论文标题
在原始张量扰动的情况下，CMB用神经网络基于神经网络的镜头重建
CMB Delensing with Neural Network Based Lensing Reconstruction in the Presence of Primordial Tensor Perturbations
论文作者
论文摘要
预计下一代CMB实验将以高精度限制张量与尺度比率$ r $。删除是一个重要的过程，因为所观察到的包含原始张量扰动信号的CMB $ B $模式极化主要由由于重力透镜而产生的较大贡献所主导。为此，探索超出传统二次估计量（QE）（QE）的镜头重建方法（对于下一代实验将成为次优的方法）以及最大后估计器（当前仍在开发中）是有用的。在Caldeira等。 2020年，作者表明，使用Resunet Architectrue的神经网络（NN）方法比QE的性能更好，并且在透镜重建性能方面，与迭代估计量相比略有优化。在这项工作中，我们迈出了进一步的一步，以使用标准删除管道的原始张量扰动来评估这些估计器在地图上的删除性能，并表明NN估计器的\ emph {delensing}性能是最佳的$ 12.7^{\ circ} \ times 12.7^{\ circ} $映射在cmb stage〜4中像极化噪声级$ 1 \，μ\ rm {k \ rm {k \，arcmin} $和1'beam。我们发现，出于延报目的，取消了$ l <l _ {\ rm {cut}} $在一组CMB地图上进行训练和评估NN，以避免在最终的$ B $ b $ l <l <l <l <l _ cut y _ {cut y _ {cut cuts cut cut cut cut cuts cuts cut cuts cut cuts cut} cut cut cut} cut cut cut} cut cut cut}的范围中的虚假相关性。和迭代估计器。我们还提出了各种NN训练技术，可以扩展，以同时处理前景和更复杂的仪器效应，而建模更不确定。
The next-generation CMB experiments are expected to constrain the tensor-to-scalar ratio $r$ with high precision. Delensing is an important process as the observed CMB $B$-mode polarization that contains the primordial tensor perturbation signal is dominated by a much larger contribution due to gravitational lensing. To do so successfully, it is useful to explore methods for lensing reconstruction beyond the traditional quadratic estimator (QE) (which will become suboptimal for the next-generation experiments), and the maximum a posterior estimator (which is still currently under development). In Caldeira et al. 2020, the authors showed that a neural network (NN) method using the ResUNet architectrue performs better than the QE and slightly suboptimally compared to the iterative estimator in terms of the lensing reconstruction performance. In this work, we take one step further to evaluate the delensing performance of these estimators on maps with primordial tensor perturbations using a standard delensing pipeline, and show that the \emph{delensing} performance of the NN estimator is optimal, agreeing with that of a converged iterative estimator, when tested on a suite of simulations with $r=0.01$ and $r=0.001$ for $12.7^{\circ} \times 12.7^{\circ}$ maps at a CMB-Stage~4 like polarization noise level $1\,μ\rm{K\,arcmin}$ and 1' beam. We found that for the purpose of delensing, it is necessary to train and evaluate the NN on a set of CMB maps with $l<l_{\rm{cut}}$ removed, in order to avoid spurious correlations on the scales of interest for the final delensed $B$-mode power spectrum $l<l_{\rm{cut}}$, similar to what was known previously for the QE and the iterative estimator. We also present various NN training techniques that can be extended for a simultaneous treatment of foregrounds and more complex instrumental effects where the modeling is more uncertain.
