Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning
The lensing effect of the cosmic microwave background (CMB) is a powerful tool for our study of the distribution of matter in the universe. The quadratic estimator (QE) method, which is widely used to reconstruct lensing potential, has been known to be suboptimal for the low noise level polarization...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | The Astrophysical Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4357/acdb72 |
| _version_ | 1797694095463809024 |
|---|---|
| author | Ye-Peng Yan Guo-Jian Wang Si-Yu Li Yang-Jie Yan Jun-Qing Xia |
| author_facet | Ye-Peng Yan Guo-Jian Wang Si-Yu Li Yang-Jie Yan Jun-Qing Xia |
| author_sort | Ye-Peng Yan |
| collection | DOAJ |
| description | The lensing effect of the cosmic microwave background (CMB) is a powerful tool for our study of the distribution of matter in the universe. The quadratic estimator (QE) method, which is widely used to reconstruct lensing potential, has been known to be suboptimal for the low noise level polarization data from next-generation CMB experiments. To improve the performance of the reconstruction, other methods, such as the maximum-likelihood estimator and machine-learning algorithms, have been developed. In this work, we present a deep convolutional neural network model named the Residual Dense Local Feature U-net (RDLFUnet) for reconstructing the CMB lensing convergence field. By simulating lensed CMB data with different noise levels to train and test network models, we find that for noise levels less than 5 μ K-arcmin, RDLFUnet can recover the input gravitational potential with a higher signal-to-noise ratio than the previous deep-learning and traditional QE methods at almost the entire observation scale. |
| first_indexed | 2024-03-12T02:52:59Z |
| format | Article |
| id | doaj.art-39d2903518d249c39e31e7013aa7defd |
| institution | Directory Open Access Journal |
| issn | 1538-4357 |
| language | English |
| last_indexed | 2024-03-12T02:52:59Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal |
| spelling | doaj.art-39d2903518d249c39e31e7013aa7defd2023-09-03T15:26:58ZengIOP PublishingThe Astrophysical Journal1538-43572023-01-0195211510.3847/1538-4357/acdb72Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine LearningYe-Peng Yan0Guo-Jian Wang1https://orcid.org/0000-0003-0272-5032Si-Yu Li2Yang-Jie Yan3Jun-Qing Xia4Institute for Frontiers in Astronomy and Astrophysics , Beijing Normal University, Beijing 100875, People's Republic of China ; xiajq@bnu.edu.cn; Department of Astronomy, Beijing Normal University , Beijing 100875, People's Republic of ChinaSchool of Chemistry and Physics, University of KwaZulu-Natal , Westville Campus, Private Bag X54001 Durban, 4000, South Africa; NAOC-UKZN Computational Astrophysics Centre (NUCAC), University of KwaZulu-Natal , Durban, 4000, South AfricaKey Laboratory of Particle Astrophysics, Institute of High Energy Physics, Chinese Academy of Science , P.O. Box 918-3 Beijing 100049, People's Republic of ChinaInstitute for Frontiers in Astronomy and Astrophysics , Beijing Normal University, Beijing 100875, People's Republic of China ; xiajq@bnu.edu.cn; Department of Astronomy, Beijing Normal University , Beijing 100875, People's Republic of ChinaInstitute for Frontiers in Astronomy and Astrophysics , Beijing Normal University, Beijing 100875, People's Republic of China ; xiajq@bnu.edu.cn; Department of Astronomy, Beijing Normal University , Beijing 100875, People's Republic of ChinaThe lensing effect of the cosmic microwave background (CMB) is a powerful tool for our study of the distribution of matter in the universe. The quadratic estimator (QE) method, which is widely used to reconstruct lensing potential, has been known to be suboptimal for the low noise level polarization data from next-generation CMB experiments. To improve the performance of the reconstruction, other methods, such as the maximum-likelihood estimator and machine-learning algorithms, have been developed. In this work, we present a deep convolutional neural network model named the Residual Dense Local Feature U-net (RDLFUnet) for reconstructing the CMB lensing convergence field. By simulating lensed CMB data with different noise levels to train and test network models, we find that for noise levels less than 5 μ K-arcmin, RDLFUnet can recover the input gravitational potential with a higher signal-to-noise ratio than the previous deep-learning and traditional QE methods at almost the entire observation scale.https://doi.org/10.3847/1538-4357/acdb72Cosmic microwave background radiationObservational cosmologyConvolutional neural networks |
| spellingShingle | Ye-Peng Yan Guo-Jian Wang Si-Yu Li Yang-Jie Yan Jun-Qing Xia Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning The Astrophysical Journal Cosmic microwave background radiation Observational cosmology Convolutional neural networks |
| title | Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning |
| title_full | Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning |
| title_fullStr | Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning |
| title_full_unstemmed | Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning |
| title_short | Lensing Reconstruction from the Cosmic Microwave Background Polarization with Machine Learning |
| title_sort | lensing reconstruction from the cosmic microwave background polarization with machine learning |
| topic | Cosmic microwave background radiation Observational cosmology Convolutional neural networks |
| url | https://doi.org/10.3847/1538-4357/acdb72 |
| work_keys_str_mv | AT yepengyan lensingreconstructionfromthecosmicmicrowavebackgroundpolarizationwithmachinelearning AT guojianwang lensingreconstructionfromthecosmicmicrowavebackgroundpolarizationwithmachinelearning AT siyuli lensingreconstructionfromthecosmicmicrowavebackgroundpolarizationwithmachinelearning AT yangjieyan lensingreconstructionfromthecosmicmicrowavebackgroundpolarizationwithmachinelearning AT junqingxia lensingreconstructionfromthecosmicmicrowavebackgroundpolarizationwithmachinelearning |