Bias on the mean redshift (see Eq. (3)) averaged over the 18 photometric noise realisations and the impact of the training sample size on the mean redshift accuracy in the LSST/Euclid case. Left and right panels: correspond to uniform and SOM spectroscopic coverage, respectively. Top panels: number of galaxies used for the training in the three considered cases. Middle and bottom panels: mean redshift accuracy using the direct calibration and the optimised zPDF methods, respectively.