The concentration of atmospheric CO2 has increased dramatically since the pre-industrial period due to human activity such as fossil fuel combustion and land use change. Space-based measurements offer an effective means of monitoring changes in atmospheric CO2, and of quantifying surface fluxes of CO2 using inverse modeling approaches. In this context, better monitoring and quantifying emissions from power plants is critical as electricity power generation accounts for more than 40% of global anthropogenic CO2 emissions. Here we use observations from the Orbiting Carbon Observtory-3 (OCO-3) together with a Column Stochastic Time-Inverted Lagrangian Transport model (X-STILT) to quantify emissions from the Bełchatów power plant in Poland. The Bełchatów power plant is the 5th largest power plant worldwide, with reported emissions of more than 100 ktCO2 per day. To quantify the emissions, the X-STILT model is driven by winds calculated by the Weather Research and Forecasting (WRF) model on a 1 km x 1 km spatial scale and convolved with a priori CO2 emissions from the Open-source Data Inventory for Anthropogenic CO2 (ODIAC) to produce simulated column-averaged dry air mole fraction of CO2 (XCO2). The modeled XCO2 are integrated with XCO2 data from OCO-3 Snapshot Area Maps (SAMs) in a Bayesian inversion approach to estimate daily CO2 emissions from the Bełchatów power plant.