Estimating national-scale ground-level PM25 concentration in China using geographically weighted regression based on MODIS and MISR AOD

Enhanced PM2.5 estimation across China: An AOD-independent two-stage approach incorporating improved spatiotemporal heterogeneity representations

In China, population growth and aging have partially negated the public health benefits of air pollution control measures, underscoring the ongoing need for precise PM2.5 monitoring and mapping. Despite its prevalence, the satellite-derived Aerosol Optical Depth (AOD) method for estimating PM2.5 concentrations often encounters significant spatial data gaps. Additionally, current research still needs better representation of PM2.5 spatiotemporal heterogeneity. Addressing these challenges, we developed a two-stage model employing the Extreme Gradient Boosting (XGBoost) algorithm. By incorporating improved spatiotemporal factors, we achieved high-precision and full-coverage daily 1-km PM2.5 mappings across China for the year 2020 without utilizing AOD products. Specifically, Model 1 develops improved temporal encodings and a terrain classification factor (DC), while Model 2 constructs an enhanced spatial autocorrelation term (Ps) by integrating observed and estimated values. Notably, Model 2 excelled in 10-fold sample-based cross-validation, achieving a coefficient of determination of 0.948, a mean absolute error of 3.792 μg/m³, a root mean square error of 7.144 μg/m³, and a mean relative error of 14.171%. Feature importance and Shapley Additive exPlanations (SHAP) analyses determined the relative importance of predictors in model training and outcome prediction, while correlation analysis identified strong links between improved temporal encodings, PM2.5 concentrations, and significant meteorological factors. Two-way Partial Dependence Plots (PDPs) further explored the interactions among these factors and their impact on PM2.5 levels. Compared to traditional methods, improved temporal encodings align more closely with seasonal variations and synergize more effectively with meteorological factors. Besides, the structured nature of DC aids in model training, while the improved Ps more effectively captures PM2.5's spatial autocorrelation, outperforming traditional Ps. Overall, this study effectively represents spatiotemporal information, thereby boosting model accuracy and enabling seamless large-scale PM2.5 estimations. It provides deep insights into variables and models, providing significant implications for future air pollution research.

A daily and complete PM2.5 dataset derived from space observations for Vietnam from 2012 to 2020

PM_2.5 pollution is a serious problem in Vietnam and around the world, having bad impacts on human health, animals and environment. Regular monitoring at a large scale is important to assess the status of air pollution, develop solutions and evaluate the effectiveness of policy implementation. However, air quality monitoring stations in Vietnam are limited. In this article, we propose an approach to estimate daily PM_2.5 concentration from 2012 to 2020 over the Vietnamese territory, which is strongly affected by cloudy conditions, using a modern statistical model named Mixed Effect Model (MEM) on a dataset consisting of ground PM_2.5 measurements, integrated satellite Aerosol Optical Depth (AOD), meteorological and land use maps. The result of this approach is the first long-term, full coverage and high quality PM_2.5 dataset of Vietnam. The daily mean PM_2.5 maps have high validation results in comparison with ground PM_2.5 measurement (Pearson r of 0.87, R² of 0.75, RMSE of 11.76 μg/m³, and MRE of 36.57 % on a total of 13,886 data samples). The aggregated monthly and annual average maps from 2012 to 2020 in Vietnam have outstanding quality when compared with another global PM_2.5 product. The PM_2.5 concentration maps has shown spatial distribution and seasonal variations of PM_2.5 concentration in Vietnam in a long period from 2012 to 2020 and has been used in other studies and applications in the environment and public health at the national scale, which has not been possible before because of the lack of monitoring stations and an appropriate PM_2.5 modeling approach.

PM2.5 concentration assessment based on geographical and temporal weighted regression model and MCD19A2 from 2015 to 2020 in Xinjiang, China

PM2.5 is closely linked to both air quality and public health. Many studies have used models combined with remote sensing and auxiliary data to inverse a large range of PM2.5 concentrations. However, the data's spatial resolution is limited. and better results might have been obtained if higher resolution data had been used. Therefore, this paper establishes a geographical and temporal weighted regression model (GTWR) and estimates the PM2.5 concentration in Xinjiang from 2015 to 2020 using 1 km resolution MCD19A2 (MODIS/Terra+Aqua Land Aerosol Optical Thickness Daily L2G Global 1km SIN Grid V006) data and 9 auxiliary variables. The findings indicate that the GTWR model performs better than the simple linear regression (SLR) and geographically weighted regression (GWR) models in terms of accuracy and feasibility in retrieving PM2.5 concentrations in Xinjiang. Simultaneously, by combining the GTWR model with MCD19A2 data, a spatial distribution map of PM2.5 with better spatial resolution can be obtained. Next, the regional distribution of annual PM2.5 concentrations in Xinjiang is consistent with the terrain from 2015 to 2020. The low value area is primarily found in the mountainous area with higher terrain, while the high value area is primarily in the basin with lower terrain. Overall, the southwest is high and the northeast is low. In terms of time change, the six-year PM2.5 shows a single peak distribution with 2016 as the inflection point. Lastly, from 2015 to 2020, the seasonal average PM2.5 concentration in Xinjiang has a significant difference, thereby showing winter (66.15μg/m3)>spring (52.28μg/m3)>autumn (40.51μg/m3)>summer (38.63μg/m3). The research shows that the combination of MCD19A2 data and GTWR model has good applicability in retrieving PM2.5 concentration.

Exploring the relationships between ground-measured particulate matter and satellite-retrieved aerosol parameters in China

In this study, the PM_2.5 and PM₁₀ concentrations from 367 cities in China were integrated with MODIS-retrieved aerosol optical depth (AOD) and Angstrom exponent (AE) data to explore the relationship between ground-measured surface particle concentrations and remote-sensing aerosol parameters. The impact of meteorological and topographical factors and seasonality were also taken into consideration and the partial least squares (PLS) regression model was adopted to evaluate the effects of surface particulate matter (PM) concentration and meteorological factors on the variation of aerosol parameters. PM concentrations and aerosol parameters all presented strong spatial disparity and seasonal patterns in China. After implementation of stringent clean air actions and policies, both the ground-measured and satellite-retrieved aerosol parameters revealed that the concentrations of suspended particles in China's cities declined dramatically from 2015 to 2018. The PM/AOD ratio showed conspicuous south-north and west-east differences. The ratio was strongly correlated to meteorological and topographic factors, and it tended to be higher in arid and less polluted regions. Moreover, the dominant factors affecting seasonal PM/AOD ratios varied among China's five regions. The correlations of daily PM-AOD were always strong in southwest China and in basin terrain (e.g., Sichuan Basin and Tarim Basin). In contrast, the PM-AOD correlation was found to be negative in some cities on the Tibetan Plateau because local relative humidity makes a greater contribution to AOD variation. Since the climate is arid and the ratio of coarse particles (e.g., PM₁₀) is much higher, PM tended to have a significantly negative correlation with AE in northwestern cities. Whereas in many southern cities, PM was positively correlated with AE because of the area's high relative humidity and aerosol hygroscopic properties.

High Spatiotemporal Resolution PM2.5 Concentration Estimation with Machine Learning Algorithm: A Case Study for Wildfire in California

As an aggregate of suspended particulate matter in the air, atmospheric aerosols can affect the regional climate. With the help of satellite remote sensing technology to retrieve AOD (aerosol optical depth) on a global or regional scale, accurate estimation of PM2.5 concentration has become an important task to quantify the spatiotemporal distribution of AOD and PM2.5. However, due to the limitations of satellite platforms, sensors, and inversion algorithms, the spatiotemporal resolution of current major AOD products is still relatively low. Meanwhile, for the impact of cloud, the AOD products often have a serious data gap problem, which also objectively limits the spatiotemporal coverage of predicted PM2.5 concentration. Therefore, how to effectively improve the spatiotemporal resolution and coverage of PM2.5 concentration under the requisite accuracy is still a grand challenge. In this study, the fused high spatial-temporal resolution AOD data in our previous study were used to estimate the ground PM2.5 concentration through machine learning algorithms, the deep belief network (DBN). The PM2.5 data had spatiotemporal autocorrelation in geostatistics and followed the Gaussian kernel distribution. Hence, the autocorrelation model modified by Gaussian kernel function integrated with DBN algorithm, named Geoi-DBN, was used to estimate PM2.5 concentration. The cross-validation results showed that the Geoi-DBN (R2 = 0.86, RMSE = 6.84 µg m−3) performed better than the original DBN (R2 = 0.67, RMSE = 10.46 µg m−3). The final high quality PM2.5 concentration data can be applied for urban air quality monitoring and related PM2.5 exposure risk assessment such as wildfire.

Self-adaptive bandwidth eigenvector spatial filtering model for estimating PM2.5 concentrations in the Yangtze River Delta region of China

PM_2.5 concentrations are commonly estimated using geographically weighted regression (GWR) models, but these models may suffer from multi-collinearity and over-focus on local feature problems. To overcome these shortcomings, a self-adaptive bandwidth eigenvector spatial filtering (SA-ESF) model utilizing the golden section search (GO-ESF) and genetic algorithm (GA-ESF) was proposed. The SA-ESF model was applied to estimate ground PM_2.5 concentrations in the Yangtze River Delta (YRD) region of China both seasonally and annually from December 2015 to November 2016 using remotely sensing data, factory locations, and road networks. The results of the original eigenvector spatial filtering (ESF), GO-ESF, GA-ESF, and GWR models show that the GA-ESF model offers better performance and exhibits a better average adjusted R² which is 26.6%, 15.3%, and 10.8% higher than for the ESF, GO-ESF, and GWR models, respectively. We next calculated stochastic site indicators that can describe characteristics of regional concentration from interpolated concentration maps derived from the GA-ESF and GWR models. The concentration maps and stochastic site indicators point to major differences in the PM_2.5 concentrations in mountainous areas. There are notably high concentrations in those areas using the GWR model, in contrast with the GA-ESF results, indicating that there may be overfitting problems using the GWR model. Overall, the proposed SA-ESF model with the genetic algorithm technique can capture both global and local features and achieve promising results.

WITHDRAWN: Analysis of distribution characteristics of PM2.5 and health risk appraisal in northeast china through the geographically weighted regression model

Ahead of Print article withdrawn by publisher.

Spatial-temporal characteristics of urban air pollution in 337 Chinese cities and their influencing factors

Urban air pollution, especially in the form of haze events, has become a serious threat to socio-economic development and public health in most developing countries. It is of great importance to assess the frequency of urban air pollution occurrence and its influencing factors. The objective of our study is to develop consistent methodologies for constructing an index system and for assessing the influencing factors of the urban air pollution occurrence based on the Driver-Pressure-State-Impact-Response (DPSIR) framework by incorporating spatial analysis, geographical detector, and geographically weighted regression models. The 27 influencing factors were selected for assessing their influences on the urban air pollution occurrence in 337 Chinese cities. The results indicate that the spatial pattern of the urban air pollution in China was mostly consistent with the Chinese population-based Hu Line. Urban air pollution frequently occurred in North China, Central China, Northeast China, and East China, and displayed strong seasonality. The influencing factors of urban air pollution were complex and diverse, varying from season to season. Influencing factor analysis also shows that the explanatory power between any two influencing factors was greater than that of a single influencing factor of the urban air pollution. Furthermore, most influencing factors had both positive and negative effects and local effects on urban air pollution. Finally, we put forward five suggestions on reducing urban air pollution occurrence, which can provide the basis and reference for the government to make policies on urban air pollution control in China.

PM2.5 Estimation and Spatial-Temporal Pattern Analysis Based on the Modified Support Vector Regression Model and the 1 km Resolution MAIAC AOD in Hubei, China

The satellite-retrieved Aerosol Optical Depth (AOD) is widely used to estimate the concentrations and analyze the spatiotemporal pattern of Particulate Matter that is less than or equal to 2.5 microns (PM2.5), also providing a way for the related research of air pollution. Many studies generated PM2.5 concentration networks with resolutions of 3 km or 10 km. However, the relatively coarse resolution of the satellite AOD products make it difficult to determine the fine-scale characteristics of PM2.5 distributions that are important for urban air quality analysis. In addition, the composition and chemical properties of PM2.5 are relatively complex and might be affected by many factors, such as meteorological and land cover type factors. In this paper, an AOD product with a 1 km spatial resolution derived from the Multi-Angle Implementation of Atmospheric Correction (MAIAC) algorithm, the PM2.5 measurements from ground sites and the meteorological data as the auxiliary variable, are integrated into the Modified Support Vector Regression (MSVR) model that proposed in this paper to estimate the PM2.5 concentrations and analyze the spatiotemporal pattern of PM2.5. Considering the relatively small dataset and the somewhat complex relationship between the variables, we propose a Modified Support Vector Regression (MSVR) model that based on SVR to fit and estimate the PM2.5 concentrations in Hubei province of China. In this paper, we obtained Cross Correlation Coefficient (R²) of 0.74 for the regression of independent and dependent variables, and the conventional SVR model obtained R² of 0.60 as comparison. We think our MSVR model obtained relatively good performance in spite of many complex factors that might impact the accuracy. We then utilized the optimal MSVR model to perform the PM2.5 estimating, analyze their spatiotemporal patterns, and try to explain the possible reasons for these patterns. The results showed that the PM2.5 estimations retrieved from 1 km MAIAC AOD could reflect more detailed spatial distribution characteristics of PM2.5 and have higher accuracy than that from 3 km MODIS AOD. Therefore, the proposed MSVR model can be a better method for PM2.5 estimating, especially when the dataset is relatively small.

Estimating PM2.5 with high-resolution 1-km AOD data and an improved machine learning model over Shenzhen, China

Studies on fine particulate matter with an aerodynamic diameter of 2.5 μm or smaller (PM_2.5) are closely related to the atmospheric environment and human activities but are often limited by ground-level in situ observations. Satellite remote sensing techniques have been widely used to estimate the PM_2.5 concentration over large areas where ground-monitoring sites are unavailable. However, satellite-retrieved aerosol optical depth (AOD) products usually feature a coarse resolution, which is insufficient for the estimation of the urban-scale PM_2.5 concentration. We developed a new improved random forest (IRF) model based on machine learning and a newly released AOD product with a high resolution of 1-km, which could more effectively and accurately estimate the PM_2.5 concentration over Shenzhen in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA), China. Daily PM_2.5 concentrations from 2016 to 2018 were estimated from ground-level PM_2.5 and meteorological variable data. The popular linear regression model, geographically and temporally weighted regression (GTWR) model and random forest (RF) model without spatiotemporal information were employed for comparison and validation purposes through the 10-fold cross-validation (CV) approach. The IRF model attained an overall R² value of 0.915 and a root mean square error (RMSE) value of 3.66 μg m^-3. This suggests that the IRF model can estimate the urban PM_2.5 concentration with a high spatial resolution at the daily, seasonal and annual scales, and the improved machine learning method is better than the linear model proposed by previous studies in terms of the estimation accuracy of the PM_2.5 concentration. Generally, the IRF model coupled with AOD data with a 1-km resolution can significantly improve the calculation accuracy of the atmospheric PM_2.5 concentration over coastal urban areas in the future.

An integrated system for rapid assessment of ecological quality based on remote sensing data

Ecological quality assessment (EQA) is important for regional socio-economic development and its sustainability. To assess the status of land ecological quality more precisely, an ecological quality assessment system with 11 indicators of ecological stability, ecosystem service function, and habitat stress was established using the analytic hierarchy process for Guangdong Province, a highly urbanized region of China. Remotely sensed data were mainly used to quantify the 11 indicators and acquire regional EQA graphs at high spatial resolution. In addition, we used the spatial autocorrelation measure Moran's I to capture dynamic signatures of spatial organization of ecological quality in the study area. The results show that the ecological quality of the study area is heterogeneous spatially but relatively consistent in different regions. Significant positive spatial autocorrelation for EQI in Guangdong was revealed by global Moran's I. Potential ecological hot spot or cold spot were detected based on the spatial clustering patterns that were obtained by local Moran's I. Lands with low ecological quality is mainly distributed in economically developed areas such as the Pearl River Delta and coastal cities in eastern and western Guangdong, while those with high ecological quality are mostly situated in northern mountainous areas that have lush vegetation. The low assessment scores for Guangdong, especially for the Pearl River Delta, are highly correlated with large populations and degrees of industrial agglomeration; this is mainly because urbanization and economic development jeopardize the environment. The presented case study can facilitate information provision and targeted strategy making for environmental protection. This study provides a helpful approach to assess and to analyze the ecological status in the future research. In contrast with methods that employ a single metric and limited data, the assessment system proposed in this study expands the potential application of the remotely sensed data and enriches the methodological system for EQAs.

Estimation of spatially continuous daytime particulate matter concentrations under all sky conditions through the synergistic use of satellite-based AOD and numerical models

Satellite-derived aerosol optical depth (AOD) products are one of main predictors to estimate ground-level particulate matter (PM₁₀ and PM_2.5) concentrations. Since AOD products, however, are only provided under high-quality conditions, missing values usually exist in areas such as clouds, cloud shadows, and bright surfaces. In this study, spatially continuous AOD and subsequent PM₁₀ and PM_2.5 concentrations were estimated over East Asia using satellite- and model-based data and auxiliary data in a Random Forest (RF) approach. Data collected from the Geostationary Ocean Color Imager (GOCI; 8 times per day) in 2016 were used to develop AOD and PM models. Three schemes (i.e. G1, A1, and A2) were proposed for AOD modeling according to target AOD data (GOCI AOD and AERONET AOD) and the existence of satellite-derived AOD. The A2 scheme showed the best performance (validation R² of 0.74 and prediction R² of 0.73 when GOCI AOD did not exist) and the resultant AOD was used to estimate spatially continuous PM concentrations. The PM models with location information produced successful estimation results with R² of 0.88 and 0.90, and rRMSE of 26.9 and 27.2% for PM₁₀ and PM_2.5, respectively. The spatial distribution maps of PM well captured the seasonal and spatial characteristics of PM reported in the literature, which implies the proposed approaches can be adopted for an operational estimation of spatially continuous AOD and PMs under all sky conditions.

Estimativa da concentração média diária de material particulado fino na região do Complexo Industrial e Portuário do Pecém, Ceará, Brasil

A exposição ao material particulado fino (MP2,5) está associada a inúmeros desfechos à saúde. Desta forma, monitoramento da concentração ambiental do MP2,5 é importante, especialmente em áreas amplamente industrializadas, pois abrigam potenciais emissores do MP2,5 e de substâncias com potencial de aumentar a toxicidade de partículas já suspensas. O objetivo desta pesquisa é estimar a concentração diária do MP2,5 em três áreas de influência do Complexo Industrial e Portuário do Pecém (CIPP), Ceará, Brasil. Foi aplicado um modelo de regressão não linear para a estimativa do MP2,5, por meio de dados de profundidade óptica monitorados por satélite. As estimativas foram realizadas em três áreas de influência (Ai) do CIPP (São Gonçalo do Amarante - Ai I, Paracuru e Paraipaba - Ai II e Caucaia - Ai III, no período de 2006 a 2017. As médias anuais das concentrações estimadas foram inferiores ao estabelecido pela legislação nacional em todas as Ai (8µg m-3). Em todas as Ai, os meses referentes ao período de seca (setembro a fevereiro) apresentaram as maiores concentrações e uma predominância de ventos leste para oeste. Os meses que compreendem o período de chuva (março a agosto) apresentaram as menores concentrações e ventos menos definidos. As condições meteorológicas podem exercer um papel importante nos processos de remoção, dispersão ou manutenção das concentrações do material particulado na região. Mesmo com baixas concentrações estimadas, é importante avaliar a constituição das partículas finas dessa região, bem como sua possível associação a efeitos adversos à saúde da população local.

Advancing the prediction accuracy of satellite-based PM2.5 concentration mapping: A perspective of data mining through in situ PM2.5 measurements

Ground-measured PM_2.5 concentration data are oftentimes used as a response variable in various satellite-based PM_2.5 mapping practices, yet few studies have attempted to incorporate ground-measured PM_2.5 data collected from nearby stations or previous days as a priori information to improve the accuracy of gridded PM_2.5 mapping. In this study, Gaussian kernel-based interpolators were developed to estimate prior PM_2.5 information at each grid using neighboring PM_2.5 observations in space and time. The estimated prior PM_2.5 information and other factors such as aerosol optical depth (AOD) and meteorological conditions were incorporated into random forest regression models as essential predictor variables for more accurate PM_2.5 mapping. The results of our case study in eastern China indicate that the inclusion of ground-based PM_2.5 neighborhood information can significantly improve PM_2.5 concentration mapping accuracy, yielding an increase of out-of-sample cross validation R² by 0.23 (from 0.63 to 0.86) and a reduction of RMSE by 7.72 (from 19.63 to 11.91) μg/m³. In terms of the estimated relative importance of predictors, the PM_2.5 neighborhood information played a more critical role than AOD in PM_2.5 predictions. Compared with the temporal PM_2.5 neighborhood term, the spatially neighboring PM_2.5 term has an even larger potential to improve the final PM_2.5 prediction accuracy. Additionally, a more robust and straightforward PM_2.5 predictive framework was established by screening and removing the least important predictor stepwise from each modeling trial toward the final optimization. Overall, our results fully confirmed the positive effects of ground-based PM_2.5 information over spatiotemporally neighboring space on the holistic PM_2.5 mapping accuracy.

Spatial characteristics and risk factor identification for land use spatial conflicts in a rapid urbanization region in China

Land use conflict is a complex problem driven by a myriad of risk factors as a result of rapid socioeconomic development and urbanization. Analyzing the spatial characteristics of land use conflict and identifying its risk factors using statistical models will help us to better understand the causes and effects of the land use conflicts for sustainable management of the limited land resources under the pressure of rapid urbanization. In this study, regression models including multiple linear regression (MLR), spatial autoregressive (SAR), and geographically weighted regression (GWR) models were employed to identify risk factors for the land use spatial conflicts in the Urban Agglomeration around Hangzhou Bay (UAHB) of China in the past 25 years. Our results showed that the overall extent and the higher-level land use spatial conflicts were actually on the decline, and their spatial autocorrelation has been weakening in the UAHB. The key risk factors that mainly caused the land use spatial conflicts in the UHAB appeared to be different at the global and local scales. This knowledge should help urban managers and policymakers to be better informed when developing pertinent land use policies at the regional and local levels. This study also underlined the importance of considering spatial autocorrelation and scale effects when identifying the risk factors for land use spatial conflicts. The lessons learned from this particular context can be extended to other areas under rapid urbanization to assess and better manage their land resources for sustainable use. Graphical abstract.

Hourly PM2.5 Estimates from a Geostationary Satellite Based on an Ensemble Learning Algorithm and Their Spatiotemporal Patterns over Central East China

Satellite-derived aerosol optical depths (AODs) have been widely used to estimate surface fine particulate matter (PM2.5) concentrations over areas that do not have PM2.5 monitoring sites. To date, most studies have focused on estimating daily PM2.5 concentrations using polar-orbiting satellite data (e.g., from the Moderate Resolution Imaging Spectroradiometer), which are inadequate for understanding the evolution of PM2.5 distributions. This study estimates hourly PM2.5 concentrations from Himawari AOD and meteorological parameters using an ensemble learning model. We analyzed the spatial agglomeration patterns of the estimated PM2.5 concentrations over central East China. The estimated PM2.5 concentrations agree well with ground-based data with an overall cross-validated coefficient of determination of 0.86 and a root-mean-square error of 17.3 μg m−3. Satellite-estimated PM2.5 concentrations over central East China display a north-to-south decreasing gradient with the highest concentration in winter and the lowest concentration in summer. Diurnally, concentrations are higher in the morning and lower in the afternoon. PM2.5 concentrations exhibit a significant spatial agglomeration effect in central East China. The errors in AOD do not necessarily affect the retrieval accuracy of PM2.5 proportionally, especially if the error is systematic. High-frequency spatiotemporal PM2.5 variations can improve our understanding of the formation and transportation processes of regional pollution episodes.

Satellite-based high-resolution mapping of ground-level PM2.5 concentrations over East China using a spatiotemporal regression kriging model

Statistical modeling using ground-based PM_2.5 observations and satellite-derived aerosol optical depth (AOD) data is a promising means of obtaining spatially and temporally continuous PM_2.5 estimations to assess population exposure to PM_2.5. However, the vast amount of AOD data that is missing due to retrieval incapability above bright reflecting surfaces such as cloud/snow cover and urban areas challenge this application. Furthermore, most previous studies cannot directly account for the spatiotemporal autocorrelations in PM_2.5 distribution, impacting the associated estimation accuracy. In this study, fixed rank smoothing was adopted to fill the data gaps in a semifinished 3 km AOD dataset, which was a combination of the Moderate Resolution Imaging Spectroradiometer (MODIS) 3 km Dark Target AOD data and MODIS 10 km Deep Blue AOD data from the Terra and Aqua satellites. By matching the gap-filled 3 km AOD data, ground-based PM_2.5 observations, and auxiliary variable data, sufficient samples were screened to develop a spatiotemporal regression kriging (STRK) model for PM_2.5 estimation. The STRK model achieved notable performance in a cross-validation experiment, with a R square of 0.87 and root-mean-square error of 16.55 μg/m³ when applied to estimate daily ground-level PM_2.5 concentrations over East China from March 1, 2015 to February 29, 2016. Using the STRK model, daily PM_2.5 concentrations with full spatial coverage at a resolution of 3 km were generated. The PM_2.5 distribution pattern over East China can be identified at a relatively fine spatiotemporal scale. Thus, the STRK model with gap-filled high-resolution AOD data can provide reliable full-coverage PM_2.5 estimations over large areas for long-term exposure assessment in epidemiological studies.

Mapping daily PM2.5 at 500 m resolution over Beijing with improved hazy day performance

The application of satellite-derived aerosol optical depth (AOD) to infer surface PM_2.5 has significantly increased the spatial coverage and resolutions (1-10 km) of ground-level PM_2.5 mapping as required for accurate exposure estimation. The remaining challenge is to further increase the mapping resolution to the sub-km level with improved algorithms to minimize misrepresentation of severe haze as clouds. In this study, we provide the first daily PM_2.5 estimation over Beijing at a 500 m resolution using AOD from the Simplified Aerosol Retrieval Algorithm (SARA) and linear mixed effects model. A novel cloud screen method is developed which significantly improves data availability during hazy days. The cross-validation R² for PM_2.5 estimations is 0.82 with the cloud-screened SARA AOD. Based on the satellite-predicted high-resolution PM_2.5 map, all-day population-weighted PM_2.5 is estimated to be 81.4 μg m^-3 over Beijing (2.3 times higher than China's NAAQS of 35 μg m^-3). Compared to the standard MODIS Dark Target 3 km product which presents a significant percentage of missing data, the 500 m resolution PM_2.5 mapping derived from SARA AOD reveals distinct pollution patterns and population exposure conditions during severe hazy days, thereby providing valuable information for pollution control and epidemiological studies.

National PM2.5 and NO2 exposure models for China based on land use regression, satellite measurements, and universal kriging

Outdoor air pollution is a major killer worldwide and the fourth largest contributor to the burden of disease in China. China is the most populous country in the world and also has the largest number of air pollution deaths per year, yet the spatial resolution of existing national air pollution estimates for China is generally relatively low. We address this knowledge gap by developing and evaluating national empirical models for China incorporating land-use regression (LUR), satellite measurements, and universal kriging (UK). Land use, traffic and meteorological variables were included for model building. We tested the resulting models in several ways, including (1) comparing models developed using forward variable selection vs. partial least squares (PLS) variable reduction, (2) comparing models developed with and without satellite measurements, and with and without UK, and (3) 10-fold cross-validation (CV), Leave-One-Province-Out CV (LOPO-CV), and Leave-One-City-Out CV (LOCO-CV). Satellite data and kriging are complementary in making predictions more accurate: kriging improved the models in well-sampled areas; satellite data substantially improved performance at locations far away from monitors. Variable-selection models performed similarly to PLS models in 10-fold CV, but better in LOPO-CV. Our best models employed forward variable selection and UK, with 10-fold CV R² of 0.89 (for both 2014 and 2015) for PM_2.5 and of 0.73 (year-2014) and 0.78 (year-2015) for NO₂. Population-weighted concentrations during 2014-2015 decreased for PM_2.5 (58.7 μg/m³ to 52.3 μg/m³) and NO₂ (29.6 μg/m³ to 26.8 μg/m³). We produced the first high resolution national LUR models for annual-average concentrations in China. Models were applied on 1 km grid to support future research. In 2015, >80% of the Chinese population lived in areas that exceeded the Chinese national PM_2.5 standard, 35 μg/m³. Results here will be publicly available and may be useful for epidemiology, risk assessment, and environmental justice research.

Interactive effects of changing stratospheric ozone and climate on tropospheric composition and air quality, and the consequences for human and ecosystem health

The composition of the air we breathe is determined by emissions, weather, and photochemical transformations induced by solar UV radiation. Photochemical reactions of many emitted chemical compounds can generate important (secondary) pollutants including ground-level ozone (O₃) and some particulate matter, known to be detrimental to human health and ecosystems. Poor air quality is the major environmental cause of premature deaths globally, and even a small decrease in air quality can translate into a large increase in the number of deaths. In many regions of the globe, changes in emissions of pollutants have caused significant changes in air quality. Short-term variability in the weather as well as long-term climatic trends can affect ground-level pollution through several mechanisms. These include large-scale changes in the transport of O₃ from the stratosphere to the troposphere, winds, clouds, and patterns of precipitation. Long-term trends in UV radiation, particularly related to the depletion and recovery of stratospheric ozone, are also expected to result in changes in air quality as well as the self-cleaning capacity of the global atmosphere. The increased use of substitutes for ozone-depleting substances, in response to the Montreal Protocol, does not currently pose a significant risk to the environment. This includes both the direct emissions of substitutes during use and their atmospheric degradation products (e.g. trifluoroacetic acid, TFA).

Spatiotemporal patterns of PM10 concentrations over China during 2005-2016: A satellite-based estimation using the random forests approach

BACKGROUND

Few studies have estimated historical exposures to PM₁₀ at a national scale in China using satellite-based aerosol optical depth (AOD). Also, long-term trends have not been investigated.

OBJECTIVES

In this study, daily concentrations of PM₁₀ over China during the past 12 years were estimated with the most recent ground monitoring data, AOD, land use information, weather data and a machine learning approach.

METHODS

Daily measurements of PM₁₀ during 2014-2016 were collected from 1479 sites in China. Two types of Moderate Resolution Imaging Spectroradiometer (MODIS) AOD data, land use information, and weather data were downloaded and merged. A random forests model (non-parametric machine learning algorithms) and two traditional regression models were developed and their predictive abilities were compared. The best model was applied to estimate daily concentrations of PM₁₀ across China during 2005-2016 at 0.1⁰ (≈10 km).

RESULTS

Cross-validation showed our random forests model explained 78% of daily variability of PM₁₀ [root mean squared prediction error (RMSE) = 31.5 μg/m³]. When aggregated into monthly and annual averages, the models captured 82% (RMSE = 19.3 μg/m³) and 81% (RMSE = 14.4 μg/m³) of the variability. The random forests model showed much higher predictive ability and lower bias than the other two regression models. Based on the predictions of random forests model, around one-third of China experienced with PM₁₀ pollution exceeding Grade Ⅱ National Ambient Air Quality Standard (>70 μg/m³) in China during the past 12 years. The highest levels of estimated PM₁₀ were present in the Taklamakan Desert of Xinjiang and Beijing-Tianjin metropolitan region, while the lowest were observed in Tibet, Yunnan and Hainan. Overall, the PM₁₀ level in China peaked in 2006 and 2007, and declined since 2008.

CONCLUSIONS

This is the first study to estimate historical PM₁₀ pollution using satellite-based AOD data in China with random forests model. The results can be applied to investigate the long-term health effects of PM₁₀ in China.

A machine learning method to estimate PM2.5 concentrations across China with remote sensing, meteorological and land use information

BACKGROUND

Machine learning algorithms have very high predictive ability. However, no study has used machine learning to estimate historical concentrations of PM_2.5 (particulate matter with aerodynamic diameter ≤ 2.5 μm) at daily time scale in China at a national level.

OBJECTIVES

To estimate daily concentrations of PM_2.5 across China during 2005-2016.

METHODS

Daily ground-level PM_2.5 data were obtained from 1479 stations across China during 2014-2016. Data on aerosol optical depth (AOD), meteorological conditions and other predictors were downloaded. A random forests model (non-parametric machine learning algorithms) and two traditional regression models were developed to estimate ground-level PM_2.5 concentrations. The best-fit model was then utilized to estimate the daily concentrations of PM_2.5 across China with a resolution of 0.1° (≈10 km) during 2005-2016.

RESULTS

The daily random forests model showed much higher predictive accuracy than the other two traditional regression models, explaining the majority of spatial variability in daily PM_2.5 [10-fold cross-validation (CV) R² = 83%, root mean squared prediction error (RMSE) = 28.1 μg/m³]. At the monthly and annual time-scale, the explained variability of average PM_2.5 increased up to 86% (RMSE = 10.7 μg/m³ and 6.9 μg/m³, respectively).

CONCLUSIONS

Taking advantage of a novel application of modeling framework and the most recent ground-level PM_2.5 observations, the machine learning method showed higher predictive ability than previous studies.

CAPSULE

Random forests approach can be used to estimate historical exposure to PM_2.5 in China with high accuracy.

Eigenvector Spatial Filtering Regression Modeling of Ground PM2.5 Concentrations Using Remotely Sensed Data

This paper proposes a regression model using the Eigenvector Spatial Filtering (ESF) method to estimate ground PM_2.5 concentrations. Covariates are derived from remotely sensed data including aerosol optical depth, normal differential vegetation index, surface temperature, air pressure, relative humidity, height of planetary boundary layer and digital elevation model. In addition, cultural variables such as factory densities and road densities are also used in the model. With the Yangtze River Delta region as the study area, we constructed ESF-based Regression (ESFR) models at different time scales, using data for the period between December 2015 and November 2016. We found that the ESFR models effectively filtered spatial autocorrelation in the OLS residuals and resulted in increases in the goodness-of-fit metrics as well as reductions in residual standard errors and cross-validation errors, compared to the classic OLS models. The annual ESFR model explained 70% of the variability in PM_2.5 concentrations, 16.7% more than the non-spatial OLS model. With the ESFR models, we performed detail analyses on the spatial and temporal distributions of PM_2.5 concentrations in the study area. The model predictions are lower than ground observations but match the general trend. The experiment shows that ESFR provides a promising approach to PM_2.5 analysis and prediction.

Satellite-based high-resolution PM2.5 estimation over the Beijing-Tianjin-Hebei region of China using an improved geographically and temporally weighted regression model

Ground fine particulate matter (PM2.5) concentrations at high spatial resolution are substantially required for determining the population exposure to PM2.5 over densely populated urban areas. However, most studies for China have generated PM2.5 estimations at a coarse resolution (≥10 km) due to the limitation of satellite aerosol optical depth (AOD) product in spatial resolution. In this study, the 3 km AOD data fused using the Moderate Resolution Imaging Spectroradiometer (MODIS) Collection 6 AOD products were employed to estimate the ground PM2.5 concentrations over the Beijing-Tianjin-Hebei (BTH) region of China from January 2013 to December 2015. An improved geographically and temporally weighted regression (iGTWR) model incorporating seasonal characteristics within the data was developed, which achieved comparable performance to the standard GTWR model for the days with paired PM_2.5- AOD samples (Cross-validation (CV) R² = 0.82) and showed better predictive power for the days without PM_2.5- AOD pairs (the R² increased from 0.24 to 0.46 in CV). Both iGTWR and GTWR (CV R² = 0.84) significantly outperformed the daily geographically weighted regression model (CV R² = 0.66). Also, the fused 3 km AODs improved data availability and presented more spatial gradients, thereby enhancing model performance compared with the MODIS original 3/10 km AOD product. As a result, ground PM2.5 concentrations at higher resolution were well represented, allowing, e.g., short-term pollution events and long-term PM2.5 trend to be identified, which, in turn, indicated that concerns about air pollution in the BTH region are justified despite its decreasing trend from 2013 to 2015.

Estimating spatiotemporal distribution of PM1 concentrations in China with satellite remote sensing, meteorology, and land use information

BACKGROUND

PM₁ might be more hazardous than PM_2.5 (particulate matter with an aerodynamic diameter ≤ 1 μm and ≤2.5 μm, respectively). However, studies on PM₁ concentrations and its health effects are limited due to a lack of PM₁ monitoring data.

OBJECTIVES

To estimate spatial and temporal variations of PM₁ concentrations in China during 2005-2014 using satellite remote sensing, meteorology, and land use information.

METHODS

Two types of Moderate Resolution Imaging Spectroradiometer (MODIS) Collection 6 aerosol optical depth (AOD) data, Dark Target (DT) and Deep Blue (DB), were combined. Generalised additive model (GAM) was developed to link ground-monitored PM₁ data with AOD data and other spatial and temporal predictors (e.g., urban cover, forest cover and calendar month). A 10-fold cross-validation was performed to assess the predictive ability.

RESULTS

The results of 10-fold cross-validation showed R² and Root Mean Squared Error (RMSE) for monthly prediction were 71% and 13.0 μg/m³, respectively. For seasonal prediction, the R² and RMSE were 77% and 11.4 μg/m³, respectively. The predicted annual mean concentration of PM₁ across China was 26.9 μg/m³. The PM₁ level was highest in winter while lowest in summer. Generally, the PM₁ levels in entire China did not substantially change during the past decade. Regarding local heavy polluted regions, PM₁ levels increased substantially in the South-Western Hebei and Beijing-Tianjin region.

CONCLUSIONS

GAM with satellite-retrieved AOD, meteorology, and land use information has high predictive ability to estimate ground-level PM₁. Ambient PM₁ reached high levels in China during the past decade. The estimated results can be applied to evaluate the health effects of PM₁.

Indoor PM2.5 exposure affects skin aging manifestation in a Chinese population

Traffic-related air pollution is known to be associated with skin aging manifestations. We previously found that the use of fossil fuels was associated with skin aging, but no direct link between indoor air pollutants and skin aging manifestations has ever been shown. Here we directly measured the indoor PM_2.5 exposure in 30 households in Taizhou, China. Based on the directly measured PM_2.5 exposure and questionnaire data of indoor pollution sources, we built a regression model to predict the PM_2.5 exposure in larger datasets including an initial examination group (N = 874) and a second examination group (N = 1003). We then estimated the association between the PM_2.5 exposure and skin aging manifestations by linear regression. In the initial examination group, we showed that the indoor PM_2.5 exposure levels were positively associated with skin aging manifestation, including score of pigment spots on forehead (12.5% more spots per increase of IQR, P-value 0.0371), and wrinkle on upper lip (7.7% more wrinkle on upper lip per increase of IQR, P-value 0.0218). The results were replicated in the second examination group as well as in the pooled dataset. Our study provided evidence that the indoor PM_2.5 exposure is associated with skin aging manifestation in a Chinese population.

Improving satellite-based PM2.5 estimates in China using Gaussian processes modeling in a Bayesian hierarchical setting

Using satellite-based aerosol optical depth (AOD) measurements and statistical models to estimate ground-level PM_2.5 is a promising way to fill the areas that are not covered by ground PM_2.5 monitors. The statistical models used in previous studies are primarily Linear Mixed Effects (LME) and Geographically Weighted Regression (GWR) models. In this study, we developed a new regression model between PM_2.5 and AOD using Gaussian processes in a Bayesian hierarchical setting. Gaussian processes model the stochastic nature of the spatial random effects, where the mean surface and the covariance function is specified. The spatial stochastic process is incorporated under the Bayesian hierarchical framework to explain the variation of PM_2.5 concentrations together with other factors, such as AOD, spatial and non-spatial random effects. We evaluate the results of our model and compare them with those of other, conventional statistical models (GWR and LME) by within-sample model fitting and out-of-sample validation (cross validation, CV). The results show that our model possesses a CV result (R² = 0.81) that reflects higher accuracy than that of GWR and LME (0.74 and 0.48, respectively). Our results indicate that Gaussian process models have the potential to improve the accuracy of satellite-based PM_2.5 estimates.

Spatial and temporal estimates of population exposure to wildfire smoke during the Washington state 2012 wildfire season using blended model, satellite, and in situ data

In the western U.S., smoke from wild and prescribed fires can severely degrade air quality. Due to changes in climate and land management, wildfires have increased in frequency and severity, and this trend is expected to continue. Consequently, wildfires are expected to become an increasingly important source of air pollutants in the western U.S. Hence, there is a need to develop a quantitative understanding of wildfire-smoke-specific health effects. A necessary step in this process is to determine who was exposed to wildfire smoke, the concentration of the smoke during exposure, and the duration of the exposure. Three different tools have been used in past studies to assess exposure to wildfire smoke: in situ measurements, satellite-based observations, and chemical-transport model (CTM) simulations. Each of these exposure-estimation tools has associated strengths and weakness. We investigate the utility of blending these tools together to produce estimates of PM2.5 exposure from wildfire smoke during the Washington 2012 fire season. For blending, we use a ridge-regression model and a geographically weighted ridge-regression model. We evaluate the performance of the three individual exposure-estimate techniques and the two blended techniques by using leave-one-out cross validation. We find that predictions based on in situ monitors are more accurate for this particular fire season than the CTM simulations and satellite-based observations because of the large number of monitors present; therefore, blending provides only marginal improvements above the in situ observations. However, we show that in hypothetical cases with fewer surface monitors, the two blending techniques can produce substantial improvement over any of the individual tools.