Forecasts on Primordial non-Gaussianity from 21 cm Intensity Mapping experiments

We forecast ability of dedicated 21 cm intensity mapping experiments to constraint primordial non-Gaussianity using power spectrum and bispectrum. We model the signal including the non-linear biasing expansion using a generalized halo model approach. We consider the importance of foreground filtering scale and of the foreground wedge. We find that the current generation intensity mapping experiments like CHIME do not posses sufficient sensitivity to be competitive with the existing limits. On the other hand, upcoming experiments like HIRAX can improve the current constraints and the proposed PUMA experiment can substantially improve them, reaching sensitivities below $\sigma (f_{\rm NL})<5$ for equilateral and orthogonal configurations and $\sigma( f_{\rm NL}) < 1$ for the local shape if good foreground control is achieved.