| 28 Sep 2026
GATES-Background 0.2.0: Emulating background greenhouse gas mole fractions for regional atmospheric inverse modelling with graph neural networks
Abstract. Regional atmospheric trace gas inverse modelling frameworks depend on accurately simulating mole fractions, which result from transporting surface fluxes within a domain and carrying mole fractions into the region from its boundaries. With the aim of improving the computational efficiency of inverse modelling pipelines, recent machine learning approaches have successfully emulated Lagrangian Particle Dispersion Model (LPDM) footprints (source-receptor relationships) at substantially reduced computational cost, compared to the numerical model simulations. However, the estimation of the background component of the simulated mole fractions, an important contributor to overall mole fraction variability, has received comparatively little attention. In this study, we build on the GATES model (Graph-Neural-Network Atmospheric Transport Emulation System, Fillola et al. (2026b)), which emulates LPDM outputs, and present GATES-Background 0.2.0, a complementary emulator for background mole fraction contributions to observations across a regional domain driven by meteorological data and large-scale background estimates from a global methane reanalysis.
GATES-Background is trained and evaluated to emulate background concentrations for GOSAT observations over South America and demonstrates strong agreement with reference calculations generated from the propagation of boundary conditions to the measurement location. The emulator generally captures daily variability, seasonal structure, and regional gradients in background mole fraction contributions, with errors that are relatively small and spatially localized, compared to the variability in the simulated background values (root-mean-square errors of 5.3–7.4 ppb, depending on season, compared to GOSAT XCH4 retrieval error on the order of 13 ppb and estimated variability due to boundary conditions within this region of approximately 15–20 ppb). The proposed approach reduces computational cost by several orders of magnitude relative to physics-based background calculations, enabling scalable and near–real-time application. When combined with GATES or other LPDM footprint emulators, this work will enable efficient machine learning–based approximation of both components of the forward model used in regional LPDM-based greenhouse gas inversion systems.
While this paper describes dispersion modelling based on atmospheric "mole fractions", the GOSAT data upon which the modelling is based are not atmospheric, but rather with reference to dry air (Parker et al., 2020), as if there were no water vapour. However, water vapour plays a non-negligible role in methane variability across the modelling domain. For example, with equal values of the methane dry air mole fraction (1.75 ppm), air in Manaus with a 3% water vapour mole fraction would have a methane mole fraction of 1.70 ppm, whereas air in Santiago with 1% water vapour would have a methane mole fraction of 1.73 ppm. Such humidity-induced variability is not negligible, but rather comparable in magnitude to methane fluctuations that are forced by its sources and sinks.
If Lagrangian Particle Dispersion Model exercises are not sensitive to methane gradients forced by changes in humidity, the authors should at least clarify, in the title and elsewhere, that they are working with mole fractions within fictitious dry air. Otherwise, atmospheric mole fractions should be calculated by taking into account the non-negligible influence of water vapour.