TOMCAT simulation is performed at T64L32 resolution that is similar to the one used in Dhomse et al., (2021, 2022) for 1991-2021 time period. Model profile are sample at ACE-FTS (2004-present) measurement collocation, so that we get model output at nearest lat/lon and time. Then collocated N2O profiles are divided in five latitude bins: SH polar (90S-50S), SH mid-lat (70S-20S), tropics (40S-40N), NH mid-lat (20N-70N) and NH polar (50N-90N). Corrections for overlapping latitude are averaged to ensure that mean correction terms do not have sharp edges

Initially, differences are calculated for each zonal bins for 51 height levels (10km to 60km). Then separate XGBoost regression models are trained for the N2O differences between TOMCAT and measurements at each level for a given latitude bin. Same model is used for all day/night time (2 X11323 days) TOMCAT output sampled at 1.30 am and 1.30 pm local time at the equator. Bias corrections for a given model grid are calculated using XGBoost and are added to the original TOMCAT day and night time profiles. Height resolved data are then interpolated on 28-pressure levels (300 - 0.1hPa). For overlapping latitude bins, we use averages and then calculate daily zonal mean values. For more details see attached presentation.