[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Next Article in Journal
SAR and Optical Image Registration Based on Deep Learning with Co-Attention Matching Module
Previous Article in Journal
Joint Design of Complementary Sequence and Receiving Filter with High Doppler Tolerance for Simultaneously Polarimetric Radar
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Remote Sensing
Volume 15
Issue 15
10.3390/rs15153878
remotesensing-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data

by
Chunhui Liu
1,
Sensen Wu
2,3,
Zhen Dai
4,
Yuanyuan Wang
2,5,
Zhenhong Du
2,3,
Xingyu Liu
1 and
Chunxia Qiu
1,*
1
College of Geomatics, Xi’an University of Science and Technology, Xi’an 710054, China
2
School of Earth Sciences, Zhejiang University, Hangzhou 310027, China
3
Zhejiang Provincial Key Laboratory of Geographic Information Science, Hangzhou 310028, China
4
China Mobile (Zhejiang) Innovation Research Institute Co., Ltd., Hangzhou 310016, China
5
Ocean Academy, Zhejiang University, Zhoushan 316021, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2023, 15(15), 3878; https://doi.org/10.3390/rs15153878
Submission received: 6 July 2023 / Revised: 26 July 2023 / Accepted: 3 August 2023 / Published: 4 August 2023
Browse Figures
Figure 1
<p>Location and distribution of ground-based air quality testing stations in BTH. (<b>a</b>) shows the geographical location of the Beijing-Tianjin-Hebei region of China. (<b>b</b>) shows the population distribution in the study area. (<b>c</b>) shows the location of air quality monitoring stations and elevation data.</p> "> Figure 2
<p>Characteristic distribution of the main influencing factors of the inversion of NO2 at ground-level.</p> "> Figure 3
<p>GTNNWR model structure (<math display="inline"><semantics><mrow><msubsup><mi mathvariant="normal">d</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">S</mi></msubsup></mrow></semantics></math> denotes the spatial distance between individual image elements, while <math display="inline"><semantics><mrow><msubsup><mi mathvariant="normal">d</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">T</mi></msubsup></mrow></semantics></math> denotes the difference between each image element).</p> "> Figure 4
<p>The process of downscaling and prediction of impact factors is based on the GTNNWR model.</p> "> Figure 5
<p>Performance indicators for the four groups of models.</p> "> Figure 6
<p>Box diagram with error lines.</p> "> Figure 7
<p>Ground-level NO2 predictions and TROPOMI NO2 concentrations daily variation.</p> "> Figure 8
<p>Average ground-level NO2 concentration map for 2019–2022.</p> "> Figure 9
<p>Standard deviation of seasonal variation in near-surface NO2 and TROPOMI NO2 concentrations.</p> "> Figure 10
<p>Percentage stacked histograms of near-surface NO2 concentrations at different thresholds, per quarter, 2019–2022.</p> "> Figure 11
<p>Spatiotemporal distribution of ground-level NO2 concentration in Beijing–Tianjin–Hebei region during the 2019 New Year holidays (4–9 February).</p> "> Figure 12
<p>Spatiotemporal distribution of ground-level NO2 concentration in Beijing–Tianjin–Hebei region during the 2020 New Year holidays (24–29 January).</p> "> Figure 13
<p>Spatiotemporal distribution of ground-level NO2 concentrations in Beijing from 11 June to 22 June 2020.</p> "> Figure 14
<p>Four models to deal with the predicted spatiotemporal distribution of ground-level NO2 concentration at 500 m resolution in Fengtai District on 15 June 2020.</p> "> Figure 15
<p>Spatiotemporal distribution of daily high-resolution ground-level NO2 concentrations in Shijiazhuang, the capital of Hebei Province, from 2 January to 13 January 2021.</p> "> Figure 16
<p>Four models deal with the predicted spatiotemporal distribution of ground-level nitrogen dioxide concentrations at 500 m resolution in Gaocheng District on 2 January 2021.</p> "> Figure 17
<p>Changes in the spatiotemporal distribution of ground-level NO2 concentrations in Beijing and Zhangjiakou during the 2022 Winter Olympic Games.</p> ">
Versions Notes

Abstract

:
This study utilized TROPOMI remote sensing data, MODIS remote sensing data, ground observation data, and other ancillary data to construct a high-resolution spatiotemporal distribution and evaluation of ground-level NO2 concentrations in the Beijing–Tianjin–Hebei (BTH) region using the Geographic Temporal Neural Network Weighted Regression (GTNNWR) model. Through this model, we obtained the daily distribution of ground-level nitrogen dioxide (NO2) concentrations in the Beijing–Tianjin–Hebei region at a resolution of 500 m for the period of 2019–2022. The research results exhibited higher accuracy and more detailed features compared to other models, enabling a more accurate reflection of the spatial distribution and temporal variations of ground-level NO2 concentrations in the region, while retaining more details and trends and excluding the influence of noisy data. Furthermore, we conducted an evaluation analysis considering important events such as public health incidents and the Winter Olympics. The results demonstrated that the GTNNWR model outperformed the Random Forest (RF), Convolutional Neural Network (CNN), and Geographic Neural Network Weighted Regression (GNNWR) models in performance metrics such as R2, RMSE, MAE, and MAPE, showcasing greater reliability when considering spatiotemporal heterogeneity and spatiotemporal non-stationarity. This study provides crucial data support and reference for atmospheric environmental management and pollution prevention and control in the Beijing–Tianjin–Hebei region.

1. Introduction

Air pollution is a complex mixture of pollutants such as particulate matter, ozone, sulfur dioxide, and nitrogen oxides, posing significant challenges to human health, environmental sustainability, and economic development [1,2]. Nitrogen dioxide (NO2), as one of the most important air pollution indicators, is a harmful gas mainly produced by the combustion of fossil fuels, especially from vehicles, power plants, and industrial processes, as well as from lightning and soil bacteria [3,4]. Moreover, nitrogen dioxide is a precursor to secondary pollutants such as ozone and particulate matter, which can further exacerbate the harmful effects of air pollution and are associated with a range of adverse health effects, including respiratory and cardiovascular diseases [5,6]. The Beijing–Tianjin–Hebei region is one of the most polluted areas in China, and monitoring the emission of nitrogen dioxide has always been a focus of air pollution prevention and control work. Our study aims to provide a high-resolution spatiotemporal distribution of surface nitrogen dioxide concentration in this region, which can be used to report and evaluate pollution control policies and measures [7,8].
Due to the harmful effects of nitrogen dioxide, accurate and timely monitoring of its concentration levels in the atmosphere is increasingly needed. Currently, there are various methods to measure and estimate ground-level nitrogen dioxide concentration, including ground-based monitoring stations, passive samplers, and remote sensing techniques such as satellite images and unmanned aerial vehicles [9,10]. Ground-based monitoring stations provide accurate and continuous measurements of nitrogen dioxide concentration at specific locations but have limited spatial coverage and may not capture changes in concentration levels over larger areas. On the other hand, passive samplers can be used to measure nitrogen dioxide concentration over longer periods and provide more representative estimates of average concentration levels in specific areas [11]. Remote sensing techniques provide wider spatial coverage and have been widely used to monitor high-resolution spatiotemporal nitrogen dioxide concentrations. This method relies on measuring the radiation reflected or emitted by the atmosphere and can be used to infer nitrogen dioxide concentrations [12]. However, remote sensing methods also have limitations, such as the need for calibration and validation with ground-based measurements, and potential errors due to atmospheric changes and cloud cover [13]. Moreover, due to the resolution limitations of data sources, obtaining information on the distribution of NO2 ground concentration at a higher resolution is also a noteworthy issue. Currently, the most authoritative results in this field internationally come from the atmospheric environment remote sensing team led by Dr. Weijing from the University of Maryland and Professor Li Zhanqing, who developed China’s high-resolution (1 km), high-quality near-surface air pollution distribution [14,15].
In recent years, there has been increasing interest in developing new methods that use deep learning and artificial intelligence technologies to estimate nitrogen dioxide concentrations [16,17]. These methods can integrate multiple data sources, including satellite images, ground measurements, and meteorological data, to improve the accuracy and reliability of nitrogen dioxide concentration estimates. Among these methods, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are some of the most commonly used deep learning methods. These methods can automatically extract features from the data and build complex nonlinear models to achieve accurate predictions of concentration distributions [18,19]. For example, recent studies have used CNN models to process remote sensing satellite data to estimate ground-level nitrogen dioxide concentration distributions [20]. The model can automatically learn spatiotemporal features in remote sensing data and output high-precision concentration distribution images. Compared with traditional supervised learning methods, this unsupervised learning method can improve the model’s generalization ability and robustness. In addition to deep learning methods, there are also artificial intelligence technologies based on physical and statistical models, such as differential optical absorption spectroscopy (DOAS) and spatial interpolation techniques. These methods can consider the influence of meteorological and environmental factors on nitrogen dioxide concentrations to improve estimation accuracy and reliability [21].
Du et al. proposed a geographically weighted neural network weighted regression (GNNWR) model, which combines the advantages of ordinary linear regression (OLR) models and neural network models [22,23]. By using the learning ability of neural networks and the local spatial interpretability of spatial weights, the model can handle the spatial heterogeneity and complex nonlinearity of regression relationships, has better fitting accuracy and prediction performance than GWR and neural network models, and has the potential to solve complex spatial relationships in many fields. However, the GNNWR model faces challenges in expressing spatiotemporal closeness and constructing optimal weights, which may lead to insufficient estimation of spatiotemporal non-stationarity. To deal with the complex nonlinear interactions between time and space, Wu et al. proposed a spatiotemporal proximal neural network (STPNN) to accurately generate spatiotemporal distances and extended it to GNNWR to develop a geospatiotemporal neural network weighted regression (GTNNWR) model to effectively model spatiotemporal non-stationarity relationships, and demonstrated that GTNNWR has the potential to handle complex spatiotemporal non-stationarity in various geographic processes and environmental phenomena in ocean analysis [24].
Therefore, this study uses the GTNNWR model to integrate the TROPOMI sensor daily data, MODIS NDVI data, ERA5 meteorological data, and other auxiliary data to simulate the surface NO2 concentrations from 2019 to 2022 and validate them with the ground station data to obtain the high-resolution (500 m) daily surface NO2 in the Beijing–Tianjin–Hebei region from 2019 to 2022 concentration distribution from 2019 to 2022. By comparing the performance indexes with regression methods such as CNN and GNNWR, the advantages of the GTNNWR model in the spatiotemporal non-smoothness relationship of atmospheric pollutants are investigated, and the consistency and differences between the results and other models in predicting ground-level NO2 concentration data are verified. The study provides a valuable reference for the spatiotemporal distribution of NO2 in the Beijing–Tianjin–Hebei region from 2019–2022. In addition, the research results emphasize the importance of remote sensing technology in NO2 pollution monitoring and evaluation, and demonstrate the potential of the GTNNWR model in improving the accuracy and reliability of air pollution evaluation.

2. Materials and Methods

2.1. Study Area

The Beijing–Tianjin–Hebei region (BTH) is one of the most industrialized and densely populated areas in China [25]. The region covers an area of approximately 218,000 square kilometers and is home to over 100 million people [26]. Due to its rapid economic development and urbanization, air pollution has become a major public health issue in the Beijing–Tianjin–Hebei region, where residents are frequently exposed to high levels of pollutants such as NO2, PM2.5, and ozone [27]. The sources of air pollution in the region are complex and include transportation, industrial activities, residential heating, and natural dust [28,29]. In recent years, a series of measures have been implemented in the region to reduce emissions and improve air quality, including the implementation of strict emission standards, the promotion of clean energy, and the closure of high-polluting enterprises [30]. However, despite these efforts, air pollution remains an urgent problem in the region. It is necessary to continue monitoring air quality comprehensively to evaluate the effectiveness of these measures and provide a basis for future policy decisions. This research will provide valuable references for the temporal and spatial patterns of NO2 in the region. Figure 1a shows the geographical location of the Beijing–Tianjin–Hebei region in China, a region that covers the political center, important port cities, and three provincial divisions with the most developed steel industries in China. It is due to the unique industrial structure and importance of this study area that high-resolution monitoring of its air quality is necessary, particularly for nitrogen dioxide which is strongly influenced by secondary and tertiary industries and transport. Figure 1b shows the population distribution in the study area, which also has a strong correlation to the production of nitrogen dioxide, and it can be seen that the population is mostly concentrated in cities and urban agglomerations, which can provide a preliminary reference for the study results. Figure 1c shows the location and elevation data of air quality monitoring stations, which are regionally heterogeneous and concentrated in large cities. Elevation has some influence on the propagation of nitrogen dioxide due to air movement.

2.2. Data and Pre-Processing

2.2.1. Ground-Level NO2 Data

The daily surface NO2 concentration data selected for the Beijing–Tianjin–Hebei region in this article were obtained from the China National Environmental Monitoring Center and cover the period from 1 January 2019 to 31 December 2022. A total of 80 air-quality ground monitoring sites were included (Figure 1). The ground NO2 concentrations were measured via a molybdenum converter method and calibrated according to the Chinese Ambient Air Quality Standard [31]. Due to reasons such as site maintenance, a small number of missing values during the study period were filled by averaging the hourly NO2 measurement results of the site to the daily scale to complete the temporal sequence.

2.2.2. TROPOMI NO2 Data

TROPOMI (TROPOspheric Monitoring Instrument) is a multispectral instrument on board the Copernicus Sentinel-5 Precursor (S5P) satellite launched in 2017, which can monitor the concentration of gases and particles in the Earth’s atmosphere with high accuracy and resolution [32]. Compared to the Ozone Monitoring Instrument (OMI) sensor data, which has a similar mission, TROPOMI has higher spatial resolution and accuracy, providing more detailed and accurate air quality data. Its high spatial resolution is 7 × 3.5 km (improved to 5.5 × 3.5 km after 6 August 2019) and has been proven to have a broader range of applications in environmental monitoring and climate research [33]. The NO2 retrieval algorithm and product information of TROPOMI have been detailed by van Geffen et al. and Wu et al. [34,35]. The tropospheric NO2 vertical column density (VCD) data in the daily TROPOMI Level-2 data covering the entire Beijing–Tianjin–Hebei region from 1 January 2019 to 31 December 2022, were obtained from GESDISC [36]. Tropospheric NO2 data with QA_value > 0.75 were selected for modeling, and cloud, inversion errors, and problematic retrievals were excluded [37]. To fill the temporal and spatial gaps in satellite tropospheric NO2 data, the inverse distance weighting (IDW) method and time-linear interpolation were used in this study.

2.2.3. Spatiotemporal Ancillary Data

To improve the modeling of NO2 gas pollutants, this study selected several spatiotemporal auxiliary variables in the Beijing–Tianjin–Hebei region that are related to NO2 emission types and anthropogenic emissions, which can affect the transmission mode of ground-level NO2 [38]. The variables include a 16-day normalized difference vegetation index (NDVI) data (500 m) produced by MODIS data to improve spatial resolution. To meet the research requirements, it was time-linearly interpolated to expand it to daily data [39]. Digital elevation model (DEM) data (90 m) obtained from the Shuttle Radar Topography Mission (SRTM) were also used [9]. Meteorological data related to potential emission sources and diffusion were obtained from eight meteorological estimates of ERA-5 atmospheric reanalysis products, including wind direction (WD) and wind speed (WS) at 10 m height, temperature (TEMP) at a height of 2 m, total precipitation (TP), surface pressure (SP), boundary layer height (BLH), evaporation (ET), and relative humidity (RH), with a resolution of 10 km [40]. Road network (RN) data in the study area were collected from OSM and their density was calculated using kernel density estimation [41]. Yearly population density data (PD, 1 km) from NASA were also used [42]. In addition to this, the study also obtained data from the China Statistical Yearbook on the number of industrial enterprise units (IEU), GDP, and the number of resident residents (RR) at the county level in Beijing, Tianjin, and Hebei for 2019–2022 to refine the modeling [43]. Table 1 shows the relevant parameters of the spatiotemporal auxiliary variables used in this study.
In order to understand the basic situation of the above data, this study first selected several influence factors with the highest correlation as well as the measured data from the ground monitoring stations, and analyzed the data for characteristic distribution (Figure 2) to obtain the basic statistical characteristics of these data. These statistical indicators provide information on the concentration trend and discrete degree of the data, which helps to understand the overall situation, shape, and change trends of the data. At the same time, the feature distribution analysis carried out on the data facilitates the detection of data outliers and assists in data cleaning in data preprocessing for model performance and accuracy.

2.3. GTNNWR Model

2.3.1. Model Development

Considering the close relationship between nitrogen dioxide concentrations and spatiotemporal factors, this study developed a geo-temporal neural network weighted regression (GTNNWR) model for air quality assessment based on a spatiotemporal weight matrix and a spatiotemporal neighborhood depth neural network [44]. The model aims to analyze the regression relationships between 16 independent variables related to nitrogen dioxide production and dispersion and the dependent variable (ground-level nitrogen dioxide concentration). To address the complex spatiotemporal heterogeneity and autocorrelation in the atmosphere, the STPNN (Spatial Temporal Distance Fusion Neural Network) was introduced based on the GNNWR model. It combines temporal and spatial distances while using STWNN (non-stationary weight calculation neural network) to calculate the weights of the factors.
The GTNNWR model consists of an input layer that receives normalized spatial distance and feature data as input, followed by a series of fully connected layers and an activation function layer. In this model, the spatial distances are first processed through the dense and PReLU activation function layers and then fused with the feature data to form the final output. The process of constructing the GTNNWR model from a mathematical perspective is described below [45].
To describe the spatiotemporal non-stationarity of geographical relationships and the differences in weights across locations, this study first reviews the ordinary linear regression model, which is mathematically expressed as
y i = β 0 + ∑ k = 1 p ( β k x ik ) + ε i
where yi is the dependent variable, xik is the kth variable of the ith sample, p denotes the number of independent variables, β0 and βk are the regression coefficients, and εi is the error terms [46].
However, the spatiotemporal non-stationarity of geographical relationships allows for variability in the regression coefficients across spatiotemporal locations [24]. Therefore, we introduce a spatiotemporal, geographically weighted regression model, whose mathematical expression is
y ( s i ,   t i ) = β 0 ( s i ,   t i ) + ∑ k = 1 p β k ( s i ,   t i ) x ik + ε i
where y(si, ti) denotes the dependent variable at the spatiotemporal location (si, ti). To further describe the spatiotemporal non-smoothness and weight differences, the study introduced a spatiotemporal weight matrix and a spatiotemporal neighborhood deep neural network to establish the GTNNWR model, which is mathematically expressed as
y ( s i ,   t i ) = ω 0 ( s i ,   t i ) * β 0 + ∑ k = 1 p ω k ( s i ,   t i )   β k x ik + ε i
In this model, ω 0 (si, ti) and ω k (si, ti) are the non-stationary weights at the spatiotemporal point (si, ti), and the corresponding regression coefficients are obtained by multiplying them by ordinary linear regression estimates.
To determine the spatiotemporal weight matrix and the non-stationary weights, a spatiotemporal neighborhood deep neural network is used to obtain a complex spatiotemporal neighborhood representation vector ST at the spatiotemporal location (si, ti). By combining ST with the weight kernel function structure, we can obtain the spatiotemporal weight matrix W (si, ti) of the form:
W   ( s i ,   t i ) = ω 0 ( s i ,   t i ) 0 0 0 0 ω 1 ( s i ,   t i ) 0 0 0 0 … 0 0 0 0 ω p ( s i ,   t i )
Thus, the spatiotemporal non-smoothness and weight differences in the GTNNWR model are determined via the spatiotemporal weight matrix W(si, ti). This relationship effectively captures the spatiotemporal variability of geographical relationships and differences in weight distributions, further improving the accuracy and explanatory power of the regression model.
In summary, the GTNNWR model combines linear regression and deep learning methods by introducing a spatiotemporal weight matrix and a spatiotemporal neighborhood deep neural network to better describe and predict spatiotemporal non-stationarity in geographic relationships. Specifically, the regression coefficients are modeled as the non-stationary weights of spatiotemporal points multiplied by ordinary linear regression estimates to obtain estimates of regression coefficients with spatiotemporal proximity. The detailed architecture of the GTNNWR model is given in Figure 3. The model has been applied in areas such as marine water quality monitoring, and the results of the empirical analysis show that the GTNNWR model is highly accurate and effective in modeling and predicting spatiotemporal non-stationarity, but its application in the atmospheric domain has not yet been carried out. This study will validate and explore the model’s capability and advantages in dealing with atmospheric spatiotemporal heterogeneity and autocorrelation problems.

2.3.2. Model Evaluation

To validate the accuracy of the GTNNWR model for regression and prediction of ground-level NO2 concentrations, three methods—geographic neural network weighted regression (GNNWR), convolutional neural network (CNN), and random forest (RF)—were selected for validation against the results of the GTNNWR model in this study [47].
Over 100,000 rows of data from 80 air monitoring sites in the study area for the period of 2019 to 2022 were first integrated into one data set. The integrated data set was divided into a training set, a validation set, and a test set, and the cross-validation method was used to divide the data set into multiple subsets, rotating one of the subsets as the validation set and the rest as the training set. The training set was trained using each of the four methods: GTNNWR model, GNNWR model, CNN, and RF. For each model, the trained model was used to predict the validation set, and four sets of predictions were obtained. These predicted values were compared with the real data corresponding to the ground sites in the validation set. By comparing the predicted values with the true values, four sets of performance metrics were calculated, including R2 (coefficient of determination), MAE (mean absolute error), RMSE (root mean square error), and MAPE (mean absolute percentage error). These metrics are used to assess the regression and prediction accuracy of the models [48]. The following equations were used to calculate the four performance indicators,
R 2 = 1 − ( S S R / S S T )
where SSR is the sum of squares of residuals, which is the sum of the squares of the errors between the predicted and true values, and SST is the total sum of squares, which is the sum of the squares of the errors between the true and mean values.
M A E = ( 1 / n ) * ∑ y _ p r e d − y _ t r u e
R M S E = ( 1 / n ) * ∑ ( y _ p r e d − y _ t r u e ) 2
M A P E = ( 1 / n ) * ∑ ( y _ p r e d − y _ t r u e ) / y _ p r e d * 100 %
where n is the number of samples, ∑ denotes summing over all samples, y_pred denotes the predicted value, and y_true denotes the true value.
The flowchart (Figure 4) shows the training process of the GTNNWR model for reducing and predicting the ground NO2 concentration when processing remote sensing data, meteorological data and auxiliary data applications. The GTNNWR model obtains the predicted values of the ground NO2 concentration for the 1 km data set and the 500 m data set, and validates and evaluates the results with the actual measured data from the ground station. In the above equations and flowcharts, the predicted values are the results given by the model and the true values correspond to the actual observations from the ground station [49]. By calculating these performance metrics, the regression and prediction accuracy of the model can be evaluated. It is important to note that the exact calculation of these metrics may vary depending on the subject area or research question. Figure 5 shows the results of the comparison of the performance metrics of the four models for predicting ground-level NO2 concentrations.
The results show that the R2 (coefficient of determination) of the GTNNWR model reached 0.89 according to the data displayed in Figure 5, indicating that the model fits the observed data well. The GTNNWR model was able to fit the correlation between the data well compared to other methods, indicating that the model has a clear advantage in dealing with the spatiotemporal heterogeneity (variability across locations and time) and autocorrelation between the ground-level NO2 concentration and the influencing factors. This implies that the GTNNWR model is able to more accurately capture the correlations between ground-level NO2 concentrations and various impact factors, including taking into account the variability in location and time as well as autocorrelation between data points.
Taken together, the GTNNWR model excels in dealing with the complex relationship between ground-level NO2 concentrations and the influencing factors, and is able to better explain and predict this relationship. This gives the GTNNWR model a clear advantage in research and application in this field.
In order to further investigate the performance metrics of several models, 100 sets of data were selected here to calculate the Pearson correlation coefficients and RMSEs between the results of the four models and the measured data, and the box plots with error lines (Figure 6) were generated to further express the differences in the result performance of the four models.
It can be seen that the Pearson correlation coefficient of the GTNNWR model is 0.89, which indicates that there is a strong positive correlation between the predictions of the model and the actual observations. Meanwhile, the RMSE of the GTNNWR model is 10.50, indicating that the average difference between its predicted and actual observed values is small. In contrast, the other three models perform slightly less well. The Pearson correlation coefficient of the GNNWR model is 0.89, which is the same as that of the GTNNWR model, but its RMSE is slightly higher at 10.65. The Pearson correlation coefficients of the CNN and the RF are 0.79 and 0.77, which are lower compared to those of the GTNNWR model and the GNNWR model, and their RMSE is 14.74 and 14.97, which is a poor performance compared to the GTNNWR results.
Taken together, the GTNNWR model performs better in terms of error control, with a strong positive correlation between its predicted results and the actual observations, and a small average difference. This makes the GTNNWR model potentially more reliable and accurate in the application of this topic. Based on this, the GTNNWR model will be used in this study to invert and analyze the daily high-resolution spatiotemporal distributions of ground-level NO2 concentrations in the Beijing–Tianjin–Hebei region from 2019 to 2022.

3. Results

3.1. Daily High-Resolution Surface NO2 Concentrations

The study used the GTNNWR model to model and analyze 16 factors affecting ground-level NO2 concentrations in the Beijing–Tianjin–Hebei region during the period of 2019–2022. By constructing a geo-temporal weighted neural network to model these factors in association with ground-level NO2 concentration data for prediction and analysis of NO2 concentrations, daily 500 m resolution ground-level NO2 concentration data for a total of 1460 days from 1 January 2019 to 31 December 2022 were successfully obtained, which will enable relevant studies to capture NO2 concentration variations in geographic space more accurately and provide valuable information for further environmental monitoring and air pollution management.
Figure 7 shows the time series variation curves of TROPOMI NO2 as well as the predicted ground-level NO2 concentrations for 1460 days during the study period. The comparison provides insight into the relationship between ground-level NO2 concentrations and meteorological remote-sensing satellite observations. In the figure, the horizontal axis indicates the time and the vertical axis indicates the TROPOMI or ground NO2 concentration.
By observing Figure 7, it is possible to study the dynamic relationship between TROPOMI and ground-level NO2 concentrations. In general, the two sets of data present the same pattern of variation, showing that the highest NO2 concentrations are found in the study area each year in winter and the lowest in summer. At the same time, the ground-level NO2 concentrations show a decreasing trend from year to year for the combined four years as a whole. The results of this figure help us to understand the correlation and spatiotemporal relationship between TROPOMI and ground NO2 concentrations. It should be noted that Figure 7 presents only the temporal variation curves and cannot directly derive the causal relationship. Further statistical analysis and modeling work can be done with these data to explore the causal relationships and interaction mechanisms between these factors and ground NO2 concentrations.
To further demonstrate the changes in ground-level NO2 concentrations from 2019–2022, We calculated a map of annual average ground-level NO2 concentrations based on daily data (Figure 8). This comparison can visually demonstrate the average NO2 levels at different locations and time periods in the Beijing–Tianjin–Hebei region.
It can be clearly observed from Figure 8 that the ground-level NO2 concentration in the Beijing–Tianjin–Hebei region shows a clear decreasing trend during the period of 2019–2022. Especially in the northern non-important industrial areas, the area of the low-concentration area shows a trend of expansion. At the same time, the annual average NO2 concentrations in important industrial areas or transportation hubs, such as Tangshan, Tianjin, and Shijiazhuang, have also decreased to some extent. This trend may be related to factors such as the development of public health events and environmental protection policies. However, there is a rebound in overall NO2 concentrations in 2022 compared to the previous year, which to some extent reflects the gradual recovery of industries in the studied area, such as industry and transportation, which have adapted to the development of public health events.
Figure 9 represents the standard deviation of the seasonal changes in near-surface NO2 concentrations and TROPOMI NO2 concentrations over different quarters. The horizontal coordinates indicate the quarters, from 1 to 4, representing the first through fourth quarters of the year, respectively. The vertical coordinate represents the standard deviation value, which measures the magnitude of change in the data over each quarter. By comparing the information on the graphs, it is possible to observe that the seasonal fluctuations of the two sets of data show a relatively well-fitting correspondence pattern as well as the same seasonal differences as in Figure 8.
In order to observe in detail the differences in air quality from quarter to quarter during the study period, this study also statistically analyzed the daily data and divided the near-surface NO2 concentration into four threshold ranges, which are less than 20 μg/m3, less than 40 μg/m3, less than 60 μg/m3, and greater than 60 μg/m3, to obtain the stacked histograms of the percentages of near-surface NO2 concentration at different thresholds for each quarter of the period of 2019 to 2022 (Figure 10).
It can be seen that there is an overall downward trend in near-surface NO2 concentrations from 2019–2022, with better air quality in the second and third quarters compared to the first and fourth quarters, and almost no NO2 concentration thresholds above 60 μg/m3 occurring throughout the quarter, but the seasonal differences presented on the graphs have yet to be discussed in depth on a daily basis, in order to explore the reasons for the differences and the factors that influence them.
Based on these findings, this study will further investigate and discuss the daily NO2 concentration changes for specific areas and specific time periods. Additionally, different modeling approaches will be used and the results will be compared cross-sectionally with those of the GTNNWR model to further validate the reliability of our research methods. In addition, attention will be paid to the results of high-resolution, small-scale areas to capture the geospatial variation in NO2 concentration more accurately.

3.2. Comparison of the Changes in NO2 Concentration in the Study Area in the New Year

The study is important for analyzing the impact of a global outbreak of public health events on industrial production, transportation, and other areas from the end of 2019 to 2022. An in-depth analysis was performed by selecting the changes in ground-level NO2 concentrations (2019, Figure 11; 2020, Figure 12) for the adjacent 2019 and 2020 New Year holidays (4–9 February 2019 and 24–29 January 2020) in the study area.
The following results can be obtained from the comparative study of Figure 11 and Figure 12: By comparing the changes in the spatiotemporal distribution of ground-level NO2 concentrations during the New Year holidays in 2019 and 2020, it was found that the ground-level NO2 concentrations during the New Year holidays in 2020 were significantly lower than those in 2019, from which it can be inferred that the public health event had a more significant effect on industrial production and transportation activities in the Beijing–Tianjin–Hebei region. At the same time, the reduction of industrial production and transportation activities leads to the improvement of air quality, and it can be seen from Figure 11 and Figure 12 that the event itself had a positive effect on the reduction of ground-level NO2 concentrations. Comparing the changes in ground NO2 in different provinces and cities over the same period, it can be seen that Tianjin and Tangshan, which are heavy industrial and port cities, are less responsive to the impact of public health events, and although the ground NO2 concentration decreases to some extent, it still remains high compared to other areas in Beijing, Tianjin, and Hebei, which may be related to the high level of industry such as manufacturing or port trade in the region.
In conclusion, by analyzing the changes in the spatiotemporal distribution of ground-level NO2 concentrations during the New Year holidays in 2019 and 2020, it is possible to gain insight into the effects of public health events on industrial production, transportation, and other areas, and to preliminarily assess their effects on the improvement of air quality in the study area. In addition, by identifying and assessing the effects of different factors, the driving mechanisms of NO2 concentration changes can be explored preliminarily. These results have important reference value for environmental management and air pollution management strategy development.

3.3. Variations in Ground-Level Nitrogen Dioxide Concentrations during Public Health Events

Building upon the aforementioned understanding, the study will focus on analyzing the variation of ground-level NO2 concentrations during the public health event that occurred at Xinfadi, Fengtai District, Beijing, from 11 June to 22 June, 2020. Three different models, namely GNNWR, CNN, and RF, will be utilized to generate data for the Fengtai District, which will be compared with the results obtained from the GTNNWR model. This comparison aims to further discuss the reliability of the research methods employed. Figure 13 illustrates the temporal variation of ground-level NO2 concentrations in the Beijing area from 11 June to 22 June, 2020.
Figure 13 presents the variation of ground-level NO2 concentrations in the Beijing area during the specified period. It can be observed that after a significant decrease, the NO2 concentrations exhibit a slow recovery trend, particularly in the Fengtai District where Xinfadi is located, and its surrounding areas. This highlights the importance of high-resolution daily data, enabling relevant personnel to make timely and accurate assessments of the event’s development by incorporating policy interventions or other influencing factors.
In order to clearly compare the differences and synergies in the predictive results among the four methods, Figure 14 was chosen to display the comparison of the 500 m resolution prediction results for the Fengtai District on 15 June 2020, processed with the four models.
Through the comparative analysis presented in Figure 14, it is evident that the GTNNWR model, in comparison to the other models, effectively captures the developmental trends and details of ground-level NO2 concentrations, while successfully avoiding the “striping” effect caused by noisy data. Particularly, in the vicinity of the Xinfadi area in the eastern part of Fengtai District, the NO2 concentrations are significantly lower than in other areas. This observation indirectly reflects the overall effectiveness of policy interventions in controlling transportation and industrial production during the specified time period.
This finding suggests that the GTNNWR model exhibits superior accuracy in data processing and robust noise filtering capabilities compared to the other models, resulting in more reliable and accurate prediction results. Furthermore, the accuracy and stability of the GTNNWR model further validate its reliability and effectiveness within the research methodology.
To further compare the differences in ground-level nitrogen dioxide (NO2) concentrations between the provincial capital city and other regions, particularly important industrial cities and transportation hubs, daily high-resolution, ground-level NO2 concentrations from 2 January to 16 January, 2021, in Shijiazhuang, the capital city of Hebei Province, were selected for the study (Figure 15).
Figure 15 shows the spatiotemporal distribution of high-resolution ground-level daily NO2 concentrations from 2 January to 13 January 2021 in Shijiazhuang, the capital of Hebei Province. According to Figure 15, the NO2 concentration in Shijiazhuang generally showed a decreasing trend during this period, especially in Shijiazhuang Gaocheng district and its surrounding areas, which were more affected by public health events during this period. The decrease in nitrogen dioxide concentration may be influenced by a variety of factors.
Firstly, the spatiotemporal distribution of ground-level NO2 concentrations during the initial phase of the study period could be affected by the collective heating in northern China during winter and the transportation activities related to the Spring Festival holiday. The collective heating in winter may lead to increased emissions of pollutants such as coal combustion, thus impacting air quality. Additionally, during the Spring Festival holiday, the substantial population movement and transportation activities could also contribute to the release of NO2 pollutants, further affecting air quality. Therefore, during the early phase of the study period, the NO2 concentrations in the urban area of Shijiazhuang were relatively high.
However, as time progressed, a declining trend in NO2 concentrations was observed in Shijiazhuang. This could be attributed to the implementation of certain policy measures or improvements in the traffic conditions during the study period, resulting in reduced NO2 emissions. This observation aligns with our previous speculation regarding the impact of policies on Shijiazhuang. Furthermore, the Gaocheng District and its surrounding areas exhibited a faster rate of decline in NO2 concentrations, which could be attributed to the influence of public health events and other factors in these regions. Moreover, unlike Beijing, as shown in Figure 13, where a faster recovery of ground-level NO2 concentrations was observed during the public health event, Shijiazhuang experienced a significant decline in ground-level NO2 concentrations, maintaining them at a lower level. This difference could also be associated with a reduction in population and an industrial slowdown in the region following the Spring Festival holiday.
Similar to the study in Fengtai District, Beijing, the results of four deep learning models, GTNNWR, GNNWR, CNN, and RF, predicting the high-resolution spatiotemporal distributions of ground NO2 concentrations on 2 January 2021, in Gaocheng District, Shijiazhuang City, which is rich in detail, were also selected for comparison in this study to produce Figure 16.
Figure 16 presents the results of the GTNNWR model compared to three other different models in predicting the spatiotemporal distribution of ground-level NO2 concentration in Gaocheng District, Shijiazhuang City, on 2 January 2021. It can be observed from the comparison that due to the consideration of spatiotemporal heterogeneity and non-stationary relationships by the GTNNWR model, it possesses a certain capability of anomaly detection and correction, enabling it to effectively identify and handle noisy data. Consequently, the anomalous points caused by noisy data, which appear in other models, are successfully suppressed in the predictive results of the GTNNWR model. Additionally, the GTNNWR model exhibits a higher sensitivity to subtle differences in the data. This implies that it is capable of capturing small-scale variations that other models may overlook, thereby displaying more detailed information in the predictive results. This enhanced sensitivity to subtle differences is also evident from the graph, which clearly demonstrates the superior display of such differences compared to other models.

3.4. Changes in NO2 Concentration in Beijing and Zhangjiakou during the Winter Olympics

Winter is a season of increased air pollution in many areas of China, especially when cold air is stable and an inversion layer is formed, making it difficult for pollutants to disperse in the atmosphere and leading to increased pollutant concentrations. Beijing and Zhangjiakou were the host cities of the 2022 Winter Olympic Games, and traffic flows in and around the host cities were likely to increase during the Winter Olympics, especially from visitors and participants. Vehicle emissions are one of the major sources of air pollution, and increased traffic may lead to an increase in pollutant emissions. In anticipation of the Winter Olympics, infrastructure construction and industrial production activities may change due to policy influences, and these activities may affect industrial emissions and thus change the trend of NO2 concentrations. In order to study and analyze the impact of the Winter Olympics on these two cities, the study selected the changes in ground-level NO2 concentrations in Beijing and Zhangjiakou from 1 February to 20 February 2022, when the Winter Olympics were be held (Figure 17).
Figure 17 illustrates the spatiotemporal distribution of ground-level NO2 concentrations in Beijing and Zhangjiakou from February 1 to 20, including the 2022 Spring Festival and Winter Olympics. Zhangjiakou has consistently been one of the areas with the best air quality in the Beijing–Tianjin–Hebei region. The inclusion of both Beijing and Zhangjiakou in this study allows for a comparison of the changes in ground-level NO2 concentrations during the high-pollution period of winter, particularly before and after the Spring Festival.
During the initial phase of the study period, the air pollution index in the region was relatively high, which could be attributed to the Spring Festival travel rush (known as “Chunyun”) and the burning of fireworks and firecrackers during the Spring Festival. Chunyun refers to the period of intensive human mobility around the Chinese Lunar New Year, which can lead to increased traffic congestion and emissions, consequently resulting in elevated concentrations of air pollutants. Additionally, the tradition of setting off fireworks and firecrackers during the Spring Festival releases a significant amount of harmful substances, negatively impacting air quality.
After a brief period of control, the ground-level NO2 concentrations rebounded on 4 February, which coincided with the opening ceremony of the Winter Olympics. The increased transportation activities in both Beijing and Zhangjiakou associated with the Winter Olympics, including the movement of athletes, spectators, and staff, may have contributed to the rise in traffic volume and, consequently, increased emissions of exhaust fumes and air pollutants.
Despite the co-occurrence of winter and the Spring Festival, for most of the Winter Olympics, the ground-level NO2 concentrations remained relatively low. This indicates the effectiveness of air pollution control measures in the region. The government and relevant authorities likely implemented a series of measures to reduce pollutant emissions, such as strengthening industrial emission controls, restricting vehicle usage, and promoting clean energy. In comparison to the northern parts, the southeastern region of Beijing, situated near heavy industrial and port cities like Tangshan and Tianjin, experiences relatively high ground-level NO2 concentrations. The geographical location and surrounding industrial activities have a significant impact on the air quality in this area.

4. Discussion

The Geographical Temporal Neural Network Regression (GTNNWR) model has been widely applied and validated in various fields such as marine GIS. This study discusses the reliability and effectiveness of the model in the atmospheric domain. The results indicate that the GTNNWR model performs well in predicting ground-level NO2 concentrations, demonstrating good performance and efficiency in both the validation process with ground monitoring stations and the production of daily high-resolution results.
Compared to deep learning and machine learning methods such as CNN and RF, the GTNNWR model exhibits a higher correlation and accuracy between predicted and actual measurement results. This difference mainly stems from the advantages of GTNNWR in handling spatiotemporal heterogeneity and non-stationarity. Additionally, the reliability of the results is enhanced by the inclusion of a wide range of remote sensing data, meteorological data, and auxiliary data related to traffic and industrial production that are relevant to ground-level NO2 concentrations. Furthermore, differences in the algorithm, data sources, and feature extraction methods used by the model may result in inconsistent results compared to other studies in specific scenarios. Similarly, in the production process of daily high-resolution, ground-level NO2 concentrations, the GTNNWR model demonstrates its suitability and generalizability in handling subtle differences between data, preserving data details while avoiding the influence of noisy data, thus reflecting the applicability and scalability of deep learning in the atmospheric domain.
Of course, there are areas for improvement in this research. The quality of ground-level NO2 concentration data significantly affects the model’s prediction results. In the data-processing stage of this study, issues such as noise or missing data in the original measurements from Ground-level air quality monitoring stations were encountered, leading to inaccurate predictions from the model. Linear interpolation was used for data preprocessing in this study to handle outliers and missing values, but this inevitably introduces deviations from the actual situation. Therefore, improving the quality and acquisition methods of actual data would greatly enhance the accuracy of the prediction results. The training process of the GTNNWR model is similar to most deep learning models, and the model’s structure and parameter settings also impact the results. Different model structures and parameter choices may lead to differences in the prediction results. In the training process, the research selected the optimal model structure and parameters as much as possible through methods like cross-validation. The next step could involve introducing new algorithms or modules to optimize the overall performance of the algorithm, improving model integration methods to enhance the accuracy and robustness of the model [50].
Like most research methods, the GTNNWR model also has limitations when handling and predicting atmospheric data. The model’s prediction results may be limited by the coverage of available data. If the data set for ground-level NO2 concentrations only covers specific regions or time periods, the applicability and generalizability of the model may be restricted. Ground-level NO2 concentrations are influenced by multiple factors, including traffic emissions, industrial emissions, and meteorological conditions. The model may not fully capture the interactions among these complex factors, leading to inaccuracies in the prediction results.
It is also important to emphasize that in selecting the time period for the study, this study focuses on discussing public health events and important time periods (e.g., New Year’s and the Winter Olympics). This is because these events or activities have a significant impact on topics such as transportation, industrial emissions, and environmental protection. As mentioned earlier, ground-level NO2 concentrations are highly sensitive to these issues. At the same time, the occurrence of public health events such as COVID-19 provides a prominent research paradigm for the study of spatiotemporal variations in the concentration of atmospheric trace gases, and as mentioned earlier, the significant decrease in NO2 concentration at the ground-level during the period of 2019–2022 is in fact highly relevant to public health events such as COVID-19 and response policies, and can be followed up with deeper discussions of the changes in atmospheric trace gas concentrations due to such complex events and exploration of the deep relationships as well as trend coupling [51,52].

5. Conclusions

This study utilized the advantages of the GTNNWR model in handling the spatiotemporal heterogeneity and spatiotemporal non-stationarity relationships in data. TROPOMI remote sensing data, MODIS remote sensing data, ground observation data, and other auxiliary data were used to construct the daily high-resolution (500 m) spatiotemporal distribution and evaluation of ground-level nitrogen dioxide (NO2) concentration in the Beijing–Tianjin–Hebei region. By introducing high-resolution MODIS_NDVI data, the model optimized the resolution of ground-level NO2 concentration to 500 m, which is a first in related studies in the study area. In the validation of the model, the research results exhibited higher accuracy and more detailed features compared to CNN, RF, and GNNWR models. The model could eliminate the influence of noise while retaining more details, accurately representing the spatiotemporal distribution of ground-level NO2 concentration at a high resolution.
The research results demonstrated an overall decreasing trend in ground-level NO2 concentration in the Beijing–Tianjin–Hebei region from 2019 to 2022. It also expressed the spatiotemporal distribution patterns of lower levels in the northwest and higher levels in the southeast, which are related to the geographical location and industrial distribution in the Beijing–Tianjin–Hebei region. The southeastern region is a more developed industrial area and includes coastal cities, including the two most important cities in China (Beijing and Tianjin). On the other hand, the northwest region is designated as an ecological conservation area by policies, mainly consisting of mountainous areas or vegetation, with less developed secondary industries. Thus, this trend has been observed.
During specific time periods related to changes in NO2 concentration, the model accurately predicted the spatiotemporal distribution of ground-level NO2 concentration that corresponded to the actual situation. Differences in ground-level NO2 concentration were observed during the New Year holidays in the Beijing–Tianjin–Hebei region in 2019 and 2020, which may have been related to public health events. Additional studies on the Xinfadi area in Beijing and the Gaocheng District in Shijiazhuang reflected this correlation and differentiation. Additionally, a study during the period of the Winter Olympics in Beijing and Zhangjiakou also demonstrated a sensitive response of ground-level NO2 concentration to transportation and industrial production activities associated with these events.

Author Contributions

Conceptualization, C.L.; Formal analysis, Y.W.; Funding acquisition, C.Q.; Investigation, Y.W.; Methodology, C.L.; Project administration, C.Q.; Resources, Z.D. (Zhen Dai); Software, C.L.; Z.D. (Zhen Dai) and Z.D. (Zhenhong Du); Supervision, S.W. and Y.W.; Validation, S.W.; Visualization, X.L.; Writing—original draft, C.L.; Writing—review and editing, S.W. and Z.D. (Zhenhong Du). All authors have read and agreed to the published version of the manuscript.

Funding

This work was supported by the National Key Research and Development Program of China (No. 2021YFB3900900) and Provincial Key R&D Program of Zhejiang (No. 2021C01031).

Data Availability Statement

Not applicable.

Acknowledgments

This study was supported by the Deep-Time Digital Earth (DDE) Big Science Program.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Zhang, Q.; Jiang, X.; Tong, D.; Davis, S.J.; Zhao, H.Y.; Geng, G.N.; Feng, T.; Zheng, B.; Lu, Z.F.; Streets, D.G.; et al. Transboundary health impacts of transported global air pollution and international trade. Nature 2017, 543, 705–709. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  2. Akimoto, H. Global air quality and pollution. Science 2003, 302, 1716–1719. [Google Scholar] [CrossRef] [Green Version]
  3. Jion, M.M.; Jannat, J.N.; Mia, M.Y.; Ali, M.A.; Islam, M.S.; Ibrahim, S.M.; Pal, S.C.; Islam, A.; Sarker, A.; Malafaia, G.; et al. A critical review and prospect of NO2 and SO2 pollution over Asia: Hotspots, trends, and sources. Sci. Total Environ. 2023, 876, 162851. [Google Scholar] [CrossRef]
  4. Kim, M.; Brunner, D.; Kuhlmann, G. Importance of satellite observations for high-resolution mapping of near-surface NO2 by machine learning. Remote Sens. Environ. 2021, 264, 112573. [Google Scholar] [CrossRef]
  5. Rudke, A.P.; Martins, J.A.; Hallak, R.; Martins, L.D.; de Almeida, D.S.; Beal, A.; Freitas, E.D.; Andrade, M.F.; Koutrakis, P.; Albuquerque, T.T. Evaluating TROPOMI and MODIS performance to capture the dynamic of air pollution in São Paulo state: A case study during the COVID-19 outbreak. Remote Sens. Environ. 2023, 289, 113514. [Google Scholar] [CrossRef] [PubMed]
  6. Wang, C.; Sheng, Y.; Wang, J.; Wang, Y.; Wang, P.; Huang, L. Air pollution and human health: Investigating the moderating effect of the built environment. Remote Sens. 2022, 14, 3703. [Google Scholar] [CrossRef]
  7. Shen, N.; Zhao, X.; Li, L.; Zhou, B.; Duan, F.; Zhao, W. Spatial and temporal variation characteristics of atmospheric NO2 and SO2 in the Beijing-Tianjin-Hebei region before and after the COVID-19 outbreak. Air Qual. Atmos. Health 2021, 14, 1175–1188. [Google Scholar] [CrossRef]
  8. Zhou, C.; Li, Q.; He, Y.; Ma, P.; Chen, C. Spatiotemporal Change and Influencing Factors of Tropospheric NO2 column density of Beijing-Tianjin-Hebei Region in the Decade Based OMI Product. In Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 10–15 July 2016; pp. 4123–4126. [Google Scholar]
  9. Zheng, Z.; Yang, Z.; Wu, Z.; Marinello, F. Spatial variation of NO2 and its impact factors in China: An application of sentinel-5P products. Remote Sens. 2019, 11, 1939. [Google Scholar] [CrossRef] [Green Version]
  10. Scheibenreif, L.; Mommert, M.; Borth, D. Toward global estimation of ground-level no 2 pollution with deep learning and remote sensing. IEEE Trans. Geosci. Remote Sens. 2022, 60, 1–14. [Google Scholar] [CrossRef]
  11. Vojtisek-Lom, M.; Suta, M.; Sikorova, J.; Sram, R.J. High NO2 concentrations measured by passive samplers in Czech cities: Unresolved aftermath of Dieselgate? Atmosphere 2021, 12, 649. [Google Scholar] [CrossRef]
  12. Alnaim, A.; Sun, Z.; Tong, D. Evaluating Machine Learning and Remote Sensing in Monitoring NO2 Emission of Power Plants. Remote Sens. 2022, 14, 729. [Google Scholar] [CrossRef]
  13. Cai, K.; Zhang, Q.; Li, S.; Li, Y.; Ge, W. Spatial–Temporal variations in NO2 and PM2.5 over the Chengdu–Chongqing economic zone in china during 2005–2015 based on satellite remote sensing. Sensors 2018, 18, 3950. [Google Scholar] [CrossRef] [Green Version]
  14. Wei, J.; Liu, S.; Li, Z.; Liu, C.; Qin, K.; Liu, X.; Pinker, R.; Dickerson, R.; Lin, J.; Boersma, K.; et al. Ground-level NO2 surveillance from space across China for high resolution using interpretable spatiotemporally weighted artificial intelligence. Environ. Sci. Technol. 2022, 56, 9988–9998. [Google Scholar] [PubMed]
  15. Wei, J.; Li, Z.; Wang, J.; Li, C.; Gupta, P.; Cribb, M. Ground-level gaseous pollutants (NO2, SO2, and CO) in China: Daily seamless mapping and spatiotemporal variations. Atmos. Chem. Phys. 2023, 23, 1511–1532. [Google Scholar]
  16. Ghahremanloo, M.; Lops, Y.; Choi, Y.; Yeganeh, B. A Coupled Deep Learning Model for Estimating Surface NO2 Levels from Remote Sensing Data: 15-Year Study Over the Contiguous United States. J. Geophys. Res. Atmos. 2023, 128, e2022JD037010. [Google Scholar] [CrossRef]
  17. Li, L.; Wu, J. Spatiotemporal estimation of satellite-borne and ground-level NO2 using full residual deep networks. Remote Sens. Environ. 2021, 254, 112257. [Google Scholar] [CrossRef]
  18. Sayeed, A.; Choi, Y.; Jung, J.; Lops, Y.; Eslami, E.; Salman, A.K. A deep convolutional neural network model for improving WRF forecasts. arXiv 2020, arXiv:2008.06489. [Google Scholar]
  19. Ahmed, M.; Xiao, Z.; Shen, Y. Estimation of Ground PM2.5 Concentrations in Pakistan Using Convolutional Neural Network and Multi-Pollutant Satellite Images. Remote Sens. 2022, 14, 1735. [Google Scholar] [CrossRef]
  20. Ghahremanloo, M.; Lops, Y.; Choi, Y.; Yeganeh, B. Deep Learning Estimation of Daily Ground-Level NO2 Concentrations From Remote Sensing Data. J. Geophys. Res. Atmos. 2021, 126, e2021JD034925. [Google Scholar] [CrossRef]
  21. Li, A.; Zhang, J.; Xie, P.; Hu, Z.; Xu, J.; Mou, F.; Wu, F.; Liu, J.; Liu, W. Variation of temporal and spatial patterns of NO2 in Beijing using OMI and mobile DOAS. Sci. China Chem. 2015, 58, 1367–1376. [Google Scholar] [CrossRef]
  22. Du, Z.; Wang, Z.; Wu, S.; Zhang, F.; Liu, R. Geographically neural network weighted regression for the accurate estimation of spatial non-stationarity. Int. J. Geogr. Inf. Sci. 2020, 34, 1353–1377. [Google Scholar] [CrossRef]
  23. Du, Z.; Qi, J.; Wu, S.; Zhang, F.; Liu, R. A spatially weighted neural network based water quality assessment method for large-scale coastal areas. Environ. Sci. Technol. 2021, 55, 2553–2563. [Google Scholar] [CrossRef] [PubMed]
  24. Wu, S.; Wang, Z.; Du, Z.; Huang, B.; Zhang, F.; Liu, R. Geographically and temporally neural network weighted regression for modeling spatiotemporal non-stationary relationships. Int. J. Geogr. Inf. Sci. 2021, 35, 582–608. [Google Scholar] [CrossRef]
  25. He, Q.; Huang, B. Satellite-based high-resolution PM2.5 estimation over the Beijing-Tianjin-Hebei region of China using an improved geographically and temporally weighted regression model. Environ. Pollut. 2018, 236, 1027–1037. [Google Scholar] [CrossRef]
  26. Tian, W.; Li, W.; Song, H.; Yue, H. Analysis on the difference of regional high-quality development in Beijing-Tianjin-Hebei city cluster. Procedia Comput. Sci. 2022, 199, 1184–1191. [Google Scholar] [CrossRef]
  27. Wang, L.; Zhang, F.; Pilot, E.; Yu, J.; Nie, C.; Holdaway, J.; Yang, L.; Li, Y.; Wang, W.; Vardoulakis, S.; et al. Taking action on air pollution control in the Beijing-Tianjin-Hebei (BTH) region: Progress, challenges and opportunities. Int. J. Environ. Res. Public Health 2018, 15, 306. [Google Scholar]
  28. Yang, H.; Tao, W.; Liu, Y.; Qiu, M.; Liu, J.; Jiang, K.; Yi, K.; Xiao, Y.; Tao, S. The contribution of the Beijing, Tianjinand Hebeiregion’s iron and steel industry to local air pollution in winter. Environ. Pollut. 2018, 245, 1095–1106. [Google Scholar] [CrossRef]
  29. Zhang, Z.; Wang, W.; Cheng, M.; Liu, S.; Xu, J.; He, Y.; Meng, F. The contribution of residential coal combustion to PM2.5 pollution over China’s Beijing-Tianjin-Hebei region in winter. Atmos. Environ. 2017, 159, 147–161. [Google Scholar] [CrossRef]
  30. Wang, Y.; Yin, S.; Fang, X.; Chen, W. Interaction of economic agglomeration, energy conservation and emission reduction: Evidence from three major urban agglomerations in China. Energy 2022, 241, 122519. [Google Scholar] [CrossRef]
  31. GB 3095-2012; Ambient Air Quality Standards. China Environmental Science Press: Beijing, China, 2012.
  32. Veefkind, J.P.; Aben, I.; Mcmullan, K.; Förster, H.; Vries, J.D.; Otter, G.; Claas, J.; Eskes, H.J.; Haan, J.; Kleipool, Q. TROPOMI on the ESA Sentinel-5 Precursor: A GMES mission for global observations of the atmospheric composition for climate, air quality and ozone layer applications. Remote Sens. Environ. 2012, 120, 70–83. [Google Scholar] [CrossRef]
  33. Ialongo, I.; Virta, H.; Eskes, H.; Hovila, J.; Douros, J. Comparison of TROPOMI/Sentinel-5 Precursor NO2 observations with ground-based measurements in Helsinki. Atmos. Meas. Tech. 2020, 13, 205–218. [Google Scholar] [CrossRef] [Green Version]
  34. Wu, S.; Huang, B.; Wang, J.; He, L.; Du, Z. Spatiotemporal mapping and assessment of daily ground NO2 concentrations in China using high-resolution TROPOMI retrievals. Environ. Pollut. 2021, 273, 116456. [Google Scholar] [CrossRef]
  35. Van Geffen, J.H.G.M.; Eskes, H.J.; Boersma, K.F.; Maasakkers, J.D.; Veefkind, J.P. TROPOMI ATBD of the Total and Tropospheric NO2 Data Products. DLR Document. 2019. Available online: https://sentinels.copernicus.eu/documents/247904/0/Sentinel-5P-TROPOMI-ATBD-NO2-data-products/7a4fdde7-516e-48e7-bf44-da60c62b1e4d (accessed on 25 July 2023).
  36. Earth Science Data Systems. Goddard Earth Sciences Data and Information Services Center. 2020. Available online: https://www.earthdata.nasa.gov/esdis (accessed on 25 July 2023).
  37. Schneider, P.; Hamer, P.D.; Kylling, A.; Shetty, S.; Stebel, K. Spatiotemporal patterns in data availability of the sentinel-5p no2 product over urban areas in Norway. Remote Sens. 2021, 13, 2095. [Google Scholar] [CrossRef]
  38. Eroglu, O.; Kurum, M.; Boyd, D.; Gurbuz, A.C. High spatiotemporal resolution CYGNSS soil moisture estimates using artificial neural networks. Remote Sens. 2019, 11, 2272. [Google Scholar] [CrossRef] [Green Version]
  39. Wu, M.; Huang, W.; Niu, Z.; Wang, C.; Li, W.; Yu, B. Validation of synthetic daily Landsat NDVI time series data generated by the improved spatial and temporal data fusion approach. Inf. Fusion 2018, 40, 34–44. [Google Scholar] [CrossRef]
  40. Zhao, X.; Fioletov, V.; Alwarda, R.; Su, Y.; Griffin, D.; Weaver, D.; Strong, K.; Cede, A.; Hanisco, T.; Tiefengraber, M.; et al. Tropospheric and Surface Nitrogen Dioxide Changes in the Greater Toronto Area during the First Two Years of the COVID-19 Pandemic. Remote Sens. 2022, 14, 1625. [Google Scholar] [CrossRef]
  41. Zhang, Y.; Li, X.; Wang, A.; Bao, T.; Tian, S. Density and diversity of OpenStreetMap road networks in China. J. Urban Manag. 2015, 4, 135–146. [Google Scholar] [CrossRef] [Green Version]
  42. Yao, Y. Variation Characteristics of PM2.5 and PM10 Concentration and its Driving Factors in the Yangtze River Economic Belt. In Proceedings of the EGU General Assembly Conference Abstracts, Vienna, Austria, 23–27 May 2022. EGU22-6890. [Google Scholar]
  43. Liu, H.; Liu, H.; Cheng, Y. Illustrating the multi-stakeholder perceptions of environmental pollution based on big data: Lessons from China. Reg. Sustain. 2022, 3, 12–26. [Google Scholar] [CrossRef]
  44. Yu, B.; Lee, Y.; Sohn, K. Forecasting road traffic speeds by considering area-wide spatiotemporal dependencies based on a graph convolutional neural network (GCN). Transp. Res. Part C Emerg. Technol. 2020, 114, 189–204. [Google Scholar] [CrossRef]
  45. Chen, S.; Jin, M.; Ding, J. Hyperspectral remote sensing image classification based on dense residual three-dimensional convolutional neural network. Multimed. Tools Appl. 2021, 80, 1859–1882. [Google Scholar] [CrossRef]
  46. Shafi, M.A. K-means clustering analysis and multiple linear regression model on household income in Malaysia. Int. J. Artif. Intell. 2023, 12, 731–738. [Google Scholar]
  47. Chen, M.H.; Chen, Y.C.; Chou, T.Y.; Ning, F.S. PM2.5 Concentration Prediction Model: A CNN–RF Ensemble Framework. Int. J. Environ. Res. Public Health 2023, 20, 4077. [Google Scholar] [CrossRef] [PubMed]
  48. Zhao, Q.; Sun, T.; Zhang, T.; He, L.; Zhang, Z.; Shen, Z.; Xiong, S. High-Precision Potential Evapotranspiration Model Using GNSS Observation. Remote Sens. 2021, 13, 4848. [Google Scholar] [CrossRef]
  49. Li, H.; Lian, Y.; Renyang, Q.; Liu, L.; Qu, Z.; Lee, L.-C. Regional Atmospheric CO2 Response to Ecosystem CO2 Budgets in China. Remote Sens. 2023, 15, 3320. [Google Scholar] [CrossRef]
  50. Semlali, B.E.B.; El Amrani, C.; Ortiz, G.; Boubeta-Puig, J.; Garcia-de-Prado, A. SAT-CEP-monitor: An air quality monitoring software architecture combining complex event processing with satellite remote sensing. Comput. Electr. Eng. 2021, 93, 107257. [Google Scholar] [CrossRef]
  51. Rodríguez-Urrego, D.; Rodríguez-Urrego, L. Air quality during the COVID-19, PM2.5 analysis in the 50 most polluted capital cities in the world. Environ. Pollut. 2020, 266, 115042. [Google Scholar] [CrossRef] [PubMed]
  52. Boudriki Semlali, B.E.; El Amrani, C. Satellite Big Data Ingestion for Environmentally Sustainable Development. In Emerging Trends in ICT for Sustainable Development: The Proceedings of NICE 2020 International Conference; Springer International Publishing: Berlin/Heidelberg, Germany, 2021; pp. 269–284. [Google Scholar]
Remotesensing 15 03878 g001
Figure 1. Location and distribution of ground-based air quality testing stations in BTH. (a) shows the geographical location of the Beijing-Tianjin-Hebei region of China. (b) shows the population distribution in the study area. (c) shows the location of air quality monitoring stations and elevation data.
Figure 1. Location and distribution of ground-based air quality testing stations in BTH. (a) shows the geographical location of the Beijing-Tianjin-Hebei region of China. (b) shows the population distribution in the study area. (c) shows the location of air quality monitoring stations and elevation data.
Remotesensing 15 03878 g001
Remotesensing 15 03878 g002
Figure 2. Characteristic distribution of the main influencing factors of the inversion of NO2 at ground-level.
Figure 2. Characteristic distribution of the main influencing factors of the inversion of NO2 at ground-level.
Remotesensing 15 03878 g002
Remotesensing 15 03878 g003
Figure 3. GTNNWR model structure ( d i S denotes the spatial distance between individual image elements, while d i T denotes the difference between each image element).
Figure 3. GTNNWR model structure ( d i S denotes the spatial distance between individual image elements, while d i T denotes the difference between each image element).
Remotesensing 15 03878 g003
Remotesensing 15 03878 g004
Figure 4. The process of downscaling and prediction of impact factors is based on the GTNNWR model.
Figure 4. The process of downscaling and prediction of impact factors is based on the GTNNWR model.
Remotesensing 15 03878 g004
Remotesensing 15 03878 g005
Figure 5. Performance indicators for the four groups of models.
Figure 5. Performance indicators for the four groups of models.
Remotesensing 15 03878 g005
Remotesensing 15 03878 g006
Figure 6. Box diagram with error lines.
Figure 6. Box diagram with error lines.
Remotesensing 15 03878 g006
Remotesensing 15 03878 g007
Figure 7. Ground-level NO2 predictions and TROPOMI NO2 concentrations daily variation.
Figure 7. Ground-level NO2 predictions and TROPOMI NO2 concentrations daily variation.
Remotesensing 15 03878 g007
Remotesensing 15 03878 g008
Figure 8. Average ground-level NO2 concentration map for 2019–2022.
Figure 8. Average ground-level NO2 concentration map for 2019–2022.
Remotesensing 15 03878 g008
Remotesensing 15 03878 g009
Figure 9. Standard deviation of seasonal variation in near-surface NO2 and TROPOMI NO2 concentrations.
Figure 9. Standard deviation of seasonal variation in near-surface NO2 and TROPOMI NO2 concentrations.
Remotesensing 15 03878 g009
Remotesensing 15 03878 g010
Figure 10. Percentage stacked histograms of near-surface NO2 concentrations at different thresholds, per quarter, 2019–2022.
Figure 10. Percentage stacked histograms of near-surface NO2 concentrations at different thresholds, per quarter, 2019–2022.
Remotesensing 15 03878 g010
Remotesensing 15 03878 g011
Figure 11. Spatiotemporal distribution of ground-level NO2 concentration in Beijing–Tianjin–Hebei region during the 2019 New Year holidays (4–9 February).
Figure 11. Spatiotemporal distribution of ground-level NO2 concentration in Beijing–Tianjin–Hebei region during the 2019 New Year holidays (4–9 February).
Remotesensing 15 03878 g011
Remotesensing 15 03878 g012
Figure 12. Spatiotemporal distribution of ground-level NO2 concentration in Beijing–Tianjin–Hebei region during the 2020 New Year holidays (24–29 January).
Figure 12. Spatiotemporal distribution of ground-level NO2 concentration in Beijing–Tianjin–Hebei region during the 2020 New Year holidays (24–29 January).
Remotesensing 15 03878 g012
Remotesensing 15 03878 g013
Figure 13. Spatiotemporal distribution of ground-level NO2 concentrations in Beijing from 11 June to 22 June 2020.
Figure 13. Spatiotemporal distribution of ground-level NO2 concentrations in Beijing from 11 June to 22 June 2020.
Remotesensing 15 03878 g013
Remotesensing 15 03878 g014
Figure 14. Four models to deal with the predicted spatiotemporal distribution of ground-level NO2 concentration at 500 m resolution in Fengtai District on 15 June 2020.
Figure 14. Four models to deal with the predicted spatiotemporal distribution of ground-level NO2 concentration at 500 m resolution in Fengtai District on 15 June 2020.
Remotesensing 15 03878 g014
Remotesensing 15 03878 g015
Figure 15. Spatiotemporal distribution of daily high-resolution ground-level NO2 concentrations in Shijiazhuang, the capital of Hebei Province, from 2 January to 13 January 2021.
Figure 15. Spatiotemporal distribution of daily high-resolution ground-level NO2 concentrations in Shijiazhuang, the capital of Hebei Province, from 2 January to 13 January 2021.
Remotesensing 15 03878 g015
Remotesensing 15 03878 g016
Figure 16. Four models deal with the predicted spatiotemporal distribution of ground-level nitrogen dioxide concentrations at 500 m resolution in Gaocheng District on 2 January 2021.
Figure 16. Four models deal with the predicted spatiotemporal distribution of ground-level nitrogen dioxide concentrations at 500 m resolution in Gaocheng District on 2 January 2021.
Remotesensing 15 03878 g016
Remotesensing 15 03878 g017
Figure 17. Changes in the spatiotemporal distribution of ground-level NO2 concentrations in Beijing and Zhangjiakou during the 2022 Winter Olympic Games.
Figure 17. Changes in the spatiotemporal distribution of ground-level NO2 concentrations in Beijing and Zhangjiakou during the 2022 Winter Olympic Games.
Remotesensing 15 03878 g017
Table 1. Basic information sheet for Remote sensing data and Spatiotemporal ancillary data.
Table 1. Basic information sheet for Remote sensing data and Spatiotemporal ancillary data.
MaterialsTemporal
Resolution 		Spatial
Resolution		Time FrameData TypeData VolumeElemental Values
TROPOMIDay7 × 3.5 km
/5.5 × 3.5 km		1 January 2019 to
31 December 2022		TIFF2170 MBKey inversion elements
MODIS_NDVI16 days0.5 × 0.5 km1 January 2019 to
31 December 2022		TIFF1986 MBImproved spatial resolution
SRTM_DEM /0.09 × 0.09 km/TIFF276 MBAssociated with potential emission sources and dispersion
ERA-5_WDDay10 × 10 km1 January 2019 to
31 December 2022		TIFF28.9 MB
ERA-5_WS28.6 MB
ERA-5_TEMP28.8 MB
ERA-5_TP28.6 MB
ERA-5_SP28.6 MB
ERA-5_BLH28.9 MB
ERA-5_ET28.4 MB
ERA-5_RH28.7 MB
OSM_RN/0.5 × 0.5 km/TIFF6.42 MB
NASA_PDYear1 × 1 km 2019 to 2022TIFF350.60 MB
GDPYearCounty2019 to 2022XLSX/
IEUYearCounty2019 to 2022XLSX/
RRYearCounty2019 to 2022XLSX/
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Liu, C.; Wu, S.; Dai, Z.; Wang, Y.; Du, Z.; Liu, X.; Qiu, C. High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data. Remote Sens. 2023, 15, 3878. https://doi.org/10.3390/rs15153878

AMA Style

Liu C, Wu S, Dai Z, Wang Y, Du Z, Liu X, Qiu C. High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data. Remote Sensing. 2023; 15(15):3878. https://doi.org/10.3390/rs15153878

Chicago/Turabian Style

Liu, Chunhui, Sensen Wu, Zhen Dai, Yuanyuan Wang, Zhenhong Du, Xingyu Liu, and Chunxia Qiu. 2023. "High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data" Remote Sensing 15, no. 15: 3878. https://doi.org/10.3390/rs15153878

APA Style

Liu, C., Wu, S., Dai, Z., Wang, Y., Du, Z., Liu, X., & Qiu, C. (2023). High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data. Remote Sensing, 15(15), 3878. https://doi.org/10.3390/rs15153878

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop