Methodology: TOMCAT simulation is performed at T64L32 resolution for the 2000-2023 period. Collocated CFC12 (CF2Cl2) 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). Initially, TOMCAT tracers are interpolated on the ACE FTS height (1km to 50km) Separate XGBoost regression models are trained to predict ACE FTS measurements for a given altitude /latitude bin if more than 2000 measurements are available. XGBoost model is then used to estimate CFC12 volume mixing ratios for all the TOMCAT grids. Height resolved data are then interpolated on 22-pressure levels. For overlapping latitude bins, we use averages and then calculate daily zonal mean values. For more details see attached presentation. Dataset also includes two files containing daily mean zonal mean CFC-12 profiles on height (1-50 km) and pressure (300-1 hPa) – 22 levels (9132 days/64 latitudes). Files also include uncertainties estimated using quantile regression and uncertainty = NaN means data is from TOMCAT CTM (scientifically useful range 5 to 25km). zmcfc12_tcom_hlev_2000-2024_V2.0.nc – height level data (1 to 50 km) zmcfc12_tcom_plev_2000-2024_V2.0.nc – pressure level data (300 to 1 hPa) Daily 3D profiles on height and pressure levels would be made available on request. Xarrays “resample” can be used to get monthly means. (attachecd pdf file gives more details. This data set improves from our previous methodology (Dhomse and Chipperfield, 2023, ESSD) and manuscript describing to those updates will be submitted to ESSD.