Satellite-Based Estimation of Hourly PM2.5 Concentrations Using a Vertical-Humidity Correction Method from Himawari-AOD in Hebei

Geostationary satellite-derived ground-level particulate matter concentrations using real-time machine learning in Northeast Asia

Rapid economic growth, industrialization, and urbanization have caused frequent air pollution events in East Asia over the last few decades. Recently, aerosol data from geostationary satellite sensors have been used to monitor ground-level particulate matter (PM) concentrations hourly. However, many studies have focused on using historical datasets to develop PM estimation models, often decreasing their predictability for unseen data in new days. To mitigate this problem, this study proposes a novel real-time learning (RTL) approach to estimate PM with aerodynamic diameters of <10 μm (PM₁₀) and <2.5 μm (PM_2.5) using hourly aerosol data from the Geostationary Ocean Color Imager (GOCI) and numerical model outputs for daytime conditions over Northeast Asia. Three schemes with different weighting strategies were evaluated using 10-fold cross-validation (CV). The RTL models, which considered both concentration and time as weighting factors (i.e., Scheme 3) yielded consistent improvement for 10-fold CV performance on both hourly and monthly scales. The real-time calibration results for PM₁₀ and PM_2.5 were R² = 0.97 and 0.96, and relative root mean square error (rRMSE) = 12.1% and 12.0%, respectively, and the 10-fold CV results for PM₁₀ and PM_2.5 were R² = 0.73 and 0.69 and rRMSE = 41.8% and 39.6%, respectively. These results were superior to results from the offline models in previous studies, which were based on historical data on an hourly scale. Moreover, we estimated PM concentrations in the ocean without using land-based variables, and clearly demonstrated the PM transport over time. Because the proposed models are based on the RTL approach, the density of in-situ monitoring sites could be a major uncertainty factor. This study identified that a high error occurred in low-density areas, whereas a low error occurred in high-density areas. The proposed approach can be operated to monitor ground-level PM concentrations in real-time with uncertainty analysis to ensure optimal results.

Estimating Full-Coverage PM2.5 Concentrations Based on Himawari-8 and NAQPMS Data over Sichuan-Chongqing

Fine particulate matter (PM2.5) has attracted extensive attention due to its harmful effects on humans and the environment. The sparse ground-based air monitoring stations limit their application for scientific research, while aerosol optical depth (AOD) by remote sensing satellite technology retrieval can reflect air quality on a large scale and thus compensate for the shortcomings of ground-based measurements. In this study, the elaborate vertical-humidity method was used to estimate PM2.5 with the spatial resolution 1 km and the temporal resolution 1 hour. For vertical correction, the scale height of aerosols (Ha) was introduced based on the relationship between the visibility data and extinction coefficient of meteorological observations to correct the AOD of the Advance Himawari Imager (AHI) onboard the Himawari-8 satellite. The hygroscopic growth factor (f(RH)) was fitted site-by-site and month by month (1–12 months). Meanwhile, the spatial distribution of the fitted coefficients can be obtained by interpolation assuming that the aerosol properties vary smoothly on a regional scale. The inverse distance weighted (IDW) method was performed to construct the hygroscopic correction factor grid for humidity correction so as to estimate the PM2.5 concentrations in Sichuan and Chongqing from 09:00 to 16:00 in 2017–2018. The results indicate that the correlation between “dry” extinction coefficient and PM2.5 is slightly improved compared to the correlation between AOD and PM2.5, with r coefficient values increasing from 0.12–0.45 to 0.32–0.69. The r of hour-by-hour verification is between 0.69 and 0.85, and the accuracy of the afternoon is higher than that of the morning. Due to the missing rate of AOD in the southwest is very high, this study utilized inverse variance weighting (IVW) gap-filling method combine satellite estimation PM2.5 and the nested air-quality prediction modeling system (NAQPMS) simulation data to obtain the full-coverage hourly PM2.5 concentration and analyze a pollution process in the fall and winter.

Himawari-8/AHI Aerosol Optical Depth Detection Based on Machine Learning Algorithm

Due to the advantage of geostationary satellites, Himawari-8/AHI can provide near-real-time air quality monitoring over China with a high temporal resolution. Satellite-based aerosol optical depth (AOD) retrieval over land is a challenge because of the large surface contribution to the top of atmosphere (TOA) signal and the uncertainty of aerosol modes. Here, by combining satellite TOA reflectance, sun-sensor geometries, meteorological factors and vegetation information, we propose a data-driven AOD detection algorithm based on a deep neural network (DNN) model for Himawari-8/AHI. It is trained by sample data of 2018 and 2019 and is applied to derive hourly AODs over China in 2020. By comparison with ground-based AERONET measurements, R2 for DNN-estimated AOD is up to 0.8702, which is much higher than that for the AHI AOD product with R2 = 0.4869. The hourly AOD results indicate that the DNN model has a good potential in improving the performance of AOD retrieval in the early morning and in the late afternoon, and the spatial distribution is reliable for capturing the variation of aerosol pollution on the regional scale. By analyzing different DNN modeling strategies, it is found that seasonal modeling can hardly increase the accuracy of AOD retrieval to a certain extent, and R2 increases from 0.7394 to 0.8168 when meteorological features, especially air pressure, are involved in the model training.

Estimation of Regional Ground-Level PM2.5 Concentrations Directly from Satellite Top-of-Atmosphere Reflectance Using A Hybrid Learning Model

The accurate prediction of PM2.5 concentrations is important for environmental protection. The accuracy of the commonly used prediction methods is not high; so, this paper proposes a PM2.5 concentration prediction method based on a hybrid learning model. The Top-of-Atmosphere Reflectance (TOAR), PM2.5 data decomposed by wavelets, and meteorological data were used as input features to build an integrated prediction model using random forest and LightGBM, which was applied to PM2.5 concentration prediction in the Beijing–Tianjin–Hebei region. The practical application showed that the proposed method using TOAR, incorporating wavelet decomposition with meteorological element data, had an improvement of 0.06 in the R2 of the model accuracy and a reduction of 2.93 and 1.14 in the root mean square error (RMSE) and mean absolute error (MAE), respectively, over the model using Aerosol Optical Depth (AOD). Our model had a prediction accuracy of R2 of 0.91, which was better than the other models. We used this model to estimate and analyze the variation in PM2.5 concentrations in the Beijing–Tianjin–Hebei region, and the results were the same as the actual PM2.5 concentration distribution trend. Obviously, the proposed model has a high prediction accuracy and can avoid the errors caused by the limitations of the AOD inversion method.

Urban Air Quality Assessment by Fusing Spatial and Temporal Data from Multiple Study Sources Using Refined Estimation Methods

In urban environmental management and public health evaluation efforts, there is an urgent need for fine-grained urban air quality monitoring. However, the high price and sparse distribution of air quality monitoring equipment make it difficult to develop effective and comprehensive fine-scale monitoring at the city scale. This has also led to air quality estimation methods based on incomplete monitoring data, which lack the ability to detect urban air quality differences within a neighborhood. To address this problem, this study proposes a refined urban air quality estimation method that fuses multisource spatio-temporal data. Based on the fact that urban air quality is easily affected by social activities, this method integrates meteorological data with urban social activity data to form a comprehensive environmental data set. It uses the spatio-temporal feature extraction model to extract the multi-source spatio-temporal features of the comprehensive environmental data set. Finally, the improved cascade forest algorithm is used to fit the relationship between the multisource spatio-temporal features and the air quality index (AQI) to construct an air quality estimation model, and the model is used to estimate the hourly PM2.5 index in Beijing on a 1 km × 1 km grid. The results show that the estimation model has excellent performance, and its goodness-of-fit (R2) and root mean square error (RMSE) reach 0.961 and 17.47, respectively. This method effectively achieves the assessment of urban air quality differences within a neighborhood and provides a new strategy for preventing information fragmentation and improving the effectiveness of information representation in the data fusion process.

An Estimation Method for PM2.5 Based on Aerosol Optical Depth Obtained from Remote Sensing Image Processing and Meteorological Factors

Understanding the spatiotemporal variations in the mass concentrations of particulate matter ≤2.5 µm (PM2.5) in size is important for controlling environmental pollution. Currently, ground measurement points of PM2.5 in China are relatively discrete, thereby limiting spatial coverage. Aerosol optical depth (AOD) data obtained from satellite remote sensing provide insights into spatiotemporal distributions for regional pollution sources. In this study, data from the Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD (1 km resolution) product from Moderate Resolution Imaging Spectroradiometer (MODIS) and hourly PM2.5 concentration ground measurements from 2015 to 2020 in Dalian, China were used. Although trends in PM2.5 and AOD were consistent over time, there were seasonal differences. Spatial distributions of AOD and PM2.5 were consistent (R2 = 0.922), with higher PM2.5 values in industrial areas. The method of cross-dividing the test set by year was adopted, with AOD and meteorological factors as the input variable and PM2.5 as the output variable. A backpropagation neural network (BPNN) model of joint cross-validation was established; the stability of the model was evaluated. The trend in the predicted values of BPNN was consistent with the monitored values; the estimation result of the BPNN with the introduction of meteorological factors is better; coefficient of determination (R2) and RMSE standard deviation (SD) between the predicted values and the monitored values in the test set were 0.663–0.752 and 0.01–0.05 μg/m3, respectively. The BPNN was simpler and the training time was shorter compared with those of a regression model and support vector regression (SVR). This study demonstrated that BPNN could be effectively applied to the MAIAC AOD data to estimate PM2.5 concentrations.

Associations of ultrafine and fine particles with childhood emergency room visits for respiratory diseases in a megacity

BACKGROUND

Ambient fine particulate matter with aerodynamic diameter less than 2.5 µm (PM_2.5) has been associated with deteriorated respiratory health, but evidence on particles in smaller sizes and childhood respiratory health has been limited.

METHODS

We collected time-series data on daily respiratory emergency room visits (ERVs) among children under 14 years old in Beijing, China, during 2015-2017. Concurrently, size-fractioned number concentrations of particles in size ranges of 5-560 nm (PNC_5-560) and mass concentrations of PM_2.5, black carbon (BC) and nitrogen dioxide (NO₂) were measured from a fixed-location monitoring station in the urban area of Beijing. Confounder-adjusted Poisson regression models were used to estimate excessive risks (ERs) of particle size fractions on childhood respiratory ERVs, and positive matrix factorisation models were applied to apportion the sources of PNC_5-560.

RESULTS

Among the 136 925 cases of all-respiratory ERVs, increased risks were associated with IQR increases in PNC_25-100 (ER=5.4%, 95% CI 2.4% to 8.6%), PNC_100-560 (4.9%, 95% CI 2.5% to 7.3%) and PM_2.5 (1.3%, 95% CI 0.1% to 2.5%) at current and 1 prior days (lag0-1). Major sources of PNC_5-560 were identified, including nucleation (36.5%), gasoline vehicle emissions (27.9%), diesel vehicle emissions (18.9%) and secondary aerosols (10.6%). Emissions from gasoline and diesel vehicles were found of significant associations with all-respiratory ERVs, with increased ERs of 6.0% (95% CI 2.5% to 9.7%) and 4.4% (95% CI 1.7% to 7.1%) at lag0-1 days, respectively. Exposures to other traffic-related pollutants (BC and NO₂) were also associated with increased respiratory ERVs.

CONCLUSION

Our findings suggest that exposures to higher levels of PNC_5-560 from traffic emissions could be attributed to increased childhood respiratory morbidity, which supports traffic emission control priority in urban areas.

Estimate hourly PM2.5 concentrations from Himawari-8 TOA reflectance directly using geo-intelligent long short-term memory network

Fine particulate matter (PM_2.5) has attracted extensive attention because of its baneful influence on human health and the environment. However, the sparse distribution of PM_2.5 measuring stations limits its application to public utility and scientific research, which can be remedied by satellite observations. Therefore, we developed a Geo-intelligent long short-term network (Geoi-LSTM) to estimate hourly ground-level PM_2.5 concentrations in 2017 in Wuhan Urban Agglomeration (WUA). We conducted contrast experiments to verify the effectiveness of our model and explored the optimal modeling strategy. It turned out that Geoi-LSTM with TOA reflectance, meteorological conditions, and NDVI as inputs performs best. The station-based cross-validation R², root mean squared error and mean absolute error are 0.82, 15.44 μg/m³, 10.63 μg/m³, respectively. Based on model results, we revealed spatiotemporal characteristics of PM_2.5 in WUA. Generally speaking, during the day, PM_2.5 concentration remained stable at a relatively high level in the morning and decreased continuously in the afternoon. While during the year, PM_2.5 concentrations were highest in winter, lowest in summer, and in-between in spring and autumn. Combined with meteorological conditions, we further analyzed the whole process of a PM_2.5 pollution event. Finally, we discussed the loss in removing clouds-covered pixels and compared our model with several popular models. Overall, our results can reflect hourly PM_2.5 concentrations seamlessly and accurately with a spatial resolution of 5 km, which benefits PM_2.5 exposure evaluations and policy regulations.

Estimating hourly full-coverage PM2.5 over China based on TOA reflectance data from the Fengyun-4A satellite

It is challenging to retrieve hourly ground-level PM_2.5 on a national scale in China due to the sparse site measurements and the limited coverage of Low Earth Orbit (LEO) satellite observations. The new geostationary meteorological satellite of China, Fengyun-4A (FY-4A), provides a unique opportunity to fill this gap. In this study, the Random Forest (RF) algorithm was applied to retrieve hourly PM_2.5 of China directly from FY-4A Top-of-Atmosphere (TOA) reflectance data. A one-year PM_2.5 retrieval shows a strong agreement to ground-based measurements, with the averaged R² approaching 0.92, while the RMSE was only 10.0 μg/m³. An analysis of the regional differences of the performance and the dependency on satellite Viewing Zenith Angle (VZA) show that sparse measurements, high VZA, and solar zenith angle (SZA) are the primary sources of the uncertainty. The use of the FY-4A improved 17% spatial coverage compared to the Himawari-8-based PM_2.5 retrievals, enabling full-coverage, hourly PM_2.5 monitoring over China, and potentially could improve PM_2.5 predictions from air quality models after data assimilation.

Retrieval and Validation of AOD from Himawari-8 Data over Bohai Rim Region, China

The geostationary satellite Himawari-8, possessing the Advanced Himawari Imager (AHI), which features 16 spectral bands from the visible to infrared range, is suitable for aerosol observations. In this study, a new algorithm is introduced to retrieve aerosol optical depth (AOD) over land at a resolution of 2 km from the AHI level 1 data. Considering the anisotropic effects of complex surface structures over land, Moderate Resolution Imaging Spectroradiometer (MODIS) bidirectional reflectance distribution function (BRDF) model parameters product (MCD19A3) is used to calculate the surface reflectance for Himawari-8’s view angle and band. In addition, daily BRDF model parameters are calculated in areas with dense vegetation, considering the rapid variation of surface reflectance caused by vegetation growth. Moreover, aerosol models are constructed based on long duration Aerosol Robotic Network (AERONET) single scattering albedo (SSA) values to stand for aerosol types in the retrieval algorithm. The new algorithm is applied to AHI images over Bohai Rim region from 2018 and is evaluated using the newest AERONET version 3 AOD measurements and the latest MODIS collection 6.1 AOD products. The AOD retrievals from the new algorithm show good agreement with the AERONET AOD measurements, with a correlation coefficient of 0.93 and root mean square error (RMSE) of 0.12. In addition, the new algorithm increases AOD retrievals and retrieval accuracy compared to the Japan Aerospace Exploration Agency (JAXA) aerosol products. The algorithm shows stable performance during different seasons and times, which makes it possible for use in climate or diurnal aerosol variation studies.

Satellite measurements of aerosol optical depth and carbon monoxide and comparison with ground data

Satellite data of aerosol optical depths (AODs) from the moderate resolution imaging spectroradiometer (MODIS) and carbon monoxide (CO) columns from the measurements of pollution in the troposphere (MOPITT) were collected for the study in Northern Thailand. Comparative analyses were conducted of MODIS (Terra and Aqua) AODs with ground particulate matter with diameter below 10 microns (PM₁₀) concentrations and MOPITT CO surface/total columns with ground CO concentrations for 2014-2017. Temporal variations in both the satellite and ground datasets were in good agreement. High levels of air pollutants were common during March-April. The annual analysis of both satellite and ground datasets revealed the highest levels of air pollutants in 2016 and the lowest levels in 2017. The AODs and PM₁₀ concentrations were at higher levels in the morning than in the afternoon. The comparison between satellite products showed that AODs correlated better with the CO total columns than the CO surface columns. The regression analysis presented better performance of Aqua AODs-PM₁₀ than Terra AODs-PM₁₀ with correlation coefficients (r) of 0.72-0.83 and 0.57-0.79, respectively. Ground CO concentrations correlated better with MOPITT CO surface columns (r = 0.65-0.73) than with CO total columns (r = 0.56-0.72). The r values of satellite and ground datasets were greatest when the analysis was restricted to November-March (dry weather periods with possible low mixing height (MH)). Overall, the results suggested that the relationships between satellite and ground data can be used to develop predictive models for ground PM₁₀ and CO in northern Thailand, particularly during air pollution episodes located where ground monitoring stations are limited.

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.

Hourly PM2.5 Estimation over Central and Eastern China Based on Himawari-8 Data

In this study, an improved geographically and temporally weighted regression (IGTWR) model for the estimation of hourly PM2.5 concentration data was applied over central and eastern China in 2017, based on Himawari-8 Advanced Himawari Imager (AHI) data. A generalized distance based on the longitude, latitude, day, hour, and land use type was constructed. AHI aerosol optical depth, surface relative humidity, and boundary layer height (BLH) data were used as independent variables to retrieve the hourly PM2.5 concentrations at 1:00, 2:00, 3:00, 4:00, 5:00, 6:00, 7:00, and 8:00 UTC (Coordinated Universal Time). The model fitting and cross-validation performance were satisfactory. For the model fitting set, the correlation coefficient of determination (R2) between the measured and predicted PM2.5 concentrations was 0.886, and the root-mean-square error (RMSE) of 437,642 samples was only 12.18 µg/m3. The tenfold cross-validation results of the regression model were also acceptable; the correlation coefficient R2 of the measured and predicted results was 0.784, and the RMSE was 20.104 µg/m3, which is only 8 µg/m3 higher than that of the model fitting set. The spatial and temporal characteristics of the hourly PM2.5 concentration in 2017 were revealed. The model also achieved stable performance under haze and dust conditions.

Optimal Inversion of Conversion Parameters from Satellite AOD to Ground Aerosol Extinction Coefficient Using Automatic Differentiation

Satellite aerosol optical depth (AOD) plays an important role for high spatiotemporal-resolution estimation of fine particulate matter with diameters ≤2.5 μm (PM2.5). However, the MODIS sensors aboard the Terra and Aqua satellites mainly measure column (integrated) AOD using the aerosol (extinction) coefficient integrated over all altitudes in the atmosphere, and column AOD is less related to PM2.5 than low-level or ground-based aerosol (extinction) coefficient (GAC). With recent development of automatic differentiation (AD) that has been widely applied in deep learning, a method using AD to find optimal solution of conversion parameters from column AOD to the simulated GAC is presented. Based on the computational graph, AD has considerably improved the efficiency in applying gradient descent to find the optimal solution for complex problems involving multiple parameters and spatiotemporal factors. In a case study of the Jing-Jin-Ji region of China for the estimation of PM2.5 in 2015 using the Multiangle Implementation of Atmospheric Correction AOD, the optimal solution of the conversion parameters was obtained using AD and the loss function of mean square error. This solution fairly modestly improved the Pearson’s correlation between simulated GAC and PM2.5 up to 0.58 (test R2: 0.33), in comparison with three existing methods. In the downstream validation, the simulated GACs were used to reliably estimate PM2.5, considerably improving test R2 up to 0.90 and achieving consistent match for GAC and PM2.5 in their spatial distribution and seasonal variations. With the availability of the AD tool, the proposed method can be generalized to the inversion of other similar conversion parameters in remote sensing.

Estimating PM2.5 Concentrations Based on MODIS AOD and NAQPMS Data over Beijing⁻Tianjin⁻Hebei

Accurately estimating fine ambient particulate matter (PM2.5) is important to assess air quality and to support epidemiological studies. To analyze the spatiotemporal variation of PM2.5 concentrations, previous studies used different methodologies, such as statistical models or neural networks, to estimate PM2.5. However, there is little research on full-coverage PM2.5 estimation using a combination of ground-measured, satellite-estimated, and atmospheric chemical model data. In this study, the linear mixed effect (LME) model, which used the aerosol optical depth (AOD) from the Moderate Resolution Imaging Spectroradiometer (MODIS), meteorological data, normalized difference vegetation index (NDVI), and elevation data as predictors, was fitted for 2017 over Beijing⁻Tianjin⁻Hebei (BTH). The LME model was used to calibrate the PM2.5 concentration using the nested air-quality prediction modeling system (NAQPMS) simulated with ground measurements. The inverse variance weighting (IVW) method was used to fuse satellite-estimated and model-calibrated PM2.5. The results showed a strong agreement with ground measurements, with an overall coefficient (R²) of 0.78 and a root-mean-square error (RMSE) of 26.44 μg/m³ in cross-validation (CV). The seasonal R² values were 0.75, 0.62, 0.80, and 0.78 in the spring, summer, autumn, and winter, respectively. The fusion results supplement the lack of satellite estimates and can capture more detailed information than the NAQPMS model. Therefore, the results will be helpful for pollution process analyses and health-related studies.

Spatial and Temporal Distribution of Aerosol Optical Depth and Its Relationship with Urbanization in Shandong Province

In the process of rapid urbanization, air environment quality has become a hot issue. Aerosol optical depth (AOD) from Moderate Resolution Imaging Spectroradiometer (MODIS) can be used to monitor air pollution effectively. In this paper, the Spearman coefficient is used to analyze the correlations between AOD and urban development, construction factors, and geographical environment factors in Shandong Province. The correlation between AOD and local climatic conditions in Shandong Province is analyzed by geographic weight regression (GWR). The results show that in the time period from 2007 to 2017, the AOD first rose and then fell, reaching its highest level in 2012, which is basically consistent with the time when the national environmental protection decree was issued. In terms of quarterly and monthly changes, AOD also rose first and then fell, the highest level in summer, with the highest monthly value occurring in June. In term of the spatial distribution, the high-value area is located in the northwestern part of Shandong Province, and the low-value area is located in the eastern coastal area. In terms of social factors, the correlation between pollutant emissions and AOD is much greater the correlations between AOD and population, economy, and construction indicators. In terms of environmental factors, the relationship between digital elevation model (DEM), temperature, precipitation, and AOD is significant, but the regulation of air in coastal areas is even greater. Finally, it was found that there are no obvious differences in AOD among cities with different development levels, which indicates that urban development does not inevitably lead to air pollution. Reasonable development planning and the introduction of targeted environmental protection policies can effectively alleviate pollution-related problems in the process of urbanization.