Satellite remote sensing of atmospheric particulate matter mass concentration: Advances, challenges, and perspectives

Assessing Tunisia's urban air quality using combined lichens and Sentinel-5 satellite integration

In Tunisia, urban air pollution is becoming a bigger problem. This study used a combined strategy of biomonitoring with lichens and satellite mapping with Sentinel-5 satellite data processed in Google Earth Engine (GEE) to assess the air quality over metropolitan Tunis. Lichen diversity was surveyed across the green spaces of the Faculty of Science of Tunisia sites, revealing 15 species with a predominance of pollution-tolerant genera. The Index of Atmospheric Purity (IAP) calculated from the lichen data indicated poor air quality. Spatial patterns of pollutants sulfur dioxide (SO2), ozone (O3), nitrogen dioxide (NO2), carbon monoxide (CO), and aerosol index across Greater Tunis were analyzed from Sentinel-5 datasets on the GEE platform. The higher values of these indices in the research area indicate that it may be impacted by industrial activity and highlight the considerable role that vehicle traffic plays in air pollution. The results of the IAP, IBL, and the combined ground-based biomonitoring and satellite mapping techniques confirm poor air quality and an environment affected by atmospheric pollutants which will enable proactive air quality management strategies to be put in place in Tunisia's rapidly expanding cities.

Health effects of exposure to urban ambient particulate matter: A spatial-statistical study on 3rd-trimester pregnant women

Pregnant women are highly vulnerable to environmental stressors such as ambient particulate matter (PM). Particularly during their 3rd trimester, their bodies undergo significant oxidative stresses. To further consolidate this dialogue into practice, the current study evaluated healthy pregnant women (n = 150 housewives; 18-40 years old; gestation age >36 weeks) from the highly polluted city of Yazd, Iran, from September to November 2021. The aerosol optical depth (AOD) data retrieved from the Moderate Resolution Imaging Spectroradiometer (MODIS) were employed as influencing variables and validated using field-collected PM10 data (r = 0.62, p-value <0.01). The links between blood platelet count, enzymes (SGOT, SGPT, LDH, bilirubin), metabolic products (urea and acid uric) and different combinations of AOD data were assessed using the Generalized Additive Model. The results showed a high temporal variability in AOD (0.94 ± 0.51) but a spatially stable distribution pattern. The mean AOD during the 3rd trimester, followed by that of the three-month peak, were identified as the most significant non-linear predictors, while the mean AOD during the 1st trimester and throughout the entire pregnancy showed no significant associations with any of the biomarkers. Considering the associations found between AOD variables and maternal oxidative stresses, urgent planning is required to improve the urban air quality for sensitive subpopulations.

Estimation of pan-European, daily total, fine-mode and coarse-mode Aerosol Optical Depth at 0.1° resolution to facilitate air quality assessments

Aerosol Optical Depth (AOD) data derived from satellites is crucial for estimating spatially-resolved PM concentrations, but existing AOD data over land remain affected by several limitations (e.g., data gaps, coarser resolution, higher uncertainty or lack of size fraction data), which weakens the AOD-PM relationship. We developed a 0.1° resolution daily AOD data set over Europe over the period 2003-2020, based on two-stage Quantile Machine Learning (QML) frameworks. Our approach first fills gaps in satellite AOD data and then constructs three components' models to obtain reliable full-coverage AOD along with Fine-mode AOD (fAOD) and Coarse-mode AOD (cAOD). These models are based on AERONET (AErosol RObotic NETwork) observations, Gap-filled satellite AOD, climate and atmospheric composition reanalyses. Our QML AOD products exhibit better quality with an out-of-sample R2 equal to 0.68 for AOD, 0.66 for fAOD and 0.65 for cAOD, which is 23-92 %, 11-13 % and 115-132 % higher than the corresponding satellite or reanalysis products, respectively. Over 91.6 %, 81.6 %, and 88.9 % of QML AOD, fAOD and cAOD predictions fall within ±20 % Expected Error (EE) envelopes, respectively. Previous studies reported that a weak satellite AOD-PM correlation across Europe (Pearson correlation coefficient (PCC) around 0.1). Our QML products exhibit higher correlations with ground-level PMs, particularly when broadly matched by size: AOD with PM10, fAOD with PM2.5, cAOD with PM coarse (R = 0.41, 0.45 and 0.26, respectively). Different AOD fractions more effectively distinct PM size fractions, than total AOD. Our QML aerosol dataset and models pioneer full-coverage, daily high-resolution monitoring of fine-mode and coarse-mode aerosols, effectively addressing existing AOD challenges for further PMs exposures' estimations. This dataset opens avenues for more in-depth exploration of the impacts of aerosols on human health, climate, visibility, and biogeochemical processes, offering valuable insights for air quality management and environmental health risk assessment.

Spatiotemporally continuous PM2.5 dataset in the Mekong River Basin from 2015 to 2022 using a stacking model

With the potential to cause millions of deaths, PM2.5 pollution has become a global concern. In Southeast Asia, the Mekong River Basin (MRB) is experiencing heavy PM2.5 pollution and the existing PM2.5 studies in the MRB are limited in terms of accuracy and spatiotemporal coverage. To achieve high-accuracy and long-term PM2.5 monitoring of the MRB, fused aerosol optical depth (AOD) data and multi-source auxiliary data are fed into a stacking model to estimate PM2.5 concentrations. The proposed stacking model takes advantage of convolutional neural network (CNN) and Light Gradient Boosting Machine (LightGBM) models and can well represent the spatiotemporal heterogeneity of the PM2.5-AOD relationship. In the cross-validation (CV), comparison with CNN and LightGBM models shows that the stacking model can better suppress overfitting, with a higher coefficient of determination (R2) of 0.92, a lower root mean square error (RMSE) of 5.58 μg/m3, and a lower mean absolute error (MAE) of 3.44 μg/m3. For the first time, the high-accuracy PM2.5 dataset reveals spatially and temporally continuous PM2.5 pollution and variations in the MRB from 2015 to 2022. Moreover, the spatiotemporal variations of annual and monthly PM2.5 pollution are also investigated at the regional and national scales. The dataset will contribute to the analysis of the causes of PM2.5 pollution and the development of mitigation policies in the MRB.

Estimation of near-surface ozone concentration and analysis of main weather situation in China based on machine learning model and Himawari-8 TOAR data

Ozone (O₃) is an important greenhouse gas in the atmosphere. Stratospheric ozone protects human beings, but high near-surface ozone concentrations threaten environment and human health. Owing to the uneven distribution of ground-monitoring stations and the low time resolution of polar orbiting satellites, it is difficult to accurately evaluate the refinement and synergistic pollution of near-surface ozone in China. Besides, atmospheric circulation patterns also affect ozone concentrations greatly. In this study, a new generation of geostationary satellite is used to estimate the hourly near-surface ozone concentration with a spatial resolution of 0.05°. First, the Pearson correlation coefficient and maximum information coefficient were used to study the correlation between the top of atmospheric radiation (TOAR) of Himawari-8 satellite and O₃ concentration; seven TOAR channels were selected. Second, based on an interpretable deep learning model, the hourly ozone concentration in China from September 2015 to August 2021 was obtained using the TOAR-O₃ model. Finally, the self-organizing map method was used to determine six major summer weather circulation patterns in China. The results showed that (1) the near-surface O₃ concentration can be accurately estimated; the R² (RMSE: μg/m³) values of the daily, monthly, and annual tenfold cross validation results were 0.91 (12.74), 0.97 (5.64), and 0.98 (1.75), respectively. The feature importance of the model showed that the temperature, TOAR, and boundary layer height contributed 38 %, 22 %, and 13 %, respectively. (2) The O₃ concentration showed obvious spatiotemporal difference and gradually increased from 10:00 to 15:00 (Beijing time) every day. In most areas of China, O₃ concentration had increased significantly. (3) The O₃ concentration in northern China was the highest under the circulation pattern of the Meiyu front over the Yangtze River Delta, while in southern China, it was the highest under the circulation pattern of the northeast cold vortex controlling most of China.

High spatiotemporal resolution estimation of AOD from Himawari-8 using an ensemble machine learning gap-filling method

The data incompleteness of aerosol optical depth (AOD) products and their lack of availability in highly urbanized areas limit their great potential of application in air quality research. In this study, we developed an ensemble machine-learning approach that integrated random forest-based Space Interpolation Model (SIM) and deep neural network-based Time Interpolation Model (TIM) to achieve high spatiotemporal resolution dataset of AOD. The spatial interpolation model first filled the spatial gaps in the Level-2 Himawari-8 hourly AOD product in 0.05° (∼5 km) spatial resolution, while the time interpolation model further improved the temporal resolution to 10 min on its basis. A full-coverage AOD dataset of Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD) and Pearl River Delta (PRD) in 2020 was obtained as a practical implementation. The validation against in-situ AOD observations from AERONET and SONET indicated that this new dataset was satisfactory (R = 0.80), and especially in spring and summer. Overall, our ensemble machine-learning model provided an effective scheme for reconstruction of AOD with high spatiotemporal resolution of 0.05° and 10 min, which may further advance the near-real-time monitoring of air-quality in urban areas.

Prediction of Fine Particulate Matter Concentration near the Ground in North China from Multivariable Remote Sensing Data Based on MIV-BP Neural Network

Rapid urbanization and industrialization lead to severe air pollution in China, threatening public health. However, it is challenging to understand the pollutants’ spatial distributions by relying on a network of ground-based monitoring instruments, considering the incomplete dataset. To predict the spatial distribution of fine-mode particulate matter (PM2.5) pollution near the surface, we established models based on the back propagation (BP) neural network for PM2.5 mass concentration in North China using remote sensing products. According to our predictions, PM2.5 mass concentrations are affected by changes in surface reflectance and the dominant particle size for different seasons. The PM2.5 mass concentration predicted by the seasonal model shows a similar spatial pattern (high in the east but low in the west) influenced by the terrain, but shows high value in winter and low in summer. Compared to the ground-based data, our predictions agree with the spatial distribution of PM2.5 mass concentrations, with a mean bias of +17% in the North China Plain in 2017. Furthermore, the correlation coefficients (R) of the four seasons’ instantaneous measurements are always above 0.7, indicating that the seasonal models primarily improve the PM2.5 mass concentration prediction.

Combining Himawari-8 AOD and deep forest model to obtain city-level distribution of PM2.5 in China

PM_2.5 (fine particulate matter with aerodynamics diameter <2.5 μm) is the most important component of air pollutants, and has a significant impact on the atmospheric environment and human health. Using satellite remote sensing aerosol optical depth (AOD) to explore the hourly ground PM_2.5 distribution is very helpful for PM_2.5 pollution control. In this study, Himawari-8 AOD, meteorological factors, geographic information, and a new deep forest model were used to construct an AOD-PM_2.5 estimation model in China. Hourly cross-validation results indicated that estimated PM_2.5 values were consistent with the site observation values, with an R² range of 0.82-0.91 and root mean square error (RMSE) of 8.79-14.72 μg/m³, among which the model performance reached the optimum value between 13:00 and 15:00 Beijing time (R² > 0.9). Analysis of the correlation coefficient between important features and PM_2.5 showed that the model performance was related to AOD and affected by meteorological factors, particularly the boundary layer height. Deep forest can detect diurnal variations in pollutant concentrations, which were higher in the morning, peaked at 10:00-11:00, and then began to decline. High-resolution PM_2.5 concentrations derived from the deep forest model revealed that some cities in China are seriously polluted, such as Xi 'an, Wuhan, and Chengdu. Our model can also capture the direction of PM_2.5, which conforms to the wind field. The results indicated that due to the combined effect of wind and mountains, some areas in China experience PM_2.5 pollution accumulation during spring and winter. We need to be vigilant because these areas with high PM_2.5 concentrations typically occur near cities.

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

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

Superior PM2.5 Estimation by Integrating Aerosol Fine Mode Data from the Himawari-8 Satellite in Deep and Classical Machine Learning Models

Artificial intelligence is widely applied to estimate ground-level fine particulate matter (PM2.5) from satellite data by constructing the relationship between the aerosol optical thickness (AOT) and the surface PM2.5 concentration. However, aerosol size properties, such as the fine mode fraction (FMF), are rarely considered in satellite-based PM2.5 modeling, especially in machine learning models. This study investigated the linear and non-linear relationships between fine mode AOT (fAOT) and PM2.5 over five AERONET stations in China (Beijing, Baotou, Taihu, Xianghe, and Xuzhou) using AERONET fAOT and 5-year (2015–2019) ground-level PM2.5 data. Results showed that the fAOT separated by the FMF (fAOT = AOT × FMF) had significant linear and non-linear relationships with surface PM2.5. Then, the Himawari-8 V3.0 and V2.1 FMF and AOT (FMF&AOT-PM2.5) data were tested as input to a deep learning model and four classical machine learning models. The results showed that FMF&AOT-PM2.5 performed better than AOT (AOT-PM2.5) in modelling PM2.5 estimations. The FMF was then applied in satellite-based PM2.5 retrieval over China during 2020, and FMF&AOT-PM2.5 was found to have a better agreement with ground-level PM2.5 than AOT-PM2.5 on dust and haze days. The better linear correlation between PM2.5 and fAOT on both haze and dust days (dust days: R = 0.82; haze days: R = 0.56) compared to AOT (dust days: R = 0.72; haze days: R = 0.52) partly contributed to the superior accuracy of FMF&AOT-PM2.5. This study demonstrates the importance of including the FMF to improve PM2.5 estimations and emphasizes the need for a more accurate FMF product that enables superior PM2.5 retrieval.