Paper detail

Eliminating Primary Beam Effect in Foreground Subtraction of Neutral Hydrogen Intensity Mapping Survey with Deep Learning

In the neutral hydrogen (HI) intensity mapping (IM) survey, the foreground contamination on the cosmological signals is extremely severe, and the systematic effects caused by radio telescopes themselves further aggravate the difficulties in subtracting foreground. In this work, we investigate whether the deep learning method, concretely the 3D U-Net algorithm here, can play a crucial role in foreground subtraction when considering the systematic effect caused by the telescope's primary beam. We consider two beam models, i.e., the Gaussian beam model as a simple case and the Cosine beam model as a sophisticated case. The traditional principal component analysis (PCA) method is employed as a comparison and, more importantly, as the preprocessing step for the U-Net method to reduce the sky map dynamic range. We find that in the case of the Gaussian beam, the PCA method can effectively clean the foreground. However, the PCA method cannot handle the systematic effect induced by the Cosine beam, and the additional U-Net method can improve the result significantly. In order to show how well the PCA and U-Net methods can recover the HI signals, we also derive the HI angular power spectra, as well as the HI 2D power spectra, after performing the foreground subtractions. It is found that, in the case of Gaussian beam, the concordance with the original HI map using U-Net is better than that using PCA by $27.4\%$, and in the case of Cosine beam, the concordance using U-Net is better than that using PCA by $144.8\%$. Therefore, the U-Net based foreground subtraction can efficiently eliminate the telescope primary beam effect and shed new light on recovering the HI power spectrum for future HI IM experiments.