A deep learning approach to galaxy cluster X-ray masses
We present a machine-learning (ML) approach for estimating galaxy cluster masses from Chandra mock images. We utilize a Convolutional Neural Network (CNN), a deep ML tool commonly used in image recognition tasks. The CNN is trained and tested on our sample of 7896 Chandra X-ray mock observations, wh...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
2019 May 7
|
| In: |
The astrophysical journal
Year: 2019, Volume: 876, Issue: 1, Pages: 1-7 |
| ISSN: | 1538-4357 |
| DOI: | 10.3847/1538-4357/ab14eb |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.3847/1538-4357/ab14eb
|
| Author Notes: | M. Ntampaka, J. ZuHone, D. Eisenstein, D. Nagai, A. Vikhlinin, L. Hernquist, F. Marinacci, D. Nelson, R. Pakmor, A. Pillepich, P. Torrey, and M. Vogelsberger |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1811011381 | ||
| 003 | DE-627 | ||
| 005 | 20220820230316.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220720s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.3847/1538-4357/ab14eb |2 doi | |
| 035 | |a (DE-627)1811011381 | ||
| 035 | |a (DE-599)KXP1811011381 | ||
| 035 | |a (OCoLC)1341464194 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 29 |2 sdnb | ||
| 100 | 1 | |a Ntampaka, Michelle |e VerfasserIn |0 (DE-588)1263707823 |0 (DE-627)181182191X |4 aut | |
| 245 | 1 | 2 | |a A deep learning approach to galaxy cluster X-ray masses |c M. Ntampaka, J. ZuHone, D. Eisenstein, D. Nagai, A. Vikhlinin, L. Hernquist, F. Marinacci, D. Nelson, R. Pakmor, A. Pillepich, P. Torrey, and M. Vogelsberger |
| 264 | 1 | |c 2019 May 7 | |
| 300 | |a 7 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 20.07.2022 | ||
| 520 | |a We present a machine-learning (ML) approach for estimating galaxy cluster masses from Chandra mock images. We utilize a Convolutional Neural Network (CNN), a deep ML tool commonly used in image recognition tasks. The CNN is trained and tested on our sample of 7896 Chandra X-ray mock observations, which are based on 329 massive clusters from the simulation. Our CNN learns from a low resolution spatial distribution of photon counts and does not use spectral information. Despite our simplifying assumption to neglect spectral information, the resulting mass values estimated by the CNN exhibit small bias in comparison to the true masses of the simulated clusters (−0.02 dex) and reproduce the cluster masses with low intrinsic scatter, 8% in our best fold and 12% averaging over all. In contrast, a more standard core-excised luminosity method achieves 15%-18% scatter. We interpret the results with an approach inspired by Google DeepDream and find that the CNN ignores the central regions of clusters, which are known to have high scatter with mass. | ||
| 700 | 1 | |a ZuHone, J. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Eisenstein, D. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Nagai, D. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Vikhlinin, A. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hernquist, L. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Marinacci, Federico |e VerfasserIn |0 (DE-588)1054438684 |0 (DE-627)79152194X |0 (DE-576)410132837 |4 aut | |
| 700 | 1 | |a Nelson, Dylan |e VerfasserIn |0 (DE-588)115182805X |0 (DE-627)101233600X |0 (DE-576)42382581X |4 aut | |
| 700 | 1 | |a Pakmor, Rüdiger |d 1982- |e VerfasserIn |0 (DE-588)14360905X |0 (DE-627)647700670 |0 (DE-576)337951543 |4 aut | |
| 700 | 1 | |a Pillepich, Annalisa |e VerfasserIn |0 (DE-588)1151829854 |0 (DE-627)1012339327 |0 (DE-576)423800841 |4 aut | |
| 700 | 1 | |a Torrey, Paul |e VerfasserIn |0 (DE-588)1177294184 |0 (DE-627)104866015X |0 (DE-576)517365162 |4 aut | |
| 700 | 1 | |a Vogelsberger, Mark |d 1978- |e VerfasserIn |0 (DE-588)133437698 |0 (DE-627)546058434 |0 (DE-576)299848299 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The astrophysical journal |d London : Institute of Physics Publ., 1995 |g 876(2019), 1, Artikel-ID 82, Seite 1-7 |h Online-Ressource |w (DE-627)269019219 |w (DE-600)1473835-1 |w (DE-576)077662733 |x 1538-4357 |7 nnas |a A deep learning approach to galaxy cluster X-ray masses |
| 773 | 1 | 8 | |g volume:876 |g year:2019 |g number:1 |g elocationid:82 |g pages:1-7 |g extent:7 |a A deep learning approach to galaxy cluster X-ray masses |
| 856 | 4 | 0 | |u https://doi.org/10.3847/1538-4357/ab14eb |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20220720 | ||
| 993 | |a Article | ||
| 994 | |a 2019 | ||
| 998 | |g 1151829854 |a Pillepich, Annalisa |m 1151829854:Pillepich, Annalisa |d 130000 |e 130000PP1151829854 |k 0/130000/ |p 10 | ||
| 998 | |g 14360905X |a Pakmor, Rüdiger |m 14360905X:Pakmor, Rüdiger |d 130000 |d 130300 |e 130000PP14360905X |e 130300PP14360905X |k 0/130000/ |k 1/130000/130300/ |p 9 | ||
| 998 | |g 115182805X |a Nelson, Dylan |m 115182805X:Nelson, Dylan |p 8 | ||
| 999 | |a KXP-PPN1811011381 |e 4171141265 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"origin":[{"dateIssuedKey":"2019","dateIssuedDisp":"2019 May 7"}],"note":["Gesehen am 20.07.2022"],"recId":"1811011381","language":["eng"],"name":{"displayForm":["M. Ntampaka, J. ZuHone, D. Eisenstein, D. Nagai, A. Vikhlinin, L. Hernquist, F. Marinacci, D. Nelson, R. Pakmor, A. Pillepich, P. Torrey, and M. Vogelsberger"]},"person":[{"display":"Ntampaka, Michelle","family":"Ntampaka","given":"Michelle","role":"aut"},{"given":"J.","role":"aut","display":"ZuHone, J.","family":"ZuHone"},{"display":"Eisenstein, D.","family":"Eisenstein","given":"D.","role":"aut"},{"family":"Nagai","display":"Nagai, D.","role":"aut","given":"D."},{"display":"Vikhlinin, A.","family":"Vikhlinin","given":"A.","role":"aut"},{"family":"Hernquist","display":"Hernquist, L.","role":"aut","given":"L."},{"role":"aut","given":"Federico","family":"Marinacci","display":"Marinacci, Federico"},{"role":"aut","given":"Dylan","family":"Nelson","display":"Nelson, Dylan"},{"role":"aut","given":"Rüdiger","family":"Pakmor","display":"Pakmor, Rüdiger"},{"role":"aut","given":"Annalisa","family":"Pillepich","display":"Pillepich, Annalisa"},{"given":"Paul","role":"aut","display":"Torrey, Paul","family":"Torrey"},{"display":"Vogelsberger, Mark","family":"Vogelsberger","given":"Mark","role":"aut"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"title":[{"title_sort":"deep learning approach to galaxy cluster X-ray masses","title":"A deep learning approach to galaxy cluster X-ray masses"}],"relHost":[{"pubHistory":["Vol. 447 (1995) [?]-"],"name":{"displayForm":["publ. in coll. with the American Astronomical Society. S. Chandrasekhar, managing ed"]},"note":["Gesehen am 18.01.2022","Fortsetzung der Druck-Ausgabe"],"recId":"269019219","language":["eng"],"origin":[{"publisherPlace":"London ; Chicago, Ill. [u.a.]","publisher":"Institute of Physics Publ. ; Univ. of Chicago Press","dateIssuedDisp":"[1995?]-"}],"id":{"issn":["1538-4357"],"eki":["269019219"],"zdb":["1473835-1"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"subtitle":"an international review of spectroscopy and astronomical physics","title":"The astrophysical journal","title_sort":"astrophysical journal"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"disp":"A deep learning approach to galaxy cluster X-ray massesThe astrophysical journal","titleAlt":[{"title":"The astrophysical journal / 1"},{"title":"ApJ"}],"part":{"pages":"1-7","issue":"1","extent":"7","year":"2019","volume":"876","text":"876(2019), 1, Artikel-ID 82, Seite 1-7"}}],"physDesc":[{"extent":"7 S."}],"id":{"doi":["10.3847/1538-4357/ab14eb"],"eki":["1811011381"]}} | ||
| SRT | |a NTAMPAKAMIDEEPLEARNI2019 | ||