the past decades, the frequency and intensity of wildfires has increased in many areas, resulting in longer smoke episodes with higher concentrations of fine particulate matter (PM_2.5). There are also many communities where seasonal open burning and residential wood heating have short- and long-term impacts on ambient air quality. Understanding the acute and chronic health effects of biomass smoke exposure requires reliable estimates of PM_2.5 concentrations during the wildfire season and throughout the year, particularly in areas without regulatory air quality monitoring stations. We have developed a machine learning approach to estimate PM_2.5 across all populated regions of Canada from 2010 to 2019. The random forest machine learning model uses potential predictor variables integrated from multiple data sources and estimates daily mean (24-hour) PM_2.5 concentrations at a 5 km × 5 km spatial resolution. The training and prediction datasets were generated using observations from National Air Pollution Surveillance (NAPS) network. The Root Mean Squared Error (RMSE) between predicted and observed PM_2.5 concentrations was 2.96 μg/m³ for the entire prediction set, and more than 96 % of the predictions were within 5 μg/m³ of the NAPS PM_2.5 measurements. The model was evaluated using 10-fold, leave one-region-out, and leave-one-year-out cross-validations. Overall, CanOSSEM performed well but performance was sensitive to removal of large wildfire events such as the Fort McMurray interface fire in May 2016 or the extreme 2017 and 2018 wildfire seasons in British Columbia. Exposure estimates from CanOSSEM will be useful for epidemiologic studies on the acute and chronic health effects associated with PM_2.5 exposure, especially for populations affected by biomass smoke where routine air quality measurements are not available.

The influence of socioeconomic and environmental determinants on acute myocardial infarction (AMI) mortality from the spatial epidemiological perspective

Plenty of epidemiological approaches have been explored to detect the effects of environmental and socioeconomic factors on acute myocardial infarction (AMI) mortality. Whereas, identifying the influence of potential affecting factors on AMI mortality based on a spatial epidemiological perspective was strongly desired. Moreover, the interaction effects of two potential factors on the diseases were always neglected previously. Here, the Geodetector and geographically & temporally weighted regression model (GTWR) combined with multi-source spatiotemporal datasets were introduced to quantitatively determine the relationship between AMI mortality and potential influencing factors across Xi'an during 2014-2016. Besides, Moran's I was adopted to diagnose the spatial autocorrelation of AMI mortality. Some findings were achieved. The number of AMI mortality cases increased from 5075 in 2014 to 6774 in 2016. Air pollutants, meteorological factors, economic status, and topography factors exhibited a significant effect on AMI mortality. The AMI mortality demonstrated an obvious spatial autocorrelation feature during 2014-2016. POP and PE represented the most obvious impact on AMI mortality, respectively. Moreover, the interaction of any two factors was larger than that of the single factor on AMI mortality, and the factors with the strongest interaction vary according to lag groups and ages. The effects of factors on AMI mortality were POP (- 628.925) > PE (140.102) > RD (79.145) > O₃ (- 58.438) > E_NH₃ (42.370) for male, and POP (- 751.206) > RD (132.935) > E_NH₃ (58.758) > PE (- 45.434) > O₃ (- 21.256) for female, respectively. This work reminds the local government to continuously control air pollution, strengthen urban planning, and improve the health care of the rural areas for alleviating AMI mortality. Meanwhile, the scheme of the current study supplies a scientific reference for examining the effects of potential impact factors on related diseases using the spatial epidemiological perspective.

Identifying Population Hollowing Out Regions and Their Dynamic Characteristics across Central China

Continuous urbanization and industrialization lead to plenty of rural residents migrating to cities for a living, which seriously accelerated the population hollowing issues. This generated series of social issues, including residential estate idle and numerous vigorous laborers migrating from undeveloped rural areas to wealthy cities and towns. Quantitatively determining the population hollowing characteristic is the priority task of realizing rural revitalization. However, the traditional field investigation methods have obvious deficiencies in describing socio-economic phenomena, especially population hollowing, due to weak efficiency and low accuracy. Here, this paper conceives a novel scheme for representing population hollowing levels and exploring the spatiotemporal dynamic of population hollowing. The nighttime light images were introduced to identify the potential hollowing areas by using the nightlight decreasing trend analysis. In addition, the entropy weight approach was adopted to construct an index for evaluating the population hollowing level based on statistical datasets at the political boundary scale. Moreover, we comprehensively incorporated physical and anthropic factors to simulate the population hollowing level via random forest (RF) at a grid-scale, and the validation was conducted to evaluate the simulation results. Some findings were achieved. The population hollowing phenomenon decreasing gradually was mainly distributed in rural areas, especially in the north of the study area. The RF model demonstrated the best accuracy with relatively higher R2 (Mean = 0.615) compared with the multiple linear regression (MLR) and the geographically weighted regression (GWR). The population hollowing degree of the grid-scale was consistent with the results of the township scale. The population hollowing degree represented an obvious trend that decreased in the north but increased in the south during 2016–2020 and exhibited a significant reduction trend across the entire study area during 2019–2020. The present study supplies a novel perspective for detecting population hollowing and provides scientific support and a first-hand dataset for rural revitalization.

Random Forest Estimation and Trend Analysis of PM2.5 Concentration over the Huaihai Economic Zone, China (2000–2020)

Consisting of ten cities in four Chinese provinces, the Huaihai Economic Zone has suffered serious air pollution over the last two decades, particularly of fine particulate matter (PM2.5). In this study, we used multi-source data, namely MAIAC AOD (at a 1 km spatial resolution), meteorological, topographic, date, and location (latitude and longitude) data, to construct a regression model using random forest to estimate the daily PM2.5 concentration over the Huaihai Economic Zone from 2000 to 2020. It was found that the variable expressing time (date) had the greatest characteristic importance when estimating PM2.5. By averaging the modeled daily PM2.5 concentration, we produced a yearly PM2.5 concentration dataset, at a 1 km resolution, for the study area from 2000 to 2020. On comparing modeled daily PM2.5 with observational data, the coefficient of determination (R2) of the modeling was 0.85, the root means square error (RMSE) was 14.63 μg/m3, and the mean absolute error (MAE) was 10.03 μg/m3. The quality assessment of the synthesized yearly PM2.5 concentration dataset shows that R2 = 0.77, RMSE = 6.92 μg/m3, and MAE = 5.42 μg/m3. Despite different trends from 2000–2010 and from 2010–2020, the trend of PM2.5 concentration over the Huaihai Economic Zone during the 21 years was, overall, decreasing. The area of the significantly decreasing trend was small and mainly concentrated in the lake areas of the Zone. It is concluded that PM2.5 can be well-estimated from the MAIAC AOD dataset, when incorporating spatiotemporal variability using random forest, and that the resultant PM2.5 concentration data provide a basis for environmental monitoring over large geographic areas.

Response of aerosol composition to the clean air actions in Baoji city of Fen-Wei River Basin

The implementation of air pollution control measures could alter the compositions of submicron aerosols. Identifying the changes can evaluate the atmospheric responses of the implemented control measures and provide more scientific basis for the formulation of new measures. The Fen-Wei River Basin is the most air polluted region in China, and thereby is a key area for the reduction of emissions. Only limited studies determine the changes in the chemical compositions of submicron aerosols. In this study, Baoji was selected as a representative city in the Fen-Wei River Basin. The compositions of submicron aerosols were determined between 2014 and 2019. Organic fractions were determined through an online instrument (Quadrupole Aerosol Chemical Speciation Monitor, Q-ACSM) and source recognition was performed by the Multilinear Engine (ME-2). The Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) was also employed to evaluate the contributions of emissions reduction and meteorological conditions to the changes of submicron aerosol compositions. The results indicate that the mass concentrations of submicron aerosols have been substantially decreased after implementation of air pollution control measures. This was mainly attributed to the emission reductions of sulfur dioxide (SO₂) and primary organic aerosol (POA). In addition, the main components that drove the pollution episodes swapped from POA, sulfate, nitrate and less-oxidized organic (LO-OOA) in 2014 to nitrate and more-oxidized OOA (MO-OOA) in 2019. Due to the changes of chemical compositions of both precursors and secondary pollutants, the pollution control measures should be modernized to focus on the emissions of ammonia (NH₃), nitrogen oxides (NO_x) and volatile organic compounds (VOC_s) in this region.

Retrieving soil heavy metals concentrations based on GaoFen-5 hyperspectral satellite image at an opencast coal mine, Inner Mongolia, China

Soil heavy metals pollution has been becoming one of the severely environmental issues globally. Previous studies reported laboratory-measured spectra could be used to infer soil heavy metals concentrations to some extent. However, using field-obtained spectra to estimate soil heavy metals concentrations is still a great challenge due to the low precision and weak efficiency at large scales. The present study collected 110 topsoil samples from an Opencast Coal Mine of Ordos, Inner Mongolia, China. Then, the spectra and soil heavy metals concentrations of samples were measured under laboratory conditions. The direct standardization (DS) algorithm was introduced to calibrate the Gaofen-5 (GF-5) hyperspectral image based on the measured spectra of samples. The spectral reflectance of the GF-5 hyperspectral image was reconstructed using continuous wavelet transform (CWT) at different scales. The characteristic bands of GF-5 for estimating heavy metals concentrations were selected by the Boruta algorithm. Finally, the random forest (RF), the extreme learning machine (ELM), the support vector machine (SVM), and the back-propagation neural network (BPNN) algorithms were used to predict the heavy metals concentrations. Some findings were achieved. First, CWT can effectively eliminate the noise of satellite hyperspectral data. The characteristic bands of Zn (480-677, 827-1029, 1241-1334, 1435-1797, and 1949-2500 nm), Ni (514-630, 835-985, 1258-1325, 1460-1578, and 1949-2319 nm), and Cu (822-831; 1029-1300, 1486-1595, and 1730-2294 nm) can be effectively retrieved via the Boruta algorithm. Second, the estimation accuracy was significantly improved by using the DS algorithm. For zinc (Zn), nickel (Ni), and copper (Cu), the determination coefficients of the validation dataset (R_v²) were 0.77 (RF), 0.62 (RF), and 0.56 (ELM), respectively. Third, the distribution trends of heavy metals were almost consistent with the results of actual ground measurements. This paper revealed that the GF-5 can be one of the reliable satellite hyperspectral imagery for mapping soil heavy metals.

Estimating the Near-Ground PM2.5 Concentration over China Based on the CapsNet Model during 2018–2020

Fine particulate matter (PM2.5) threatens human health and the natural environment. Estimating the near-ground PM2.5 concentrations accurately is of great significance in air quality research. Statistical and deep-learning models are widely used for estimating PM2.5 concentration based on remotely sensed aerosol optical depth (AOD) products. Deep-learning models can effectively express the nonlinear relationship between AOD, parameters, and PM2.5. This study proposed a capsule network model (CapsNet) to address the spatial differences in PM2.5 concentration distribution by introducing a capsule structure and dynamic routing algorithm for the first time, which integrates AOD, surface PM2.5 measurements, and auxiliary variables (e.g., normalized difference vegetation index (NDVI) and meteorological parameters). Moreover, we examined the longitude and latitude of pixels as input parameters to reflect spatial location information, and the results showed that the introduction of longitude (LON) and latitude (LAT) parameters improved the model fitting accuracy. The coefficient of determination (R2) increased by 0.05 ± 0.01, and the root mean square error (RMSE), mean relative error (MRE), and mean absolute error (MAE) decreased by 3.30 ± 1.0 μg/m3, 8 ± 3%, and 1.40 ± 0.2 μg/m3, respectively. To verify the accuracy of our proposed CapsNet, the deep neural network (DNN) model was executed. The results indicated that the R2 values of the validation dataset using CapsNet improved by 4 ± 2%, and RMSE, MRE, and MAE decreased by 1.50 ± 0.4 μg/m3, ~5%, and 0.60 ± 0.2 μg/m3, respectively. Finally, the effects of seasons and spatial region on the fitting accuracy were examined separately from 2018 to 2020. With respect to seasons, the model performed more robustly in the cold season. In terms of spatial region, the R2 values exceeded 0.9 in the central-eastern region, while the accuracy was lower in the western and coastal regions. This study proposed the CapsNet model to estimate PM2.5 concentrations for the first time and achieved good accuracy, which could be used for the estimation of other air contaminants.

Interpolation-Based Fusion of Sentinel-5P, SRTM, and Regulatory-Grade Ground Stations Data for Producing Spatially Continuous Maps of PM2.5 Concentrations Nationwide over Thailand

Atmospheric pollution has recently drawn significant attention due to its proven adverse effects on public health and the environment. This concern has been aggravated specifically in Southeast Asia due to increasing vehicular use, industrial activity, and agricultural burning practices. Consequently, elevated PM2.5 concentrations have become a matter of intervention for national authorities who have addressed the needs of monitoring air pollution by operating ground stations. However, their spatial coverage is limited and the installation and maintenance are costly. Therefore, alternative approaches are necessary at national and regional scales. In the current paper, we investigated interpolation models to fuse PM2.5 measurements from ground stations and satellite data in an attempt to produce spatially continuous maps of PM2.5 nationwide over Thailand. Four approaches are compared, namely the inverse distance weighted (IDW), ordinary kriging (OK), random forest (RF), and random forest combined with OK (RFK) leveraging on the NO2, SO2, CO, HCHO, AI, and O3 products from the Sentinel-5P satellite, regulatory-grade ground PM2.5 measurements, and topographic parameters. The results suggest that RFK is the most robust, especially when the pollution levels are moderate or extreme, achieving an RMSE value of 7.11 μg/m3 and an R2 value of 0.77 during a 10-day long period in February, and an RMSE of 10.77 μg/m3 and R2 and 0.91 during the entire month of March. The proposed approach can be adopted operationally and expanded by leveraging regulatory-grade stations, low-cost sensors, as well as upcoming satellite missions such as the GEMS and the Sentinel-5.

A full-coverage estimation of PM2.5 concentrations using a hybrid XGBoost-WD model and WRF-simulated meteorological fields in the Yangtze River Delta Urban Agglomeration, China

In spite of the state-of-the-art performances of machine learning in the PM_2.5 estimation, the high-value PM_2.5 underestimation and non-random aerosol optical depth (AOD) missing are still huge obstacles. By incorporating wavelet decomposition (WD) into the extreme gradient boosting (XGBoost), a hybrid XGBoost-WD model was established to obtain the full-coverage PM_2.5 estimation at 3-km spatial resolution in the Yangtze River Delta Urban Agglomeration (YRDUA). In this study, 3-km-resolution meteorological fields simulated by WRF along with AOD derived from Moderate Resolution Imaging Spectroradiometer (MODIS) were served as explanatory variables. Model MW and Model NW were developed using XGBoost-WD for the areas with and without AOD respectively to obtain a full-coverage PM_2.5 mapping in the YRDUA. The XGBoost-WD model showed good performances in estimating PM_2.5 with R² of 0.80 in the Model MW and 0.87 in the Model NW. Moreover, the K-value of Model MW increased from 0.77 to 0.79 and that of Model NM increased from 0.81 to 0.86 compared with the model without the step of WD, indicating an improvement on the problem of PM_2.5 underestimation. Due to a better ability of capturing abrupt changes in the PM_2.5 concentrations, the spatial evolution of PM_2.5 during a typical pollution event could be mapped more accurately. Finally, the analysis of variable importance showed that the three most important variables in the estimation of the low-frequency coefficients of PM_2.5 (PM_2.5_A4) were temperature at 2 m (T2), day of year (DOY) and longitude (LON), while that in the high-frequency coefficients of PM_2.5 (PM_2.5_D) were CO, AOD and NO₂. This study not only provided an effective solution to the PM_2.5 underestimation and AOD missing problems in the PM_2.5 estimation, but also proposed a new method to further refine the sophisticated correlations between PM_2.5 and some spatiotemporal variables.

The Direct and Spillover Effect of Multi-Dimensional Urbanization on PM2.5 Concentrations: A Case Study from the Chengdu-Chongqing Urban Agglomeration in China

The Chengdu-Chongqing urban agglomeration (CUA) faces considerable air quality concerns, although the situation has improved in the past 15 years. The driving effects of population, land and economic urbanization on PM_2.5 concentrations in the CUA have largely been overlooked in previous studies. The contributions of natural and socio-economic factors to PM_2.5 concentrations have been ignored and the spillover effects of multi-dimensional urbanization on PM_2.5 concentrations have been underestimated. This study explores the spatial dependence and trend evolution of PM_2.5 concentrations in the CUA at the grid and county level, analyzing the direct and spillover effects of multi-dimensional urbanization on PM_2.5 concentrations. The results show that the mean PM_2.5 concentrations in CUA dropped to 48.05 μg/m³ at an average annual rate of 4.6% from 2000 to 2015; however, in 2015, there were still 91% of areas exposed to pollution risk (>35 μg/m³). The PM_2.5 concentrations in 92.98% of the area have slowly decreased but are rising in some areas, such as Shimian County, Xuyong County and Gulin County. The PM_2.5 concentrations in this region presented a spatial dependence pattern of "cold spots in the east and hot spots in the west". Urbanization was not the only factor contributing to PM_2.5 concentrations. Commercial trade, building development and atmospheric pressure were found to have significant contributions. The spillover effect of multi-dimensional urbanization was found to be generally stronger than the direct effects and the positive impact of land urbanization on PM_2.5 concentrations was stronger than population and economic urbanization. The findings provide support for urban agglomerations such as CUA that are still being cultivated to carry out cross-city joint control strategies of PM_2.5 concentrations, also proving that PM_2.5 pollution control should not only focus on urban socio-economic development strategies but should be an integration of work optimization in various areas such as population agglomeration, land expansion, economic construction, natural adaptation and socio-economic adjustment.

Retrieving zinc concentrations in topsoil with reflectance spectroscopy at Opencast Coal Mine sites

Heavy metals contaminations in mining areas aroused wide concerns globally. Efficient evaluation of its pollution status is a basis for further soil reclamation. Visible and near-infrared reflectance (Vis-NIR) spectroscopy has been diffusely used for retrieving heavy metals concentrations. However, the reliability and feasibility of calibrated models were still doubtful. The present study estimated zinc (Zn) concentrations via the random forest (RF) and partial least squares regression (PLSR) using ground in-situ Zn concentrations as well as soil spectral reflectance at an Opencast Coal Mine of Ordos, China in February 2020. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and the ratio of performance to deviation (RPD) were selected to assess the robustness of the methods in estimating Zn contents. Moreover, the characteristic bands were chosen by Pearson correlation analysis and Boruta Algorithm. Finally, the comparison between RF and PLSR combined with eight spectral reflectance transformation methods was conducted for four concentration groups to determine the optimal model. The results indicated that: (1) Zn contents represented a skewed distribution (coefficient of variation (CV) = 33%); (2) the spectral reflectance tended to decrease with the increase of Zn contents during 580-1850 nm based on Savitzky-Golay smoothing (SG); (3) the continuous wavelet transform (CWT) demonstrated higher effectiveness than other spectral reflectance transformation methods in enhancing spectral responses, the R2 between Zn contents and the soil spectral reflectance achieved the highest (R2 = 0.71) by using CWT; (4) the RF combined with CWT exhibited the best performance than other methods in the current study (R2 = 0.97, RPD = 3.39, RMSE = 1.05 mg kg-1, MAE = 0.79 mg kg-1). The current study supplied a scientific scheme and theoretical support for predicting heavy metals concentrations via the Vis-NIR spectral method in possible contaminated areas such as coal mines and metallic mineral deposit areas.