|
|
|
|
|
|
| An Algorithm for Redshift Estimation of Photometric Images Using
Convolutional Neural Networks |
| WU Kuang, SUN Chun, CAO Guan-long*, QIU Bo*, YAO Lin, ZHANG Ming-ru, ZHANG Li-wen |
Hebei University of Technology, Tianjin 300400, China
|
|
|
|
|
Abstract Redshift is one of the basic parameters of galaxies. The number of photometric images is enormous relative to the spectrum. A large number of known galaxies have only photometric images and no spectra. It is，therefore, common to obtain redshift values from photometric images rather than spectra. This paper constructs the Galactic Redshift Regression Network (GRRnet), a convolutional neural network for estimating photometric redshift from galaxy images. It has a deeper network layer than previous similar methods and adds an attention mechanism to help it focus on more useful information. Based on GRRnet, this paper further proposes a two-step strategy, GRRnet-C-R: the first step is to classify the galaxies according to the redshift roughly; the second step is to perform regression estimation according to the classified categories, and finally merge them. This strategy can significantly reduce the error of photometric redshift estimation. The data in this paper are all from the Sloan Digital Sky SurveyDR16. The relevant data of each galaxy includes the composite images of the three bands of g, r, and z, the photometric values of the five bands of u, g, r, i, and z, and the observed Spectral redshift for labeling. In the pre-processing process, the photometric image is cut to the size of 50×50, to ensure that most of the galaxies can be framed while the computation is reduced. Since the input size of the comparison algorithm NetZ is 64×64, to keep the input size consistent, use the function cv2. resize to change the image size to 64×64. The experimental results show that the mean squared error (MSE) of GRRnet-C-R reaches 0.001 46, which is 22.3%, 21.9% and 18.0% lower than that of random forest (RF), eXtreme Gradient Boosting (XGBoost) and NetZ, respectively. The linear regression coefficient of determination of GRRnet-C-R reached 0.948, which achieved a good model fitting effect. Experimental results show that this two-part strategy can effectively reduce the error of metering redshift estimation, which provides a new idea and method for subsequent metering redshift estimation.
|
|
Received: 2022-08-31
Accepted: 2023-05-31
|
|
|
|
Corresponding Authors:
CAO Guan-long, QIU Bo
E-mail: caoguanlong@hebut.edu.cn；qiubo@hebut.edu.cn
|
|
[1] Vera C. Rubin Observatory LSST Solar System Science Collaboration, Jones L, Bannister M T, et al. The Scientific Impact of the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) for Solar System Science. 2020, arXiv. 2009. 07653[astro-ph. IM].
[2] Salvato M, Ilbert O, Hoyle B. Nature Astronomy, 2019, 3(3): 212.
[3] Zhang Y, Ma H, Peng N, et al. The Astronomical Journal, 2013, 146(2): 22.
[4] Li C, Zhang Y, Cui C, et al. Monthly Notices of the Royal Astronomical Society, 2022, 509(2): 2289.
[5] MU Yong-huan, QIU Bo, WEI Shi-ya, et al(穆永欢, 邱 波, 魏诗雅, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(9): 2693.
[6] Li M, Gao Z, Qiu B, et al. Monthly Notices of the Royal Astronomical Society, 2021, 506(4): 5923.
[7] Pasquet J, Bertin E, Treyer M, et al. Astronomy & Astrophysics, 2019, 621: A26.
[8] Schuldt S, Suyu S H, Canameras R, et al. Astronomy & Astrophysics, 2021, 651: A55.
[9] Henghes B, Thiyagalingam J, Pettitt C, et al. Monthly Notices of the Royal Astronomical Society, 2022, 512(2): 1696.
[10] Lupton R, Blanton M R, Fekete G, et al. Publications of the Astronomical Society of the Pacific, 2004, 116(816): 133.
[11] Woo S, Park J, Lee J Y, et al. CBAM: Convolutional Block Attention Module. Computer Vision—ECCV 2018. Springer, 2018, 3.
[12] Breiman L. Machine learning, 2001, 45(1): 5.
[13] Chen T, Guestrin C. XGBoost: A Scalable Tree Bossting System, 2016, arXiv. 1603.02754[cs LG].
[14] Henghes B, Pettitt C, Thiyagalingam J, et al. Monthly Notices of the Royal Astronomical Society, 2021, 505(4): 4847.
[15] Kosten J. Scientometrics, 2016, 108(1): 457.
|
|
|
|
