Characterising improvements in photometric redshift probability density functions with galaxy morphology

In this work, we studied the impact of galaxy morphology on photometric redshift (photo-$z$) probability density functions (PDFs). By including morphological parameters like radius, axis-ratio, surface brightness and S\'ersic index in addition to $ugriz$ broadbands as input parameters, used machine learning photo-$z$ algorithm ANNz2 train test galaxies from Canada-France-Hawaii Telescope Stripe-82 (CS82) Survey. Metrics continuous ranked score (CRPS), integral transform (PIT), Bayesian odds parameter, even width height PDFs were evaluated, results compared when different number during training process. We find improvements CRPS has been added training, improvement is larger especially broadband magnitudes are lacking.