Generating daily high-resolution and full-coverage XCO2 across China from 2015 to 2020 based on OCO-2 and CAMS data.

China has set a goal to achieve carbon neutrality by 2060, and satellite remote sensing allows for acquiring large-range and high-resolution carbon dioxide (CO2) data, which can aid in achieving this goal. However, satellite-derived column-averaged dry-air mole fraction of CO2 (XCO2) products often suffer from substantial spatial gaps due to the impacts of narrow swath and clouds. Here, this paper generates daily full-coverage XCO2 data at a high spatial resolution of 0.1° over China during 2015-2020, by fusing satellite observations and reanalysis data in a deep neural network (DNN) framework. Specifically, DNN constructs the relationships between Orbiting Carbon Observatory-2 satellite XCO2 retrievals, Copernicus Atmosphere Monitoring Service (CAMS) XCO2 reanalysis data, and environmental factors. Then, daily full-coverage XCO2 data can be generated based on CAMS XCO2 and environmental factors. Results show that a satisfactory performance is reported in multiform validations, with RMSE and R2 of 0.99 ppm and 0.963 in terms of the sample-based cross-validation, respectively. The independent in-situ validation also indicates high consistency (R2 = 0.866 and RMSE = 1.71 ppm) between XCO2 estimates and ground measurements. Based on the generated dataset, spatial and seasonal distributions of XCO2 across China are investigated, and a growth rate of 2.71 ppm/yr is found from 2015 to 2020. This paper generates long time series of full-coverage XCO2 data, which helps promote our understanding of carbon cycling. The dataset is available from https://doi.org/10.5281/zenodo.7793917.

Global estimates of gap-free and fine-scale CO2 concentrations during 2014-2020 from satellite and reanalysis data.

Carbon dioxide (CO2) is a crucial greenhouse gas with substantial effects on climate change. Satellite-based remote sensing is a commonly used approach to detect CO2 with high precision but often suffers from extensive spatial gaps. Thus, the limited availability of data makes global carbon stocktaking challenging. In this paper, a global gap-free column-averaged dry-air mole fraction of CO2 (XCO2) dataset with a high spatial resolution of 0.1° from 2014 to 2020 is generated by the deep learning-based multisource data fusion, including satellite and reanalyzed XCO2 products, satellite vegetation index data, and meteorological data. Results indicate a high accuracy for 10-fold cross-validation (R2 = 0.959 and RMSE = 1.068 ppm) and ground-based validation (R2 = 0.964 and RMSE = 1.010 ppm). Our dataset has the advantages of high accuracy and fine spatial resolution compared with the XCO2 reanalysis data as well as that generated from other studies. Based on the dataset, our analysis reveals interesting findings regarding the spatiotemporal pattern of CO2 over the globe and the national-level growth rates of CO2. This gap-free and fine-scale dataset has the potential to provide support for understanding the global carbon cycle and making carbon reduction policy, and it can be freely accessed at https://doi.org/10.5281/zenodo.7721945.

A new perspective to satellite-based retrieval of ground-level air pollution: Simultaneous estimation of multiple pollutants based on physics-informed multi-task learning.

Remote sensing of air pollution is essential for air quality management and health risk assessment. Many machine-learning-based retrieval models have been established for estimating various kinds of air pollutants. These methods mainly aimed to estimate a single pollutant (single-pollutant approach). However, different air pollutants interact with each other and are highly correlated. Building a unified model and conducting a joint retrieval of multiple pollutant can make a better use of these connections and improve the model efficiency. This study proposed a physics-informed multi-task deep neural network (phyMTDNN) for the joint retrieval of six main air pollutants, i.e., PM2.5, PM10, SO2, NO2, CO, and O3. The relationships among these pollutants were used to design the physics-informed network structure and loss function. Top-of-atmosphere reflectance which can generate retrieval results at ultrahigh resolution was used as model input. Experiments for mainland China in 2019 showed that the proposed model successfully achieved simultaneous estimation of six air pollutants, with the cross-validated R2 for the six pollutants varying from 0.72 to 0.90. The contrast experiments proved that physics-informed network structure contributed to the most of the model performance improvement. Compared to the single-pollutant approach, phyMTDNN ameliorated the model accuracy on traces gases retrieval. Furthermore, the modeling efficiency was largely improved in that a lot of repetitive work was avoided and modeling method was optimized. The proposed new multiple-pollutant retrieval frame can be applied to various fields for multi-variate retrieval or estimation.

Ultrahigh-resolution PM2.5 estimation from top-of-atmosphere reflectance with machine learning: Theories, methods, and applications.

Intra-urban pollution monitoring requires fine particulate (PM2.5) concentration mapping at ultrahigh-resolution (dozens to hundreds of meters). However, current PM2.5 concentration estimation, which is mainly based on aerosol optical depth (AOD) and meteorological data, usually had a low spatial resolution (kilometers) and severe spatial missing problem, cannot be applied to intra-urban pollution monitoring. To solve these problems, top-of-atmosphere reflectance (TOAR), which contains both the information about land and atmosphere and has high resolution and large spatial coverage, may be efficiently used for PM2.5 estimation. This study aims to systematically evaluate the feasibility of retrieving ultrahigh-resolution PM2.5 concentration at a large scale (national level) from TOAR. Firstly, we make a detailed discussion about several important but unsolved theoretic problems on TOAR-based PM2.5 retrieval, including the band selection, scale effect, cloud impact, and mapping quality evaluation. Secondly, four types and eight retrieval models are compared in terms of quantitative accuracy, mapping quality, model generalization, and model efficiency, with the pros and cons of each type summarized. Deep neural network (DNN) model shows the highest retrieval accuracy, and linear models were the best in efficiency and generalization. As a compromise, ensemble learning shows the best overall performance. Thirdly, using the highly accurate DNN model (cross-validated R2 equals 0.93) and through combining Landsat 8 and Sentinel 2 images, a 90 m and ∼4-day resolution PM2.5 product was generated. The retrieved maps were used for analyzing the fine-scale interannual pollution change inner the city and the pollution variations during novel coronavirus disease 2019 (COVID-19). Results of this study proves that ultrahigh resolution can bring new findings of intra-urban pollution change, which cannot be observed at previous coarse resolution. Lastly, some suggestions for future ultrahigh-resolution PM2.5 mapping research were given.

Full-coverage spatiotemporal mapping of ambient PM2.5 and PM10 over China from Sentinel-5P and assimilated datasets: Considering the precursors and chemical compositions.

Ambient concentrations of particulate matters (PM2.5 and PM10) are significant indicators for monitoring the air quality relevant to living conditions. At present, most remote sensing based approaches for the estimation of PM2.5 and PM10 employed Aerosol Optical Depth (AOD) products as the main variate. Nevertheless, the coverage of missing data is generally large in AOD products, which can cause deviations in practical applications of estimated PM2.5 and PM10 (e.g., air quality monitoring and exposure evaluation). To efficiently address this issue, our study explores a novel approach using the datasets of the precursors & chemical compositions for PM2.5 and PM10 instead of AOD products. Specifically, the daily full-coverage ambient concentrations of PM2.5 and PM10 are estimated at 5-km (0.05°) spatial girds across China based on Sentinel-5P and assimilated datasets (GEOS-FP). The estimation models are acquired via an advanced ensemble learning method named Light Gradient Boosting Machine in this paper. For comparison, the Deep Blue AOD product from VIIRS is adopted in a similar framework as a baseline (AOD-based). Validation results show that the ambient concentrations are well estimated through the proposed approach, with the space-based Cross-Validation R2s and RMSEs of 0.88 (0.83) and 11.549 (22.9) µg/m3 for PM2.5 (PM10), respectively. Meanwhile, the proposed approach achieves better performance than the AOD-based in different cases (e.g., overall and seasonal). Compared to the related previous works over China, the estimation accuracy of our method is also satisfactory. Regarding the mapping, the estimated results through the proposed approach display consecutive spatial distribution and can exactly express the seasonal variations of PM2.5 and PM10. The proposed approach could efficiently present daily full-coverage results at 5-km spatial grids. It has a large potential to be extended for providing global accurate ambient concentrations of PM2.5 and PM10 at multiple temporal scales (e.g., daily and annual).

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

Fine particulate matter (PM2.5) has attracted extensive attention because of its baneful influence on human health and the environment. However, the sparse distribution of PM2.5 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 PM2.5 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 PM2.5 in WUA. Generally speaking, during the day, PM2.5 concentration remained stable at a relatively high level in the morning and decreased continuously in the afternoon. While during the year, PM2.5 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 PM2.5 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 PM2.5 concentrations seamlessly and accurately with a spatial resolution of 5 km, which benefits PM2.5 exposure evaluations and policy regulations.

The Effects of Fireworks Discharge on Atmospheric PM2.5 Concentration in the Chinese Lunar New Year.

Discharging fireworks during the Chinese Lunar New Year celebrations is a deep-rooted custom in China. In this paper, we analyze the effect of this cultural activity on PM2.5 concentration using both ground observations and satellite data. By combining remote sensing data, the problem of uneven spatial distribution of ground monitoring has been compensated, and the research time span has been expanded. The results show that the extensive firework displays on New Year's Eve lead to a remarkable increase in nationwide PM2.5 concentration, which were 159~223% of the average level, indicating the instantaneous effect far exceeds that of any other factor over the whole year. However, the averaged PM2.5 concentrations of the celebration period were 0.99~16.32 µg/m3 lower compared to the average values of the corresponding pre-celebration period and post-celebration period, indicating the sustained effect is not very significant. The implementation of firework prohibition policies can greatly reduce the instantaneous PM2.5 increase, but no obvious air quality improvement is observed over the entire celebration period. Combining these findings and the cultural significance of this activity, we recommend that this custom is actively maintained, using new technologies and scientific governance programs to minimize the negative effects.

Investigation of the spatially varying relationships of PM2.5 with meteorology, topography, and emissions over China in 2015 by using modified geographically weighted regression.

PM2.5 pollution is caused by multiple factors and determining how these factors affect PM2.5 pollution is important for haze control. In this study, we modified the geographically weighted regression (GWR) model and investigated the relationships between PM2.5 and its influencing factors. Experiments covering 368 cities and 9 urban agglomerations were conducted in China in 2015 and more than 20 factors were considered. The modified GWR coefficients (MGCs) were calculated for six variables, including two emission factors (SO2 and NO2 concentrations), two meteorological factors (relative humidity and lifted index), and two topographical factors (woodland percentage and elevation). Then the spatial distribution of MGCs was analyzed at city, cluster, and region scales. Results showed that the relationships between PM2.5 and the different factors varied with location. SO2 emission positively affected PM2.5, and the impact was the strongest in the Beijing-Tianjin-Hebei (BTH) region. The impact of NO2 was generally smaller than that of SO2 and could be important in coastal areas. The impact of meteorological factors on PM2.5 was complicated in terms of spatial variations, with relative humidity and lifted index exerting a strong positive impact on PM2.5 in Pearl River Delta and Central China, respectively. Woodland percentage mainly influenced PM2.5 in regions of or near deserts, and elevation was important in BTH and Sichuan. The findings of this study can improve our understanding of haze formation and provide useful information for policy-making.

Temporal and Spatial Features of the Correlation between PM2.5 and O3 Concentrations in China.

In recent years, particulate matter of 2.5 µm or less (PM2.5) pollution in China has decreased but, at the same time, ozone (O3) pollution has become increasingly serious. Due to the different research areas and research periods, the existing analyses of the correlation between PM2.5 and O3 have reached different conclusions. In order to clarify the relationship between PM2.5 and O3, this study selected mainland China as the research area, based on the PM2.5 and O3 concentration data of 1458 air quality monitoring stations, and analyzed the correlation between PM2.5 and O3 for different time scales and geographic divisions. Moreover, by combining the characteristics of the pollutants, topography, and climatic features of the study area, we attempted to discuss the causes of the spatial and temporal differences of R-PO (the correlation between PM2.5 and O3). The study found that: (1) R-PO tends to show a positive correlation in summer and a negative correlation in winter, (2) the correlation coefficient of PM2.5 and O3 is lower in the morning and higher in the afternoon, and (3) R-PO also shows significant spatial differences, including north-south differences and coastland-inland differences.

Integration of Remote Sensing and Social Sensing Data in a Deep Learning Framework for Hourly Urban PM2.5 Mapping.

Fine spatiotemporal mapping of PM2.5 concentration in urban areas is of great significance in epidemiologic research. However, both the diversity and the complex nonlinear relationships of PM2.5 influencing factors pose challenges for accurate mapping. To address these issues, we innovatively combined social sensing data with remote sensing data and other auxiliary variables, which can bring both natural and social factors into the modeling; meanwhile, we used a deep learning method to learn the nonlinear relationships. The geospatial analysis methods were applied to realize effective feature extraction of the social sensing data and a grid matching process was carried out to integrate the spatiotemporal multi-source heterogeneous data. Based on this research strategy, we finally generated hourly PM2.5 concentration data at a spatial resolution of 0.01°. This method was successfully applied to the central urban area of Wuhan in China, which the optimal result of the 10-fold cross-validation R2 was 0.832. Our work indicated that the real-time check-in and traffic index variables can improve both quantitative and mapping results. The mapping results could be potentially applied for urban environmental monitoring, pollution exposure assessment, and health risk research.

The influence of urban planning factors on PM2.5 pollution exposure and implications: A case study in China based on remote sensing, LBS, and GIS data.

In recent years, haze pollution has become a serious environmental problem affecting cities in China. Reducing PM2.5 concentrations through urban planning is a promising method that has been a focus of recent multidisciplinary research. Most existing studies only analyze the relationship between urban planning factors and PM2.5 concentration, and it is difficult to accurately reflect residents' actual air pollution exposure without considering their space-time behaviors. This study uses satellite remote sensing and location service data to measure PM2.5 pollution exposure in Wuhan metropolitan area and explores the effects of urban spatial structure, land use, spatial form, transportation, and green space on pollution exposure. The results show that spatial structure, building density, road density, and green space coverage have a significant impact on PM2.5 pollution exposure. In addition, this study proposes corresponding implications for urban planning to improve public respiratory health.

The relationships between PM2.5 and aerosol optical depth (AOD) in mainland China: About and behind the spatio-temporal variations.

Satellite aerosol products have been widely used to retrieve ground PM2.5 concentration because of their wide coverage and continuous spatial distribution. While more and more studies have focused on the retrieval algorithms, the foundation for the retrieval-relationship between PM2.5 and satellite aerosol optical depth (AOD) has not been fully investigated. In this study, the relationships between PM2.5 and AOD were investigated in 368 cities in mainland China from February 2013 to December 2017, at different temporal and regional scales. Pearson correlation coefficients and the PM2.5/AOD ratio were used as indicators. Firstly, we established the relationship between PM2.5 and AOD in terms of the spatio-temporal variations, and discuss the impact of some potential factors for a better understanding of the spatio-temporal variations. Spatially, we found that the correlation is higher in the Beijing-Tianjin-Hebei and Chengyu regions and weaker in coastal areas. The PM2.5/AOD ratio shows an obvious north-south difference, with the ratio in North China higher than South China. Temporally, the correlation coefficient tends to be higher in May and September, with the PM2.5/AOD ratio higher in winter and lower in summer. As for interannual variations, we detected a decreasing tendency for the PM2.5-AOD correlation and PM2.5/AOD ratio for recent years. Then, to determine the impact of the weakening of the PM2.5-AOD relationship on PM2.5 remote sensing retrieval performance, a geographically weighted regression (GWR) retrieval experiment was conducted. The results showed that the performance of retrievals is also decreasing while PM2.5-AOD relationship getting weaker. Our study investigated the PM2.5-AOD relationship over a large extent at the city scale, and investigated the temporal variations in terms of interannual variations. The results will be useful for the satellite retrieval of PM2.5 concentration and will help us to further understand the PM2.5 pollution situation in mainland China.

The Relationships between PM2.5 and Meteorological Factors in China: Seasonal and Regional Variations.

The interactions between PM2.5 and meteorological factors play a crucial role in air pollution analysis. However, previous studies that have researched the relationships between PM2.5 concentration and meteorological conditions have been mainly confined to a certain city or district, and the correlation over the whole of China remains unclear. Whether spatial and seasonal variations exist deserves further research. In this study, the relationships between PM2.5 concentration and meteorological factors were investigated in 68 major cities in China for a continuous period of 22 months from February 2013 to November 2014, at season, year, city, and regional scales, and the spatial and seasonal variations were analyzed. The meteorological factors were relative humidity (RH), temperature (TEM), wind speed (WS), and surface pressure (PS). We found that spatial and seasonal variations of their relationships with PM2.5 exist. Spatially, RH is positively correlated with PM2.5 concentration in north China and Urumqi, but the relationship turns to negative in other areas of China. WS is negatively correlated with PM2.5 everywhere except for Hainan Island. PS has a strong positive relationship with PM2.5 concentration in northeast China and mid-south China, and in other areas the correlation is weak. Seasonally, the positive correlation between PM2.5 concentration and RH is stronger in winter and spring. TEM has a negative relationship with PM2.5 in autumn and the opposite in winter. PS is more positively correlated with PM2.5 in autumn than in other seasons. Our study investigated the relationships between PM2.5 and meteorological factors in terms of spatial and seasonal variations, and the conclusions about the relationships between PM2.5 and meteorological factors are more comprehensive and precise than before. We suggest that the variations could be considered in PM2.5 concentration prediction and haze control to improve the prediction accuracy and policy efficiency.