Quantifying greenhouse gas (GHG) emissions is critically important for projecting future climate and assessing the impact of environmental policy. Estimating GHG emissions using atmospheric observations is typically done using source-receptor relationships (i.e., "footprints"). Constructing these footprints can be computationally expensive and is rapidly becoming a computational bottleneck for studying GHG fluxes at high spatio-temporal resolution using dense observations. Here we demonstrate a computationally efficient GHG flux inversion framework using a machine learning emulator for atmospheric transport (FootNet) as a surrogate for the full-physics model. This flux inversion using a machine learning surrogate model only requires meteorological data, densely spaced measurements, and prior emission fluxes. This flux inversion framework is 84 times faster than the conventional inversion framework on a similar infrastructure such that it only takes 1.13 days to perform hourly urban flux inversions at a kilometer scale for a 3-month period on a single machine, this time includes both the construction of footprints and the GHG flux inversion. This shows the feasibility of using FootNet in the near-real-time quantification of GHG emission fluxes at a kilometer scale.