CMB delensing with deep learning

The cosmic microwave background (CMB) stands as a pivotal source for studying weak gravitational lensing. While the lensed CMB aids in constraining cosmological parameters, it simultaneously smooths the original CMB’s features. The angular power spectrum of the unlensed CMB showcases sharper acoustic peaks and more pronounced damping tails, enhancing the precision of inferring cosmological parameters that influence these aspects. Although delensing diminishes the B-mode power spectrum (BB), it facilitates the pursuit of primordial gravitational waves and enables a lower variance reconstruction of lensing and additional sources of secondary CMB anisotropies. We employed the U-shaped convolutional neural network (UNet++) algorithm to perform operations and analysis on CMB delensing, presenting the angular power spectra of temperature-temperature (TT), E-mode (EE), and BB after CMB delensing, and compared them with those obtained using the quadratic estimator (QE) delensing algorithm. The lensing CMB sky map and full-sky angular power spectrum processed by the UNet++ algorithm are very close to those of the CMB without lensing effects, and the error is more than 10 times smaller than that given by the QE algorithm. The code utilized for this analysis is publicly available.