DeepMerge: Classifying high-redshift merging galaxies with deep neural networks
- Univ. of Belgrade (Serbia); Mathematical Inst. of the Serbian Academy of Sciences and Arts, Belgrade (Serbia); Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Space Telescope Science Inst., Baltimore, MD (United States)
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States); Univ. of Chicago, IL (United States)
- Space Telescope Science Inst., Baltimore, MD (United States); Johns Hopkins Univ., Baltimore, MD (United States)
In this work, we investigate and demonstrate the use of convolutional neural networks (CNNs) for the task of distinguishing between merging and non-merging galaxies in simulated images, and for the first time at high redshifts (i.e. $z=2$). We extract images of merging and non-merging galaxies from the Illustris-1 cosmological simulation and apply observational and experimental noise that mimics that from the Hubble Space Telescope; the data without noise form a "pristine" data set and that with noise form a "noisy" data set. The test set classification accuracy of the CNN is $$79\%$$ for pristine and $$76\%$$ for noisy. The CNN outperforms a Random Forest classifier, which was shown to be superior to conventional one- or two-dimensional statistical methods (Concentration, Asymmetry, the Gini, $$M_{20}$$ statistics etc.), which are commonly used when classifying merging galaxies. We also investigate the selection effects of the classifier with respect to merger state and star formation rate, finding no bias. Finally, we extract Grad-CAMs (Gradient-weighted Class Activation Mapping) from the results to further assess and interrogate the fidelity of the classification model.
- Research Organization:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25); Ministry of Education, Science and Technological Development of the Republic of Serbia; National Aeronautic and Space Administration (NASA)
- Grant/Contract Number:
- AC02-07CH11359
- OSTI ID:
- 1632199
- Alternate ID(s):
- OSTI ID: 1809811
- Report Number(s):
- arXiv:2004.11981; FERMILAB-PUB--20-199-SCD-V; oai:inspirehep.net:1794894
- Journal Information:
- Astronomy and Computing, Journal Name: Astronomy and Computing Journal Issue: C Vol. 32; ISSN 2213-1337
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains