Machine Learning Model-Based Estimation of XCO2 with High Spatiotemporal Resolution in China

As the most abundant greenhouse gas in the atmosphere, CO2 has a significant impact on climate change. Therefore, the determination of the temporal and spatial distribution of CO2 is of great significance in climate research. However, existing CO2 monitoring methods have great limitations, and it is difficult to obtain large-scale monitoring data with high spatial resolution, thus limiting the effective monitoring of carbon sources and sinks. To obtain complete Chinese daily-scale CO2 information, we used OCO-2 XCO2 data, Carbon Tracker XCO2 data, and multivariate geographic data to build a model training data set, which was then combined with various machine learning models including Random Forest, Extreme Random Forest, XGBoost, LightGBM, and CatBoost. The results indicated that the Random Forest model presented the best performance, with a cross-validation R2 of 0.878 and RMSE of 1.123 ppm. According to the final estimation results, in terms of spatial distribution, the highest multi-year average RF XCO2 value was in East China (406.94 ± 0.65 ppm), while the lowest was in Northwest China (405.56 ± 1.43 ppm). In terms of time, from 2016 to 2018, the annual XCO2 in China continued to increase, but the growth rate showed a downward trend. In terms of seasonal effects, the multi-year average XCO2 was highest in spring (407.76 ± 1.72 ppm) and lowest in summer (403.15 ± 3.36ppm). Compared with the Carbon-Tracker data, the XCO2 data set constructed in this study showed more detailed spatial changes, thus, can be effectively used to identify potentially important carbon sources and sinks.

[1]  Tongwen Li,et al.  Deriving gapless CO2 concentrations using a geographically weighted neural network: China, 2014-2020 , 2022, Int. J. Appl. Earth Obs. Geoinformation.

[2]  W. Wang,et al.  High-Coverage Reconstruction of XCO2 Using Multisource Satellite Remote Sensing Data in Beijing–Tianjin–Hebei Region , 2022, International journal of environmental research and public health.

[3]  Yuzhou Luo,et al.  Deriving Full‐Coverage and Fine‐Scale XCO2 Across China Based on OCO‐2 Satellite Retrievals and CarbonTracker Output , 2022, Geophysical Research Letters.

[4]  Linlin Zhao,et al.  High-spatiotemporal resolution mapping of spatiotemporally continuous atmospheric CO2 concentrations over the global continent , 2022, Int. J. Appl. Earth Obs. Geoinformation.

[5]  S. Zang,et al.  Spatial and Temporal Variations of Atmospheric CO2 Concentration in China and Its Influencing Factors , 2020, Atmosphere.

[6]  T. Machida,et al.  Assessment of spatio-temporal distribution of CO2 over greater Asia using the WRF–CO2 model , 2020, Journal of Earth System Science.

[7]  Bing Zhang,et al.  Specific patterns of XCO2 observed by GOSAT during 2009–2016 and assessed with model simulations over China , 2020, Science China Earth Sciences.

[8]  O. Hasekamp,et al.  XCO2 observations using satellite measurements with moderate spectral resolution: investigation using GOSAT and OCO-2 measurements , 2019, Atmospheric Measurement Techniques.

[9]  Samereh Falahatkar,et al.  Spatial distribution of XCO2 using OCO-2 data in growing seasons. , 2019, Journal of environmental management.

[10]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[11]  Samereh Falahatkar,et al.  Spatial and temporal distribution of carbon dioxide gas using GOSAT data over IRAN , 2017, Environmental Monitoring and Assessment.

[12]  Ming-wei Zhao,et al.  Fusion of multi-source near-surface CO2 concentration data based on high accuracy surface modeling , 2017 .

[13]  David Crisp,et al.  Quantifying CO2 Emissions From Individual Power Plants From Space , 2017 .

[14]  Wei Gong,et al.  Comparison of Satellite-Observed XCO2 from GOSAT, OCO-2, and Ground-Based TCCON , 2017, Remote. Sens..

[15]  Wenfeng Zhan,et al.  Variations in satellite-derived carbon dioxide over different regions of China from 2003 to 2011 , 2017 .

[16]  Andrew J. Tatem,et al.  WorldPop, open data for spatial demography , 2017, Scientific Data.

[17]  David Crisp,et al.  Comparisons of the Orbiting Carbon Observatory-2 (OCO-2) X CO 2 measurements with TCCON , 2016 .

[18]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[19]  Noel Cressie,et al.  Spatio-Temporal Data Fusion for Very Large Remote Sensing Datasets , 2014, Technometrics.

[20]  Bing Zhang,et al.  Incorporating temporal variability to improve geostatistical analysis of satellite-observed CO2 in China , 2013 .

[21]  Jing Li,et al.  Assessment of Global Carbon Dioxide Concentration Using MODIS and GOSAT Data , 2012, Sensors.

[22]  Dorit Hammerling,et al.  Mapping of CO2 at high spatiotemporal resolution using satellite observations: Global distributions from OCO‐2 , 2012 .

[23]  Liping Yang,et al.  SRTM DEM and its application advances , 2011 .

[24]  Sander Houweling,et al.  Evaluation of various observing systems for the global monitoring of CO2 surface fluxes , 2010 .

[25]  Ilse Aben,et al.  Retrievals of atmospheric CO2 from simulated space-borne measurements of backscattered near-infrared sunlight: accounting for aerosol effects. , 2009, Applied optics.

[26]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[27]  L. Breiman Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[28]  M. Buchwitz,et al.  SCIAMACHY: Mission Objectives and Measurement Modes , 1999 .

[29]  I. Girach,et al.  Applicability of machine learning model to simulate atmospheric CO2 variability , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[30]  C. Turley Intergovernmental Panel on Climate Change (IPCC) , 2010 .

[31]  Rex Britter,et al.  ATMOSPHERIC DISPERSION OF DENSE GASES , 1989 .

[32]  P. Ciais,et al.  Archived Version from Ncdocks Institutional Repository a Synthesis of Carbon Dioxide Emissions from Fossil-fuel Combustion Title: a Synthesis of Carbon Dioxide Emissions from Fossil-fuel Combustion a Synthesis of Carbon Dioxide Emissions from Fossil-fuel Combustion , 2022 .