Estimating Global Anthropogenic CO<sub>2</sub> Gridded Emissions Using a Data-Driven Stacked Random Forest Regression Model

oleh: Yucong Zhang, Xinjie Liu, Liping Lei, Liangyun Liu

Format: Article
Diterbitkan: MDPI AG 2022-08-01

Deskripsi

The accurate estimation of anthropogenic carbon emissions is of great significance for understanding the global carbon cycle and guides the setting and implementation of global climate policy and CO<sub>2</sub> emission-reduction goals. This study built a data-driven stacked random forest regression model for estimating gridded global fossil fuel CO<sub>2</sub> emissions. The driving variables include the annual features of column-averaged CO<sub>2</sub> dry-air mole fraction (XCO<sub>2</sub>) anomalies based on their ecofloristic zone, night-time light data from the Visible Infrared Imaging Radiometer Suite (VIIRS), terrestrial carbon fluxes, and vegetation parameters. A two-layer stacked random forest regression model was built to fit 1° gridded inventory of open-source data inventory for anthropogenic CO<sub>2</sub> (ODIAC). Then, the model was trained using the 2014–2018 dataset to estimate emissions in 2019, which provided a higher accuracy compared with a single-layer model with an R<sup>2</sup> of 0.766 and an RMSE of 0.359. The predicted gridded emissions are consistent with Global Carbon Grid at 1° scale with an R<sup>2</sup> of 0.665, and the national total emissions provided a higher R<sup>2</sup> at 0.977 with the Global Carbon Project (GCP) data, as compared to the ODIAC (R<sup>2</sup> = 0.956) data, in European countries. This study demonstrates that data-driven random forest regression models are capable of estimating anthropogenic CO<sub>2</sub> emissions at a grid scale.