Top-down estimates of fossil fuel CO2 (FFCO2) emissions are crucial for tracking emissions and evaluating mitigation strategies. However, their practical application is hindered by limited data coverage and overreliance on NOx-to-CO2 emission ratios from emission inventories. We developed the Machine Learning-Driven Mapping Satellite-based XCO2en (ML-MSXE) model using the column-averaged dry-air mole fraction of CO2 enhancement (XCO2en) derived from OCO-2 and OCO-3 measurements to reconstruct the XCO2en distribution for monitoring FFCO2 emissions. Compared to the previous Machine Learning-Driven Deriving XCO2en from Mapped XCO2 (ML-DXEMX) model, ML-MSXE enhances the utilization of TROPOMI NO2 measurements, increasing their relative contribution from 4.3 to 21.7%, thereby improving XCO2en reconstruction accuracy and enhancing the ability to track emissions. Despite the COVID-19 lockdown, XCO2en levels in China rose from 1.33 ± 1.06 in 2019 to 1.39 ± 1.01 ppm in 2021. In February 2020, while the national average rate of XCO2en decline (16.3%) aligned with the reduction in FFCO2 emissions estimated by inventories, XCO2en further revealed varying rates of decline between cities. Furthermore, the spatial distribution of XCO2en identified hotspots where FFCO2 emissions might be underestimated by inventories. This study presents a space-based approach for monitoring FFCO2 emissions, offering valuable insights for assessing carbon neutrality progress and informing policy.