Mapping seamless monthly XCO2 in East Asia: Utilizing OCO-2 data and machine learning

Abstract

High spatial resolution XCO2 data is key to investigating the mechanisms of carbon sources and sinks. However, current carbon satellites have a narrow swath and uneven observation points, making it difficult to obtain seamless and full-coverage data. We propose a novel method combining extreme gradient boosting (XGBoost) with particle swarm optimization (PSO) to construct the relationship between OCO-2 XCO2 data and auxiliary data (i.e., vegetation, meteorological, anthropogenic emissions, and LST data), and to map the seamless monthly XCO2 concentration in East Asia from 2015 to 2020. Validation results based on TCCON ground station data demonstrate the high accuracy of the model with an average R2 of 0.93, Root Mean Square Error (RMSE) of 1.33 and Mean Absolute Percentage Error (MAPE) of 0.24 % in five sites. The results show that the average atmospheric XCO2 concentration in East Asia shows a continuous increasing trend from 2015 to 2020, with an average annual growth rate of 2.21 ppm/yr. This trend is accompanied by clear seasonal variations, with the highest XCO2 concentration in winter and the lowest in summer. Additionally, anthropogenic activities contributed significantly to XCO2 concentrations, which were higher in urban areas. These findings highlight the dynamics of regional XCO2 concentrations over time and their association with human activities. This study provides a detailed examination of XCO2 distribution and trends in East Asia, enhancing our comprehension of atmospheric CO2 dynamics.

Keywords

• Atmospheric XCO2
• Machine learning
• OCO-2 satellite
• Spatiotemporal distribution