Next Article in Journal
Spatiotemporal Interaction and Socioeconomic Determinants of Rural Energy Poverty in China
Next Article in Special Issue
Spatial Equity of PM2.5 Pollution Exposures in High-Density Metropolitan Areas Based on Remote Sensing, LBS and GIS Data: A Case Study in Wuhan, China
Previous Article in Journal
Night Work and Sustainable Working Life—A Prospective Trajectory Analysis of Swedish Twins
Previous Article in Special Issue
Evaluation of the Street Canyon Level Air Pollution Distribution Pattern in a Typical City Block in Baoding, China
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

High-Coverage Reconstruction of XCO2 Using Multisource Satellite Remote Sensing Data in Beijing–Tianjin–Hebei Region

School of Geosciences and Info-Physics, Central South University, Changsha 410017, China
*
Author to whom correspondence should be addressed.
Int. J. Environ. Res. Public Health 2022, 19(17), 10853; https://doi.org/10.3390/ijerph191710853
Submission received: 13 July 2022 / Revised: 26 August 2022 / Accepted: 28 August 2022 / Published: 31 August 2022

Abstract

:
The extreme climate caused by global warming has had a great impact on the earth’s ecology. As the main greenhouse gas, atmospheric CO2 concentration change and its spatial distribution are among the main uncertain factors in climate change assessment. Remote sensing satellites can obtain changes in CO2 concentration in the global atmosphere. However, some problems (e.g., low time resolution and incomplete coverage) caused by the satellite observation mode and clouds/aerosols still exist. By analyzing sources of atmospheric CO2 and various factors affecting the spatial distribution of CO2, this study used multisource satellite-based data and a random forest model to reconstruct the daily CO2 column concentration (XCO2) with full spatial coverage in the Beijing–Tianjin–Hebei region. Based on a matched data set from 1 January 2015, to 31 December 2019, the performance of the model is demonstrated by the determination coefficient (R2) = 0.96, root mean square error (RMSE) = 1.09 ppm, and mean absolute error (MAE) = 0.56 ppm. Meanwhile, the tenfold cross-validation (10-CV) results based on samples show R2 = 0.91, RMSE = 1.68 ppm, and MAE = 0.88 ppm, and the 10-CV results based on spatial location show R2 = 0.91, RMSE = 1.68 ppm, and MAE = 0.88 ppm. Finally, the spatially seamless mapping of daily XCO2 concentrations from 2015 to 2019 in the Beijing–Tianjin–Hebei region was conducted using the established model. The study of the spatial distribution of XCO2 concentration in the Beijing–Tianjin–Hebei region shows its spatial differentiation and seasonal variation characteristics. Moreover, daily XCO2 map has the potential to monitor regional carbon emissions and evaluate emission reduction.

1. Introduction

The global atmospheric CO2 concentration has increased dramatically since the industrial revolution. From ground observation, the atmospheric CO2 concentration has increased from 280 ppm at the beginning of the industrial revolution to 413.2 ppm in 2020 [1] and is also rising at a rate of nearly 2 ppm every year [2]. With the increase in atmospheric CO2 concentration, the global greenhouse effect is also increasing [3], and extreme weather and natural disasters are frequent [4]. Accurately estimating and effectively responding to the change in atmospheric CO2 concentration are major scientific issues to achieve the earth’s sustainable development [5]. Atmospheric CO2 column concentration (XCO2) is often used to represent atmospheric CO2 concentration [6]. Atmospheric XCO2 concentration can be measured in two ways: (1) Observing CO2 concentration based on ground stations: The total carbon column observing network (TCCON) established by the American Center for Atmospheric Research in 2004 can provide long-time and high-precision XCO2 concentration and effectively reveal the spatiotemporal variation trend of XCO2 concentration [7]. However, accurately representing the spatial distribution and temporal changes in XCO2 concentration by a few TCCON stations is difficult [8]. (2) Observing CO2 concentration based on remote sensing satellites: XCO2 concentration with high spatial–temporal resolution can be provided by remote sensing satellites [9], which have large-scale and long-time-series advantages. Currently, widely used CO2-monitoring satellites include GOSAT [10], OCO-2 [11], TanSat [12], and so on.
Although a remote sensing satellite has many advantages in monitoring XCO2 concentration, it inevitably has some problems. (1) The monitored scope is limited by the satellite observation mode [13]. (2) Satellites can be easily influenced by cloud cover and aerosols [14]. For example, the valid observation of the OCO-2 satellite only account for about 10% of all observation after quality control [15]. Currently, the coverage of atmospheric XCO2 monitored by satellites is low. This low coverage of XCO2 concentration has a negative influence on accurately estimating the carbon source and sink is difficult [16].
Researchers have developed various methods to reconstruct the high coverage of XCO2 data [17]. A high-accuracy surface modeling method was used to reconstruct the high coverage of OCO-2 XCO2 data [18]. Monthly XCO2 concentration can be obtained using the middle and low latitudes of the world. Additionally, the Goddard Earth Observing System Chemistry model has been used to obtain XCO2 concentration with continuous space–time coverage based on the atmospheric driving method [19,20]. However, the spatial resolution of the XCO2 concentration data obtained by the above method is generally above 0.5°, which cannot support the detailed study of regional carbon sources and sinks [21].
Machine learning algorithms can effectively deal with nonlinear complex system problems [22,23] and have been widely used in atmospheric XCO2 concentration estimation models. For example, the artificial neural network (ANN) method and variables (e.g., longitude and latitude, sea temperature, salinity level, and chlorophyll-a concentration) were used to model the XCO2 concentration over the ocean [24]. Siabi and Falahatkar modeled the 5 km seamless XCO2 concentration over Iran using the ANN method [25], OCO-2 XCO2, and eight environmental variables, including the normalized difference vegetation index (NDVI), net primary productivity (NPP), leaf area index, land surface temperature, wind direction, wind speed, air temperature, and land cover type.
Tarko and Usatyuk [26] showed that the temporal and spatial distributions of atmospheric CO2 concentration are affected by multiple factors, among which atmospheric meteorological conditions, vegetation carbon sink absorption, and carbon emissions from human activities are the most significant factors. Focusing on the aforementioned three types of variables is necessary to obtain more accurate XCO2 concentration [27].
Thus, this study aimed to obtain a high-coverage and high-spatial–temporal resolution atmospheric XCO2 concentration based on a machine learning model by integrating multisource remote sensing satellite data, considering meteorological factors, anthropogenic emissions, natural carbon sinks, and so on. Then, spatial–temporal changes in regional XCO2 concentration were analyzed. Simultaneously, the geographical locations of regional carbon sources and sinks are explored.

2. Data and Methods

2.1. Study Area and Data

2.1.1. Study Area

The study area was the Beijing–Tianjin–Hebei region in the North China Plain. The Beijing–Tianjin–Hebei region is centered in Beijing, the capital of China, including Tianjin, Shijiazhuang, Tangshan, Handan, Baoding, Cangzhou, Xingtai, Langfang, Chengde, Zhangjiakou, Hengshui, and Qinhuangdao, with a total area of 216,000 km2. The land use type map of the study area in 2014 is shown in Figure 1. The land use data are from the MODIS Land Cover (MCD12Q1) Product, which can be downloaded from https://lpdaac.usgs.gov/products/mcd12q1v006, accessed on 1 September 2021.
Li et al. [28] pointed out that population size has a great impact on carbon emissions. Beijing and Tianjin are the second and third largest cities in China, respectively, with developed industries and a large population [29]. The Beijing–Tianjin–Hebei region has become a typical high-carbon-emission region in China. Thus, reconstructing high-coverage XCO2 map in the Beijing–Tianjin–Hebei region is necessary.

2.1.2. Data

  • OCO-2 XCO2
Following the failure to launch the carbon olfactory satellite (OCO) in 2009, the National Aeronautics and Space Administration launched the OCO-2 satellite in 2014 to monitor the change in atmospheric XCO2 concentration [30]. The level 2 product published on the official website (https://search.earthdata.nasa.gov, accessed on 10 February 2021) was used in this study. The spatial resolution and the measured period of this product are 1.29 km × 2.25 km and 16 days, respectively [13]. The OCO-2 level 2 product includes three XCO2 products, namely, V7, V7r, and Lite_FP file products. For data applications, Lite_FP was selected in this study because it usually has the most effective data volume and relatively stable spatial coverage. Liang et al. [31] showed that OCO-2 XCO2 has a random error of ~1.8 ppm compared with ground-based TCCON data, which was sufficient to improve the estimation of the carbon source and carbon sink. Obviously measured gaps in XCO2 retrievals due to the influence of the observation orbit, cloud coverage, and aerosols (Figure 2).
2.
VIIRS S-NPP
The level of regional economic development is closely related to the population size and the industrial development level, which are closely related to the magnitude of anthropogenic carbon emissions [32]. The mean value of lighting data can effectively reflect the overall economic development level of the region and then effectively reflect the magnitude of anthropogenic carbon emissions [33].
The visible infrared imaging radiometer (VIIRS) night-light data used in this study is an extension of the MODIS series and is carried on the S-NPP satellite [34]. Global daily measurement of night-visible and near-infrared light can be provided by VIIRS, with spatial and time resolutions of 500 m and 1 day, respectively. Level-3 data were used in this study. This level of data has been geometrically and radiometrically corrected and can be downloaded from https://search.earthdata.nasa.gov, accessed on 21 October 2020.
Atmospheric CO2 is distributed in the form of aggregation and fog. The difference of XCO2 concentration within a certain range is small, while the night-light values of different grid points are very different. The point-to-point matching mode cannot effectively correspond to the XCO2 concentration. Therefore, the mean night-light value was adopted to represent the overall emissions in a region.
Firstly, the four-scene noctilucent data were spliced to obtain the complete lighting data in the Beijing–Tianjin–Hebei region. Then, the lighting map was resampled to 0.05° × 0.05°. The sum of lighting value in each city was counted and then divided by the region area of each city to obtain the average value. The formula is as follows:
DN mean = DN all Area city
where DN all is the sum of lighting value in a city; Area city is the area of the city, counted by the number of pixels; and DN mean represents the mean value of the city’s lighting data.
The same processing was performed on the light data for each day from 1 January 2015 to 31 December 2019. Examples of regional mean light values are shown in Figure 3.
3.
Natural carbon sink
As an important part of the carbon sink, the growth status and spatial coverage of surface vegetation have a very significant impact on atmospheric CO2 concentration [35,36]. In this study, the NDVI was used to characteristic the vegetation growth status and vegetation coverage. The calculation formula is shown in Equation (2). The NDVI data used in this study are from Terra’s MODIS sensor, with spatial and time resolutions of 500 m × 500 m and 16 days, respectively, downloaded from https://search.earthdata.nasa.gov, accessed on 10 October 2021.
NDVI = NIR Red NIR + Red
where, NIR and Red are the near-infrared band and red band surface reflectance, respectively.
4.
Meteorological factors
In this study, the impact of meteorological parameters on atmospheric CO2 concentration was also considered in addition to selecting the influencing factors of carbon sources and sinks of anthropogenic emissions and natural vegetation [24,25,37]. As one of the atmospheric chemical components, the temporal and spatial variations in CO2 concentration are greatly affected by meteorological factors. The meteorological factors affecting the concentration of atmospheric chemical components mainly include wind speed, temperature, and atmospheric stability. Such as, wind can dilute the atmospheric molecules. The temperature can reflect the stability of the atmosphere. In winter, the temperature is low, and the atmospheric structure is relatively stable, which is not conducive to the vertical diffusion of pollutants.
Five meteorological factors, including temperature (TEMP), relative humidity (RELH), pressure (PRES), wind speed (WS), and boundary layer height (BLH), were selected. Meteorological data from the European Meteorological Center reanalysis data set (ERA5) were used in this study. These are the fifth-generation ECMWF global climate data for atmospheric reanalysis. The spatial resolution of ERA5 data used in this study is 0.25° × 0.25° with a time resolution of 1 h, which can be downloaded from the ECMWF official website (https://cds.climate.copernicus.eu, accessed on 3 June 2021). All meteorological data were resampled to a resolution of 0.05° to fit the OCO-2 XCO2 data by a bilinear interpolation method in this study, and the meteorological data at 13:00 local time were selected to match the XCO2 data.
Table 1 shows the data sets used in this study.
5.
Time series variables
Relevant studies have shown that the atmospheric CO2 concentration has obvious seasonal variation characteristics. Keeling et al. [38] put forward the classical formula for the variation in atmospheric CO2 concentration over time:
y = A 1 sin 2 π t + A 2 cos 2 π t + A 3 sin 4 π t + A 4 cos 4 π t + A 5 + A 6 t
In the above formula, A 1 A 4 determines the periodic change law of atmospheric CO2 concentration with seasons, A 5 determines the background atmospheric CO2 concentration, and A 6 represents the interannual linear increment. t represents the time from the start date in years, and y represents the XCO2 concentration in ppm.
In this study, the seasonal variation characteristics of atmospheric CO2 concentration were also considered, and time series variables were added to the model to improve performance.

2.2. Methodology

2.2.1. Methodological Process

The flow chart of this study is shown in Figure 4, which mainly consists of three parts.
The first part was mainly to obtain the data and screen the model variables. By analyzing influence factors of atmospheric CO2 and the correlation between the variables and XCO2 concentration, the appropriate variables were selected to build the model.
The second part was mainly to build the model and verify the accuracy, including select the appropriate algorithm to build the model, and use statistical indicators to evaluate the model’s results. Finally, cross-validation was used to check whether the model overfitting or not.
The third part was mainly to compare and analyze the spatio-temporal differences between the XCO2 data set simulated by the model and the XCO2 data set monitored by the satellite.

2.2.2. Random Forest Model

The atmospheric system is a complex system with uncertainty. The number of atmospheric molecules (e.g., CO2) is influenced by different atmospheric conditions. For example, CO2 near the ground can be rapidly transported to the upper air and surrounding areas in summer due to intense atmospheric convection. In addition, some gases containing the element C, such as CO and CH4, will be converted into CO2 under the action of atmospheric chemistry for a long time. Therefore, certain limitations were observed in modeling and estimating CO2 concentration using the mechanism model. A neural network algorithm has a strong nonlinear and self-learning ability. However, it has some problems (e.g., slow convergence, serious overfitting, and so on) for the estimation of high-dimensional features and needs to continuously optimize the model parameters to achieve optimal results [39].
The random forest model selected in this study, which was first proposed by Cutler et al. [40]. It is an integrated algorithm, including multiple decision trees. The stochastic forest model has the following advantages:
  • The model has few adjustment parameters and does not require too much time.
  • The random selection of sample sets and split attributes can effectively reduce the overfitting of the model.
Through the continuous implementation and verification of the fitting results of the model, the random forest model established in this study mainly adjusts two important parameters: the maximum depth of the decision tree and the minimum number of samples of leaf nodes. The deeper the decision tree is, the longer time the model takes, but the model performance may be improved to some extent. In this research model, the maximum depth of the decision tree was set to 30. The larger the minimum number of leaf nodes, the smaller the branches of the decision tree, and it has a certain ability to resist overfitting. However, as the minimum number of leaf nodes increases to a certain extent, the accuracy of the decision tree will be difficult to guarantee. Through continuous experiments, the minimum number of samples of leaf nodes was set to 3 in the model.

2.2.3. Data Resampling and Matching Method

In the process of building the model, bilinear interpolation was used to uniformly sample with a spatial resolution of 0.05°. The matched data include XCO2 concentration, VIIRS S-NPP, NDVI, temperature, relative humidity, atmospheric pressure, wind speed, and boundary layer height. By matching the data from 1 January 2015 to 31 December 2019, 62,964 samples were obtained. Subsequently, the matched samples were used for model training and verification.

2.2.4. Model Validation Method

In this study, in addition to the direct fitting results of model, the model was also verified by tenfold cross-validation (10-CV), which can avoid the potential overfitting in the model. After randomly dividing 62,964 pieces of data into 10 subparts, 9 of them were used for training, and 1 was used for estimation. The estimated results were compared with the measurements, the process was repeated ten times until each piece of data was estimated, and finally, the estimated values of all data were obtained.
The determination coefficient (R2), root mean square error (RMSE), mean absolute error (MAE), and other statistical indicators were used to evaluate the accuracy of the model. The formulas of R2, RMSE, and ME are as follows:
R 2 = ( i = 1 n ( x i x ¯ ) ( y i y ¯ ) i = 1 n ( x i x ¯ ) 2 · i = 1 n ( y i y ¯ ) 2 ) 2
where x and y represent the satellite-based and model estimated XCO2, respectively, x ¯ represents the mean XCO2 value observed by the satellite, y ¯ represents the mean XCO2 value estimated by the model, and n represents the number of samples.
RMSE = i = 1 n ( X i X ˆ ) 2 n 1
where X i represents model fitting results, X ˆ represents the mean value of model fitting, and n represents the total number of samples.
MAE = 1 n i = 1 n | Y ˆ Y i |
where Y i represents model fitting results, Y ˆ represents the mean value of the model fitting results, and n represents the total number of samples.

3. Results

3.1. Descriptive Statistics

Before modeling, the above-mentioned various types of data were matched one by one according to longitude, dimension, and time, and a total of 69,512 pieces of data were matched. Statistical analysis of the 62,964 matched data was performed y to avoid problems in the data preprocessing process. The frequency histogram of each parameter is shown in Figure 5. The statistical results showed that the maximum, minimum, and average values of XCO2 concentration are 428.33, 354.54, and 405.64 ppm, respectively. The XCO2 concentration in the region is relatively high.
In addition, the study also conducted a correlation analysis between each variable parameter. The correlation analysis is shown in Table 2.
Through the calculation of the correlation coefficient, a certain correlation was noted between the XCO2 concentration and the selected modeling variables. Some variables have poor correlations, which may be attributed to the low spatial resolution of the data themselves. Data authenticity cannot be guaranteed when resampling to a finer spatial resolution. In addition, the correlation between temperature and NDVI is high, because the vegetation growth process is closely related to temperature [41]. The correlation between temperature and boundary layer height is high, mainly because temperature affects the stability of atmospheric molecules, resulting in certain changes in the boundary layer height.

3.2. Model Accuracy

By establishing random forest model for the XCO2 reconstruction by integrating multisource remote sensing data, the model accuracy statistics were computed, including the direct fitting results of the training model, the cross-validation results based on samples, and the spatial cross-validation results based on spatial locations (Figure 6). The longitude and latitude information of each group of data were recorded. During the spatial cross-validation, all matched data were randomly divided into ten equal parts according to longitude and latitude.
The direct fitting results obtained are R2 = 0.96, RMSE = 1.09 ppm, and MAE = 0.56 ppm; the 10-CV results based on samples are R2 = 0.91, RMSE = 1.68 ppm, and MAE = 0.88 ppm; and the 10-CV results based on spatial location are R2 = 0.91, RMSE = 1.68 ppm, and MAE = 0.88 ppm. The validation results show that the estimation results of the model in this study are relatively close to the XCO2 concentration monitored by the satellite. Simultaneously, according to the results of direct fitting and 10-CV based on samples, their R2 values are relatively close (0.96 vs. 0.91), which can be used to judge that the model does not have a serious overfitting phenomenon. In addition, according to the 10-CV results based on spatial location (R2 = 0.91), it can be found that the estimation ability of the model at different positions is also outstanding. Therefore, it can be used to estimate the XCO2 concentration in this region.
In addition, to conduct a more detailed analysis of the accuracy of the model, the current study computed the seasonal accuracy of the model for a total of 21 seasons from 1 January 2015 to 31 December 2019. The statistical results of model accuracy by season are shown in Table 3.
Due to the influence of cloud cover and aerosols, the number of effective XCO2 concentration obtained in each season is different. The performance of the model in spring is poor. The mean R2 of the direct fitting results in the 5 years is 0.84, and the mean value of the 10-CV results is 0.64. In the 4 years from 2016 to 2019, the model accuracy in spring is the lowest. The R2 values of the direct fitting results are 0.81, 0.82, 0.85, and 0.81, respectively, and the R2 of the 10-CV results of the sample are 0.57, 0.59, 0.65, and 0.60, respectively. The performance of the model is similar in summer, autumn, and winter. The mean R2 values of the direct fitting results of the model in summer, autumn, and winter in the 5 years from 2015 to 2019 are 0.88, 0.90, and 0.90, respectively, and the mean values of the sample 10-CV results are 0.73, 0.77, and 0.77, respectively. The statistical results of model accuracy by season will decline to a certain extent because the model is guaranteed to be globally optimal. In addition, the MAE of the 10-CV results of the model is within 1.5 ppm for the period between the winter of 2014 and the autumn of 2019, and the average value of MAE is 0.89 ppm. It can be seen that this model can estimate regional XCO2 concentrations with high performance.

3.3. Seasonal Maps

To better reflect the overall change in XCO2 concentration in the Beijing–Tianjin–Hebei region, the proposed model was used to estimate and map the XCO2 concentration in the whole region from 1 January 2015 to 31 December 2019. First of all, this study used the original OCO-2 satellite observation data to map the seasonal mean values of XCO2 concentration in Beijing, Tianjin, and Hebei. Since the winter data in 2019 are only in December, only the seasonal mean value results of OCO-2 XCO2 concentration in spring, summer, autumn, and winter from 2015 to 2018 are plotted (Figure 7).
Figure 7 shows that the coverage of the original OCO-2 XCO2 data in the Beijing–Tianjin–Hebei region is very low, and effective XCO2 monitoring cannot be conducted in many regions. Simultaneously, the return period of the OCO-2 satellite is 16 days, and XCO2 concentration data are only obtained once in 16 days. Due to the low coverage degree of original satellite observations, it is difficult to reflect the situation of the carbon source and carbon sink in the region. The XCO2 satellite observation results, as shown in Figure 7, show that the XCO2 concentration in the region has seasonal periodic change characteristics, and it is high in winter and spring and low in summer and autumn.
Secondly, the proposed model and multisource remote sensing satellite data were used to estimate the XCO2 concentration in the region and map the seasonal mean of the XCO2 concentration from 2015 to 2018 (Figure 8).
Figure 8 shows that compared with the XCO2 data directly observed by the OCO-2 satellite, the XCO2 reconstruction model established in this study can estimate the regional XCO2 concentration with the complete spatial distribution and can conduct more accurate studies on the regional carbon source and sink. In addition, the time resolution of the XCO2 concentration obtained in this study is 1 day, which can carry out more precise detection in the time dimension and effectively monitor the short-term anomaly of CO2 emissions.
Simultaneously, a quantitative analysis of the seasonal mean values of the XCO2 concentration monitored by the OCO-2 satellite and the XCO2 concentration estimated by the random forest model was conducted. Since the winter data in 2019 are only 1 month’s data, statistics were not computed here. The statistical results of other seasons are shown in Table 4.
Table 4 shows that little difference exists between the seasonal mean values of XCO2 concentration estimated by the random forest model and the seasonal mean values of XCO2 concentration observed by the OCO-2 satellite. The maximum difference in the mean value occurred in the spring of 2018, reaching 1.42 ppm, and the minimum difference in mean value occurred in the autumn of 2016, with a difference of only 0.03 ppm. Simultaneously, the seasonal median values of the two groups of data were calculated. Moreover, Table 4 shows that the maximum value of the median difference also appeared in the spring of 2018, reaching 1.23 ppm, and the minimum value of the difference appeared in the spring of 2017, with a difference of only 0.03 ppm. The statistical results also show that the XCO2 concentration was higher in spring and winter every year, followed by autumn, and smallest in summer, with periodic changes, and this is completely compatible with the findings of Yingying et al. and Bie et al. [6,42]. In this area, a dense population, high anthropogenic CO2 emissions, and major grain-producing areas in North China exist. However, severe seasonal changes in crops [43] and human activities make the regional seasonal change range in this area reach 9 ppm.

3.4. Long-Term Pattern of XCO2 Concentration

To make a more detail comparison between the XCO2 concentration monitored by the OCO-2 satellite and the XCO2 concentration estimated by the random forest model, the monthly mean values of the XCO2 concentration were also determined in this study. The results are shown in Figure 9.
Figure 9 shows that the monthly mean values of the XCO2 concentration estimated by this model are in good agreement with the XCO2 concentrations observed by the OCO-2 satellite. A large concentration deviation of the two groups of data generally occurs in the peak area of each cycle (i.e., around April and May of each year). By comparing the monthly mean values of the two groups of data, it can be found that the XCO2 concentration estimated by this model is consistent with the XCO2 concentration observed by the OCO-2 satellite. All monthly deviations are around 2 ppm, and the average absolute value of all deviations is 0.53 ppm. Simultaneously, the monthly mean concentration changes observed by the satellite and estimated by the model were compared in this study. The results are shown in Table 5.
Table 5 shows that the minimum monthly mean values of the XCO2 concentration observed by satellite and estimated by the model in the region appeared in August 2015, with concentrations of 393.73 and 394.10 ppm, respectively. The maximum monthly mean value of the XCO2 concentration observed by the satellite appeared in April 2019, with a concentration of 413.46 ppm. The maximum monthly mean value of XCO2 concentration estimated by the model appeared in March 2019, with a concentration of 413.00 ppm. The minimum difference in the monthly mean values of the XCO2 concentration observed by the satellite and estimated by the model was about 0.00 ppm, which occurred in October 2016, and the maximum difference occurred in November 2015, which was 1.67 ppm.

3.5. Spatial Distribution of Monthly XCO2 Concentration

To show the temporal and spatial changes in XCO2 concentration in this study, the monthly maps of the XCO2 concentration in 2015 and 2016 are drawn (Figure 10 and Figure 11).
Figure 10 and Figure 11 show that the XCO2 concentration in the Beijing–Tianjin–Hebei region shows fluctuations. Simultaneously, it has a rhythm: the XCO2 concentration is higher in spring and winter, followed by autumn, and the lowest in summer, which has a rhythm of seasonal change.
According to the monthly change in net primary productivity in the Beijing–Tianjin–Hebei region, Quanhong [44] pointed out that the vegetation in this region recovers in spring and enters the growth season. After summer, the water and heat conditions are suitable, the vegetation grows vigorously, the ecosystem productivity is the best, and the carbon fixation capacity is the strongest. In autumn, due to the maturity of agricultural crops, the ecological productivity of the whole region gradually decreases.
The high XCO2 concentration from March to May may be caused by the CO2, CH4, and other gases released by the decaying litter of forest vegetation. The low XCO2 concentration from July to September is mainly caused by a large amount of CO2 absorbed by forest vegetation during the growth process. The CO2 release from forest vegetation is greater than the absorption from March to June every year, while the CO2 absorption of forest vegetation from July to October is greater than the release. Therefore, in the process of the carbon cycle, the carbon source is the main feature in spring, and the carbon sink is the main feature in summer and autumn. In spring, plants begin to grow and absorb CO2 in the atmosphere but are offset by CO2 released into the atmosphere by plant decay. These plants do not completely decay between the colder late autumn and winter due to the low activity of humus organisms.
In addition, compared with the banded XCO2 concentration observed by the OCO-2 satellite, some carbon source and sink regions can be effectively reflected by the seamless XCO2 concentration monitored by the model of the Beijing–Tianjin–Hebei region. Figure 10 and Figure 11 show that some areas in Beijing, Tianjin, Tangshan, and Shijiazhuang are carbon source areas, and their monthly average XCO2 concentrations are significantly higher than those of the surrounding areas. The main reason may be that the above cities have large populations and large anthropogenic emissions. In some areas, such as Zhangjiakou and Chengde, the monthly XCO2 concentration is significantly lower than that of the surrounding areas. The main reason may be that the above two cities are underdeveloped, have a small residential population, and have relatively low industrial CO2 emissions.

4. Discussion

Many models have been established to estimate regional CO2 concentrations to better reveal the change in atmospheric CO2 concentration. Guo modeled the spatial distribution of XCO2 in five continents, considering temperature and vegetable cover [45]. However, the highest R2 was 0.75 in Eurasia, which is not sufficient to meet the requirements of high-performance CO2 concentration analysis. With the development of artificial intelligence, machine learning models have been used in XCO2 concentration monitoring. Saibi et al. [25] modeled the spatial distribution of XCO2 to assess the spatial distribution of CO2 concentration during the growing seasons in Iran, considering meteorological factors and natural carbon sink factors. However, the highest and lowest R2 values were 0.77 and 0.38 for April and September, respectively.
To better estimate CO2 concentration, more influencing factors and model performance need to be considered. The random forest model, based on the consideration of time series factors, meteorological factors, anthropogenic emission factors, natural carbon sink factors, and other factors affecting atmospheric CO2 concentration, can achieve higher R2 (0.96) and 10-CV R2 (0.91) than other models (0.77 and 0.75). This high-precision model can be used to estimate the XCO2 concentration, which can better reflect the changing trend and spatial distribution of atmospheric CO2 concentration in the study area.
In addition, the observation data of the OCO-2 satellite were mainly used to model and estimate the CO2 concentration in the Beijing–Tianjin–Hebei region in the study. However, due to the insufficient spatial resolution of the OCO-2 satellite, the spatial resolution of regional CO2 concentration obtained in this study is not sufficient to support the carbon emission monitoring of large-scale power plants and coal-fired plants. Thanks to the continuous development of remote sensing satellites, CO2 satellite monitoring data with higher spatial resolution and higher accuracy are being continuously retrieved. In the next work, more CO2 satellites, such as GF-5 and OCO-3 satellites, will be combined to retrieve higher-quality CO2 data to achieve the monitoring of plant carbon emissions.

5. Conclusions

CO2 is the most abundant greenhouse gas in the atmosphere, and its rising concentration has caused various climate changes and natural disasters, which have attracted extensive attention. Since the 1970s, the means of monitoring atmospheric CO2 have been continuously developed and updated. From station monitoring to satellite observation, from surface concentration to column concentration, the accurate estimation of atmospheric CO2 concentration and the accurate identification of regional and even global carbon source and sink locations require high-precision, high-spatial–temporal-resolution, and high-coverage atmospheric CO2 concentration monitoring data. In this study, multiple sources of atmospheric CO2 were considered, multisource remote sensing data were fused, and the random forest algorithm was used to build a high-coverage reconstruction model of XCO2 concentration, and temporal and spatial differences in the XCO2 concentration data set in the Beijing–Tianjin–Hebei region obtained from the model were analyzed. The main achievements are as follows:
  • Aiming at the problems of the low spatial coverage and insufficient temporal resolution of the XCO2 concentration observation data obtained by the OCO-2 monitoring satellite, this study developed a high-coverage reconstruction model for XCO2 concentration by integrating multisource remote sensing data. Simultaneously, the accuracy of the model was evaluated. The direct fitting results are R2 = 0.96, RMSE = 1.09 ppm, and MAE = 0.56 ppm; the 10-CV results based on samples are R2 = 0.91, RMSE = 1.68 ppm, and MAE = 0.88 ppm; and the 10-CV results based on spatial location are R2 = 0.91, RMSE = 1.68 ppm, and MAE = 0.88 ppm. The developed model has the potential to play an important role in the monitoring of atmospheric CO2 concentration.
  • Using the developed model, the high-coverage daily XCO2 concentration with a spatial resolution of 0.05° in the Beijing–Tianjin–Hebei region from 2015 to 2019 was outputted, and the monthly and seasonal means of XCO2 concentration were compared with those measured by the OCO-2 satellite. The study found that the XCO2 concentration has obvious fluctuation and rhythm. The XCO2 concentration is higher in spring and winter due to the decay of litter and human emissions. With the large amount of CO2 absorbed by green vegetation photosynthesis, the XCO2 concentration in summer is lower. In addition, in terms of the spatial XCO2 distribution concentration, some areas in Beijing, Tianjin, Tangshan, and Shijiazhuang are carbon source areas, and their monthly average XCO2 concentrations are significantly higher than those of the surrounding areas.
In general, this model has the potential to play a role in estimating the change in regional XCO2 concentration, monitoring the location of carbon sources and to help constrain city emissions on city scales.

Author Contributions

Conceptualization, J.H., W.W. and H.F.; methodology, J.H., Z.J., W.W. and H.F.; software, J.H., Z.J. and W.W.; validation, J.H., Z.J. and W.W.; formal analysis, J.H. and W.W.; investigation, J.H., Z.J. and W.W; resources, J.H., Z.J. and W.W.; data curation, J.H.; writing—original draft preparation, J.H. and W.W.; writing—review and editing, J.H. and W.W.; visualization, J.H., W.W., Z.J. and H.F.; supervision, W.W. and H.F.; project administration, W.W.; funding acquisition, W.W. All authors have read and agreed to the published version of the manuscript.

Funding

This study was supported by the National Natural Science Foundation of China (42071378 and 41901295), the Basic Science-Center Project of National Natural Science Foundation of China (72088101), the Natural Science Foundation of Hunan Province, China (2020JJ5708), and the Key Program of the National Natural Science Foundation of China (41930108).

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

OCO-2 XCO2 data supporting the reported results can be found and downloaded from website (https://search.earthdata.nasa.gov, accessed on 10 February 2021).

Acknowledgments

We are grateful to the NASA official website for providing data free of charge.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Friedlingstein, P.; O’Sullivan, M.; Jones, M.W.; Andrew, R.M.; Zaehle, S. Global Carbon Budget 2020. Glob. Carbon Budg. 2020, 12, 3269–3340. [Google Scholar] [CrossRef]
  2. Kappelle, M. WMO Statement on the State of the Global Climate in 2019; World Meteorological Organization: Geneva, Switzerland, 2020. [Google Scholar]
  3. Pachauri, R.K.; Meyer, L.; Groups, I.T. IPCC, Climate Change 2014: Synthesis Report; IPCC: Geneva, Switzerland, 2014; 151p. [Google Scholar]
  4. Dietz, S.; Bowen, A.; Dixon, C.; Gradwell, P. ‘Climate value at risk’ of global financial assets. Nat. Clim. Change 2016, 6, 676–679. [Google Scholar] [CrossRef]
  5. Gurney, K.R.; Law, R.M.; Denning, A.S.; Rayner, P.J.; Baker, D.; Bousquet, P.; Bruhwiler, L.; Chen, Y.H.; Ciais, P.; Fan, S.; et al. Towards robust regional estimates of CO2 sources and sinks using atmospheric transport models. Nature 2002, 415, 626–630. [Google Scholar] [CrossRef] [PubMed]
  6. Bie, N.; Lei, L.; Zeng, Z.; Cai, B.; Yang, S.; Yang, S.; He, Z.; He, Z.; Wu, C.; Nassar, R. Regional uncertainty of GOSAT XCO2 retrievals in China: Quantification and attribution. Atmos. Meas. Tech. 2018, 11, 1251–1272. [Google Scholar] [CrossRef]
  7. Jacobson, M.Z. Enhancement of Local Air Pollution by Urban CO_2 Domes. Environ. Sci. Technol. 2010, 44, 2497–2502. [Google Scholar] [CrossRef]
  8. O’Dell, C.W.; Connor, B.; Bösch, H.; O’Brien, D.; Frankenberg, C.; Castano, R.; Christi, M.; Eldering, D.; Fisher, B.; Gunson, M.; et al. The ACOS CO2 retrieval algorithm—Part 1: Description and validation against synthetic observations. Atmos. Meas. Tech. 2012, 5, 99–121. [Google Scholar] [CrossRef]
  9. Frankenberg, C.; O’Dell, C.; Berry, J.; Guanter, L.; Joiner, J.; Köhler, P.; Taylor, T.E. Prospects for chlorophyll fluorescence remote sensing from the Orbiting Carbon Observatory-2. Remote Sens. Environ. 2014, 147, 1–12. [Google Scholar] [CrossRef]
  10. Yokota, T.; Tsay, S.C.; Yokota, T.; Oguma, H.; Morino, I.; Ahn, M.H.; Higurashi, A.; Aoki, T.; Inoue, G. Test measurements by a BBM of the nadir-looking SWIR FTS aboard GOSAT to monitor CO2 column density from space. In Passive Optical Remote Sensing of the Atmosphere and Clouds IV; SPIE: Bellingham, WA, USA, 2004; Volume 5652, p. 182. [Google Scholar]
  11. Crisp, D. Measuring atmospheric carbon dioxide from space with the Orbiting Carbon Observatory-2 (OCO-2). In Proceedings of the SPIE Optical Engineering + Applications, Singapore, 5–8 November 2018. [Google Scholar]
  12. Chen, W.; Zhang, Y.; Yin, Z.; Zheng, Y.; Yan, C.; Yang, Z.; Liu, Y. The TanSat mission: Global CO2 observation and monitoring. In Proceedings of the 63rd IAC (International Astronautical Congress), Naples, Italy, 1–5 October 2012. [Google Scholar]
  13. Hammerling, D.M.; Michalak, A.M.; Kawa, S.R. Mapping of CO2 at high spatiotemporal resolution using satellite observations: Global distributions from OCO-2. J. Geophys. Res. Atmos. 2012, 117, D06306. [Google Scholar] [CrossRef]
  14. Mao, J.; Kawa, S.R. Sensitivity studies for space-based measurement of atmospheric total column carbon dioxide by reflected sunlight. Appl. Opt. 2004, 43, 914–927. [Google Scholar] [CrossRef]
  15. Liang, A.; Gong, W.; Han, G.; Xiang, C. Comparison of Satellite-Observed XCO2 from GOSAT, OCO-2, and Ground-Based TCCON. Remote Sens. 2017, 9, 1033. [Google Scholar] [CrossRef] [Green Version]
  16. Chen, L.; Zhang, Y.; Zou, M.; Xu, Q.; Li, L.; Li, X.; Tao, J. Overview of atmospheric CO2 remote sensing from space. J. Remote Sens. 2015, 19, 1–11. [Google Scholar]
  17. Pei, Z.; Han, G.; Ma, X.; Shi, T.; Gong, W. A Method for Estimating the Background Column Concentration of CO2 Using the Lagrangian Approach. IEEE Trans. Geosci. Remote Sens. 2022, 60, 1–12. [Google Scholar] [CrossRef]
  18. Zhang, L.; Zhao, M.; Zhao, N.; Yue, T. Modeling the Spatial Distribution of XCO_2 with High Accuracy Based on OCO-2’s Observations. J. Geo-Inf. Sci. 2018, 20, 1316–1326. [Google Scholar]
  19. Bey, I.; Jacob, D.J.; Yantosca, R.M.; Logan, J.A.; Field, B.D.; Fiore, A.M.; Li, Q.; Liu, H.Y.; Mickley, L.J.; Schultz, M.G. Global modeling of tropospheric chemistry with assimilated meteorology: Model description and evaluation. J. Geophys. Res. Atmos. 2001, 106, 23073–23095. [Google Scholar] [CrossRef]
  20. Baker, D.F.; Law, R.M.; Gurney, K.R.; Rayner, P.; Peylin, P.; Denning, A.S.; Bousquet, P.; Bruhwiler, L.; Chen, Y.; Ciais, P.; et al. TransCom 3 inversion intercomparison: Impact of transport model errors on the interannual variability of regional CO2 fluxes, 1988–2003. Glob. Biogeochem. Cycles 2006, 20, GB1002. [Google Scholar] [CrossRef]
  21. Ahmadov, R.; Gerbig, C.; Kretschmer, R.; Rner, S.K.; Denbeck, C.R.; Bousquet, P.; Ramonet, M. Comparing high resolution WRF-VPRM simulations and two global CO2 transport models with coastal tower measurements of CO2. Biogeosciences 2009, 6, 807–817. [Google Scholar] [CrossRef]
  22. Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. TensorFlow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA, 2–4 November 2016. [Google Scholar]
  23. Luo, B.; Yang, J.; Song, S.; Shi, S.; Gong, W.; Wang, A.; Du, L. Target Classification of Similar Spatial Characteristics in Complex Urban Areas by Using Multispectral LiDAR. Remote Sens. 2022, 14, 238. [Google Scholar] [CrossRef]
  24. Zeng, J. Reconstructed surface ocean CO2 in 1990–2011 with link to a feed-forward neural network model in NetCDF format. PANGAEA 2014. [Google Scholar] [CrossRef]
  25. Siabi, Z.; Falahatkar, S.; Alavi, S.J. Spatial distribution of XCO2 using OCO-2 data in growing seasons. J. Environ. Manag. 2019, 244, 110–118. [Google Scholar] [CrossRef]
  26. Tarko, A.M.; Usatyuk, V.V. Simulation of the Global Biogeochemical Carbon Cycle with Account for Its Seasonal Dynamics and Analysis of Variations in Atmospheric CO_2 Concentrations. Dokl. Earth Sci. 2013, 448, 258–261. [Google Scholar] [CrossRef]
  27. Zhang, J. Multi-source remote sensing data fusion: Status and trends. Int. J. Image Data Fusion 2010, 1, 5–24. [Google Scholar] [CrossRef]
  28. Li, H.; Mu, H.; Zhang, M.; Nan, L. Analysis on influence factors of China’s CO2 emissions based on Path–STIRPAT model. Energy Policy 2011, 39, 6906–6911. [Google Scholar] [CrossRef]
  29. Xu, W.; Wang, W.; Wang, N.; Chen, B. A New Algorithm for Himawari-8 Aerosol Optical Depth Retrieval by Integrating Regional PM2.5 Concentrations. IEEE Trans. Geosci. Remote Sens. 2022, 60, 1–11. [Google Scholar] [CrossRef]
  30. Frankenberg, C.; Pollock, R.; Lee, R.A.M.; Rosenberg, R.; Blavier, J.F.; Crisp, D.; O’Dell, C.W.; Osterman, G.B.; Roehl, C.; Wennberg, P.O.; et al. The Orbiting Carbon Observatory (OCO-2): Spectrometer performance evaluation using pre-launch direct sun measurements. Atmos. Meas. Tech. 2015, 8, 301–313. [Google Scholar] [CrossRef]
  31. Liang, A.; Wei, G.; Ge, H. OCO-2 XCO2 validation using TCCON data. In Proceedings of the Geoscience & Remote Sensing Symposium, Beijing, China, 10–15 July 2016. [Google Scholar]
  32. Raupach, M.R.; Rayner, P.J.; Paget, M. Regional variations in spatial structure of nightlights, population density and fossil-fuel CO2 emissions. Energy Policy 2010, 38, 4756–4764. [Google Scholar] [CrossRef]
  33. Chen, J.; Gao, M.; Cheng, S.; Hou, W.; Shan, Y. County-level CO2 emissions and sequestration in China during 1997–2017. Sci. Data 2020, 7, 1–12. [Google Scholar] [CrossRef]
  34. Meng, F.; Cao, C.; Shao, X. Spatio-temporal variability of Suomi-NPP VIIRS-derived aerosol optical thickness over China in 2013. Remote Sens. Environ. 2015, 163, 61–69. [Google Scholar] [CrossRef]
  35. Yan, Q.; Zhang, C.; Wang, D.; Tian, P.; Wu, Q. Comparison of atmospheric CO2observed by GOSAT and two ground stations in China. Int. J. Remote Sens. 2013, 34, 3938–3946. [Google Scholar]
  36. He, Z.; Zeng, Z.C.; Lei, L.; Bie, N.; Yang, S. A Data-Driven Assessment of Biosphere-Atmosphere Interaction Impact on Seasonal Cycle Patterns of XCO2 Using GOSAT and MODIS Observations. Remote Sens. 2017, 9, 251. [Google Scholar]
  37. Liu, B.; Ma, X.; Ma, Y.; Li, H.; Jin, S.; Fan, R.; Gong, W. The relationship between atmospheric boundary layer and temperature inversion layer and their aerosol capture capabilities. Atmos. Res. 2022, 271, 106121. [Google Scholar] [CrossRef]
  38. Keeling, C.D.; Bacastow, R.B.; Bainbridge, A.E.; Ekdahl, C.A., Jr.; Guenther, P.R.; Waterman, L.S.; Chin, J.F. Atmospheric carbon dioxide variations at Mauna Loa Observatory, Hawaii. Tellus 1976, 28, 538–551. [Google Scholar]
  39. Tu, B. Advantages and Disadvantages of Using Artificial Neural Networks Versus Logistic Regression for Predicting. J. Clin. Epidemiol. 1996, 49, 1225–1231. [Google Scholar] [CrossRef]
  40. Cutler, A.; Cutler, D.R.; Stevens, J.R. Random Forests. Mach. Learn. 2004, 45, 157–176. [Google Scholar]
  41. Ichii, K.; Kawabata, A.; Yamaguchi, Y. Global correlation analysis for NDVI and climatic variables and NDVI trends: 1982–1990. Int. J. Remote Sens. 2002, 23, 3873–3878. [Google Scholar] [CrossRef]
  42. Jing, Y.; Shi, J.; Wang, T.; Sussmann, R. Mapping Global Atmospheric CO2 Concentration at High Spatiotemporal Resolution. Atmosphere 2014, 5, 870–888. [Google Scholar]
  43. Lei, L.P.; Guan, X.H.; Zeng, Z.C.; Zhang, B.; Ru, F.; Bu, R. A comparison of atmospheric CO2 concentration GOSAT-based observations and model simulations. Sci. China Earth Sci. 2014, 57, 1393–1402. [Google Scholar] [CrossRef]
  44. Xu, Q. Estimation of ecosystem productivity and analysis of spatial-temporal pattern in Beijing Tianjin Hebei region. Geogr. Geogr. Inf. Sci. 2019, 35, 10. [Google Scholar]
  45. Guo, M.; Wang, X.; Li, J.; Yi, K.; Zhong, G.; Tani, H. Assessment of Global Carbon Dioxide Concentration Using MODIS and GOSAT Data. Sensors 2012, 12, 16368–16389. [Google Scholar] [CrossRef] [Green Version]
Figure 1. Land use types in the Beijing–Tianjin–Hebei (BTH) region in China.
Figure 1. Land use types in the Beijing–Tianjin–Hebei (BTH) region in China.
Ijerph 19 10853 g001
Figure 2. Average monthly data of OCO-2 XCO L2 Lite_FP in China: (a) January 2015, (b) January 2016, (c) January 2017, and (d) January 2018.
Figure 2. Average monthly data of OCO-2 XCO L2 Lite_FP in China: (a) January 2015, (b) January 2016, (c) January 2017, and (d) January 2018.
Ijerph 19 10853 g002
Figure 3. Regional mean value results of VIIRS S-NPP luminous data. The left and right figures show the regional mean value results of luminous data on (a) 1 January 2015 and (b) 1 January 2016, respectively.
Figure 3. Regional mean value results of VIIRS S-NPP luminous data. The left and right figures show the regional mean value results of luminous data on (a) 1 January 2015 and (b) 1 January 2016, respectively.
Ijerph 19 10853 g003
Figure 4. Flow chart of this study.
Figure 4. Flow chart of this study.
Ijerph 19 10853 g004
Figure 5. The frequency histogram of parameters in XCO2 concentration modeling (n = 62,964). (ai) represent CO2 column concentration, digital number, temperature, relative humidity, pressure, vertical wind speed, horizontal wind speed, boundary layer height, and normalized vegetation index, respectively.
Figure 5. The frequency histogram of parameters in XCO2 concentration modeling (n = 62,964). (ai) represent CO2 column concentration, digital number, temperature, relative humidity, pressure, vertical wind speed, horizontal wind speed, boundary layer height, and normalized vegetation index, respectively.
Ijerph 19 10853 g005
Figure 6. Scatter density plot of (a) direct fitting, (b) sample-based cross-validation, and (c) spatial cross-validation.
Figure 6. Scatter density plot of (a) direct fitting, (b) sample-based cross-validation, and (c) spatial cross-validation.
Ijerph 19 10853 g006
Figure 7. Seasonal means of OCO-2 XCO2 L2 Lite_FP data during 20150301–20190228, all resampled to 0.05° × 0.05° spatial resolution: (ad) 2015, (eh) 2016, (il) 2017, and (mp) 2018 in spring, summer, autumn, and winter, respectively.
Figure 7. Seasonal means of OCO-2 XCO2 L2 Lite_FP data during 20150301–20190228, all resampled to 0.05° × 0.05° spatial resolution: (ad) 2015, (eh) 2016, (il) 2017, and (mp) 2018 in spring, summer, autumn, and winter, respectively.
Ijerph 19 10853 g007
Figure 8. Seasonal XCO2 in the Beijing–Tianjin–Hebei region estimated by the random forest model from March 1, 2015 to February 28, 2019: (ad) 2015, (eh) 2016, (il) 2017, and (mp) 2018 in spring, summer, autumn, and winter, respectively.
Figure 8. Seasonal XCO2 in the Beijing–Tianjin–Hebei region estimated by the random forest model from March 1, 2015 to February 28, 2019: (ad) 2015, (eh) 2016, (il) 2017, and (mp) 2018 in spring, summer, autumn, and winter, respectively.
Ijerph 19 10853 g008
Figure 9. Comparison between monthly XCO2 concentrations from the OCO-2 satellite (red line) and the random forest model (blue line), as well as the deviation value (green line), where the deviation value increased by 400 ppm (yellow dotted line).
Figure 9. Comparison between monthly XCO2 concentrations from the OCO-2 satellite (red line) and the random forest model (blue line), as well as the deviation value (green line), where the deviation value increased by 400 ppm (yellow dotted line).
Ijerph 19 10853 g009
Figure 10. Monthly average XCO2 concentrations in the Beijing–Tianjin–Hebei region from January 2015 to December 2015. ZJK, CD, BJ, TJ, TS, and SJZ represent Zhangjiakou, Chengde, Beijing, Tianjin, Tangshan, and Shijiazhuang, respectively. (al) represent January to December respectively.
Figure 10. Monthly average XCO2 concentrations in the Beijing–Tianjin–Hebei region from January 2015 to December 2015. ZJK, CD, BJ, TJ, TS, and SJZ represent Zhangjiakou, Chengde, Beijing, Tianjin, Tangshan, and Shijiazhuang, respectively. (al) represent January to December respectively.
Ijerph 19 10853 g010
Figure 11. Monthly average XCO2 concentrations in the Beijing–Tianjin–Hebei region from January 2016 to December 2016. ZJK, CD, BJ, TJ, TS, and SJZ represent Zhangjiakou, Chengde, Beijing, Tianjin, Tangshan, and Shijiazhuang, respectively. (al) represent January to December respectively.
Figure 11. Monthly average XCO2 concentrations in the Beijing–Tianjin–Hebei region from January 2016 to December 2016. ZJK, CD, BJ, TJ, TS, and SJZ represent Zhangjiakou, Chengde, Beijing, Tianjin, Tangshan, and Shijiazhuang, respectively. (al) represent January to December respectively.
Ijerph 19 10853 g011
Table 1. Data sets used in this study.
Table 1. Data sets used in this study.
DataVariableUnitTime ResolutionSpatial ResolutionSource
XCO2XCO2ppm1 day2.25 km × 1.29 kmOCO-2
Lighting dataDNUnitless1 day500 mS-NPP
Carbon sinkNDVIUnitless16 days500 mMODIS
RELH%1 h0.25°
Meteorological dataTEMPK1 h0.25°ERA5
WSm/s1 h0.25°
PRESKpa1 h0.25°
BLHkm1 h0.25°
Table 2. Pearson correlation coefficient matrix of XCO2 concentration reconstruction model with matching data set variables.
Table 2. Pearson correlation coefficient matrix of XCO2 concentration reconstruction model with matching data set variables.
TimeXCO2TEMPRELHPRESuwindvwindBLHNDVIDN
Time1.000.620.07−0.10−0.020.030.010.070.070.00
XCO2 1.00−0.21−0.300.160.100.03−0.01−0.260.08
TEMP 1.000.050.22−0.390.290.420.650.08
RELH 1.000.04−0.240.18−0.490.130.00
PRES 1.00−0.330.08−0.100.110.37
uwind 1.00−0.170.19−0.30−0.11
vwind 1.00−0.260.160.01
BLH 1.000.24−0.01
NDVI 1.000.05
DN 1.00
Table 3. Statistical results of seasonal accuracy of the model from 1 January 2015 to 31 December 2019 (21 seasons, n = 62,964 is the total number of samples, and the evaluation indicators are R2, MAE, and RMSE).
Table 3. Statistical results of seasonal accuracy of the model from 1 January 2015 to 31 December 2019 (21 seasons, n = 62,964 is the total number of samples, and the evaluation indicators are R2, MAE, and RMSE).
SeasonDirect Fitting Results10-CV Results Based on SamplesNumber
R2MAE (ppm)RMSE (ppm)R2MAE (ppm)RMSE (ppm)
2014 Winter0.890.430.870.770.651.252078
2015 Spring0.910.490.910.790.731.353603
2015 Summer0.890.831.430.731.272.142913
2015 Autumn0.880.611.250.700.941.933342
2015 Winter0.920.531.090.810.821.666015
2016 Spring0.810.530.940.570.811.372586
2016 Summer0.870.871.610.711.302.372318
2016 Autumn0.930.571.170.820.871.763200
2016 Winter0.930.501.000.820.781.573703
2017 Spring0.820.551.040.590.831.513158
2017 Summer0.910.721.220.791.111.821700
2017 Autumn0.890.611.230.720.931.851702
2017 Winter0.860.471.070.680.701.564971
2018 Spring0.850.450.820.650.681.222789
2018 Summer0.850.981.640.661.482.432509
2018 Autumn0.900.510.990.780.761.443894
2018 Winter0.900.440.840.740.661.302899
2019 Spring0.810.511.060.600.751.463147
2019 Summer0.900.861.510.761.292.202020
2019 Autumn0.920.430.780.830.641.153493
2019 Winter0.920.510.940.820.761.38924
Table 4. Statistical results of the seasonal mean values of the XCO2 concentration monitored by the OCO-2 satellite and the XCO2 concentration estimated by the random forest model.
Table 4. Statistical results of the seasonal mean values of the XCO2 concentration monitored by the OCO-2 satellite and the XCO2 concentration estimated by the random forest model.
SeasonMonitored by SatelliteEstimated by ModelBias
MeanMedianStandard DeviationMeanMedianStandard DeviationMeanMedianStandard Deviation
201501402.59402.772.85402.40402.660.750.180.112.10
201502395.50395.554.10395.39395.610.830.11−0.063.27
201503398.74398.733.30398.59399.001.670.15−0.271.63
201504404.13404.193.10403.77404.011.860.360.181.24
201601406.02406.132.00405.42405.550.540.600.581.47
201602398.50398.414.44399.19399.290.92−0.69−0.883.52
201603403.15403.493.85403.18402.921.36−0.030.572.49
201604407.43407.523.77407.66407.801.91−0.23−0.281.86
201701408.68408.582.25408.24408.550.860.440.031.39
201702404.18404.473.84404.33404.430.94−0.150.042.91
201703406.24406.683.05406.70407.171.17−0.46−0.491.89
201704408.77408.842.71408.75409.231.520.02−0.391.19
201801411.09410.992.01409.67409.760.851.421.231.16
201802404.09404.064.18403.71403.690.460.390.373.72
201803407.22407.353.00407.53407.861.13−0.31−0.511.87
201804411.05411.082.59411.35411.911.29−0.30−0.831.30
201901412.96412.862.10411.94411.940.541.020.921.56
201902406.09406.264.43406.33406.460.86−0.24−0.203.57
201903409.63409.722.73409.35409.891.160.27−0.171.58
Table 5. The monthly mean concentration changes observed by the satellite and estimated by the model.
Table 5. The monthly mean concentration changes observed by the satellite and estimated by the model.
Observed by the OCO-2 satelliteMinimum 393.73201508
Maximum 413.46201904
Bias19.73
Estimated by the random forest modelMinimum 394.10201508
Maximum 413.00201903
Bias18.94
BiasMinimum 0.00201610
Maximum 1.67201511
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Share and Cite

MDPI and ACS Style

Wang, W.; He, J.; Feng, H.; Jin, Z. High-Coverage Reconstruction of XCO2 Using Multisource Satellite Remote Sensing Data in Beijing–Tianjin–Hebei Region. Int. J. Environ. Res. Public Health 2022, 19, 10853. https://doi.org/10.3390/ijerph191710853

AMA Style

Wang W, He J, Feng H, Jin Z. High-Coverage Reconstruction of XCO2 Using Multisource Satellite Remote Sensing Data in Beijing–Tianjin–Hebei Region. International Journal of Environmental Research and Public Health. 2022; 19(17):10853. https://doi.org/10.3390/ijerph191710853

Chicago/Turabian Style

Wang, Wei, Junchen He, Huihui Feng, and Zhili Jin. 2022. "High-Coverage Reconstruction of XCO2 Using Multisource Satellite Remote Sensing Data in Beijing–Tianjin–Hebei Region" International Journal of Environmental Research and Public Health 19, no. 17: 10853. https://doi.org/10.3390/ijerph191710853

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