
The project is aimed at developing an innovative retrieval framework to derive CH4 vertical profiles from satellite data, driven and validated by circulation modeling and known CH4 temporal trends. The methodology is based on Physics-Informed Neural Networks, which include equations that inform about the physical variability of the output parameter. The methodology will be tuned for and applied to IASI data, already extensively used to retrieve CH4 column abundances. By working on selected target regions, results will be validated with established retrieval schemes, with co-located ground measurements of the full vertical profile, and by comparison of the retrieved profiles with 3D transport models. Ancillary information from climate reanalyses and circulation models themselves will be used to provide input for radiative transfer simulations used to train the scheme.Spatial interpolation techniques will be used to produce Level 3 products, which will be provided through the construction of a dedicated, modern web interface with searchable products.
This project is funded by European Union - Next Generation EU, within the PRIN 2022 PNRR program (D.D. 1409 del 14/09/2022 Ministero dell’Università e della Ricerca) within the PRIN 2022 PNRR call - Decreto Direttoriale n. 1409 del 14-9-2022 Ministero dell’Università e della Ricerca. (CUP-CNR B53D23033700001)