Greenhouse gas (GHG) retrievals rely on repeated evaluations of computationally expensive physics-based forward models, which limit the feasibility of near-real-time retrievals and timely detection of emission hotspots. A promising alternative is to replace these forward models with fast machine learning emulators trained to approximate their input-output mapping, while retaining the overall retrieval algorithm.</p> <p>Here, we assess the feasibility of this approach in the context of the Sentinel-5 mission, systematically comparing two different emulation strategies: an end-to-end approach, which directly approximates the full forward model with neural networks, and a hybrid approach, which combines fast non-scattering simulations with a neural network-based correction for atmospheric scattering effects. We comprehensively validate each emulator in the full retrieval chain, evaluating their impact on the accuracy of retrieved XCO₂ and XCH₄.</p> <p>Our results show that a hybrid approach is needed to meet the stringent accuracy requirements on XCH₄ and XCO₂. While the end-to-end emulator achieves large speed-ups exceeding a factor of 300, it introduces considerable errors of 7.22 ppb for XCH₄ and 4.25 ppm for XCO₂ compared to full-physics retrievals, and fails to generalize to high-emission scenarios beyond the training range. In contrast, the hybrid approach can effectively leverage the information provided by the non-scattering approximation, reducing emulator-induced retrieval errors to less than 1.5 ppb for XCH₄ and 0.5 ppm for XCO₂, while still being an order of magnitude faster than full-physics retrievals and maintaining robust performance for high-emission scenarios.</p> <p>Together, these results pave the way for operational deployment of neural network-based forward models in GHG retrievals from Sentinel-5, and more broadly demonstrate the potential of hybrid machine learning emulators to facilitate timely and accurate processing of the rapidly growing data volumes from modern satellite missions.