Mapping high-resolution XCO2 concentrations in China from 2015 to 2020 based on spatiotemporal ensemble learning model

作者：Weican Liu, Rong Li, Jun Cao, Congwu Huang, Fan Zhang, Meigen Zhang · 发表于：Ecological Informatics · 年份：2024 · DOI：10.1016/j.ecoinf.2024.102806 · 被引用次数：11 · 研究领域：Atmospheric and Environmental Gas Dynamics、Geochemistry and Geologic Mapping、Health, Environment, Cognitive Aging

High-resolution column-averaged dry air mole fraction of CO 2 (XCO 2 ) data is crucial for understanding the spatiotemporal patterns of XCO 2 and for mitigating carbon emissions. Due to the limited scanning range of sensors and strict inversion conditions, satellite-retrieved XCO 2 data are often significantly incomplete. Machine learning models are widely used to fill these gaps in satellite XCO 2 data. However, the limitations of individual machine learning models and the complexity of the spatial distribution of XCO₂ mean that the accuracy of XCO 2 predictions still needs improvement. In this study, a new spatiotemporal stacked ensemble learning model (STEL) was developed by combining random forest (RF), extremely randomized trees (ERT), extreme gradient boosting (XGBoost), optical gradient boosting (LightGBM), and categorical boosting (CatBoost) using the stacking ensemble learning methodology. Considering the spatiotemporal heterogeneity of XCO 2 , a novel spatiotemporal weighting feature was constructed as part of the model's input parameters. Finally, the XCO 2 observed by Orbiting Carbon Observatory 2 (OCO-2) was reconstructed using STEL, and a monthly mean XCO 2 dataset covering China from 2015 to 2020 was generated at a spatial resolution of 0.1°. The results show that STEL exhibits superior performance and generalization capabilities compared to individual machine-learning models. R 2 RMSE and MAPE were 0.9624, 1.0023 ppm, and 0.1583 % on the test set, and 0.8970, ...