Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies

Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies. Walmsley, M., Lintott, C., Geron, T., Kruk, S., Krawczyk, C., Willett, K. W., Bamford, S., Keel, W., Kelvin, L. S., Fortson, L., Masters, K. L., Mehta, V., Simmons, B. D., Smethurst, R., Baeten, E. M., & Macmillan, C. arXiv e-prints, 2102:arXiv:2102.08414, February, 2021.

Paper abstract bibtex

We present Galaxy Zoo DECaLS: detailed visual morphological classifications for Dark Energy Camera Legacy Survey images of galaxies within the SDSS DR8 footprint. Deeper DECaLS images (r=23.6 vs. r=22.2 from SDSS) reveal spiral arms, weak bars, and tidal features not previously visible in SDSS imaging. To best exploit the greater depth of DECaLS images, volunteers select from a new set of answers designed to improve our sensitivity to mergers and bars. Galaxy Zoo volunteers provide 7.5 million individual classifications over 314,000 galaxies. 140,000 galaxies receive at least 30 classifications, sufficient to accurately measure detailed morphology like bars, and the remainder receive approximately 5. All classifications are used to train an ensemble of Bayesian convolutional neural networks (a state-of-the-art deep learning method) to predict posteriors for the detailed morphology of all 314,000 galaxies. When measured against confident volunteer classifications, the networks are approximately 99% accurate on every question. Morphology is a fundamental feature of every galaxy; our human and machine classifications are an accurate and detailed resource for understanding how galaxies evolve.

@article{walmsley_galaxy_2021,
	title = {Galaxy {Zoo} {DECaLS}: {Detailed} {Visual} {Morphology} {Measurements} from {Volunteers} and {Deep} {Learning} for 314,000 {Galaxies}},
	volume = {2102},
	shorttitle = {Galaxy {Zoo} {DECaLS}},
	url = {http://adsabs.harvard.edu/abs/2021arXiv210208414W},
	abstract = {We present Galaxy Zoo DECaLS: detailed visual morphological 
classifications for Dark Energy Camera Legacy Survey images of galaxies
within the SDSS DR8 footprint. Deeper DECaLS images (r=23.6 vs. r=22.2
from SDSS) reveal spiral arms, weak bars, and tidal features not
previously visible in SDSS imaging. To best exploit the greater depth of
DECaLS images, volunteers select from a new set of answers designed to
improve our sensitivity to mergers and bars. Galaxy Zoo volunteers
provide 7.5 million individual classifications over 314,000 galaxies.
140,000 galaxies receive at least 30 classifications, sufficient to
accurately measure detailed morphology like bars, and the remainder
receive approximately 5. All classifications are used to train an
ensemble of Bayesian convolutional neural networks (a state-of-the-art
deep learning method) to predict posteriors for the detailed morphology
of all 314,000 galaxies. When measured against confident volunteer
classifications, the networks are approximately 99\% accurate on every
question. Morphology is a fundamental feature of every galaxy; our human
and machine classifications are an accurate and detailed resource for
understanding how galaxies evolve.},
	urldate = {2021-02-24},
	journal = {arXiv e-prints},
	author = {Walmsley, Mike and Lintott, Chris and Geron, Tobias and Kruk, Sandor and Krawczyk, Coleman and Willett, Kyle W. and Bamford, Steven and Keel, William and Kelvin, Lee S. and Fortson, Lucy and Masters, Karen L. and Mehta, Vihang and Simmons, Brooke D. and Smethurst, Rebecca and Baeten, Elisabeth M. and Macmillan, Christine},
	month = feb,
	year = {2021},
	keywords = {Astrophysics - Astrophysics of Galaxies, Computer Science - Computer Vision and Pattern Recognition},
	pages = {arXiv:2102.08414},
}

Downloads: 0

{"_id":"beqssb2FajxbTmaiy","bibbaseid":"walmsley-lintott-geron-kruk-krawczyk-willett-bamford-keel-etal-galaxyzoodecalsdetailedvisualmorphologymeasurementsfromvolunteersanddeeplearningfor314000galaxies-2021","author_short":["Walmsley, M.","Lintott, C.","Geron, T.","Kruk, S.","Krawczyk, C.","Willett, K. W.","Bamford, S.","Keel, W.","Kelvin, L. S.","Fortson, L.","Masters, K. L.","Mehta, V.","Simmons, B. D.","Smethurst, R.","Baeten, E. M.","Macmillan, C."],"bibdata":{"bibtype":"article","type":"article","title":"Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies","volume":"2102","shorttitle":"Galaxy Zoo DECaLS","url":"http://adsabs.harvard.edu/abs/2021arXiv210208414W","abstract":"We present Galaxy Zoo DECaLS: detailed visual morphological classifications for Dark Energy Camera Legacy Survey images of galaxies within the SDSS DR8 footprint. Deeper DECaLS images (r=23.6 vs. r=22.2 from SDSS) reveal spiral arms, weak bars, and tidal features not previously visible in SDSS imaging. To best exploit the greater depth of DECaLS images, volunteers select from a new set of answers designed to improve our sensitivity to mergers and bars. Galaxy Zoo volunteers provide 7.5 million individual classifications over 314,000 galaxies. 140,000 galaxies receive at least 30 classifications, sufficient to accurately measure detailed morphology like bars, and the remainder receive approximately 5. All classifications are used to train an ensemble of Bayesian convolutional neural networks (a state-of-the-art deep learning method) to predict posteriors for the detailed morphology of all 314,000 galaxies. When measured against confident volunteer classifications, the networks are approximately 99% accurate on every question. Morphology is a fundamental feature of every galaxy; our human and machine classifications are an accurate and detailed resource for understanding how galaxies evolve.","urldate":"2021-02-24","journal":"arXiv e-prints","author":[{"propositions":[],"lastnames":["Walmsley"],"firstnames":["Mike"],"suffixes":[]},{"propositions":[],"lastnames":["Lintott"],"firstnames":["Chris"],"suffixes":[]},{"propositions":[],"lastnames":["Geron"],"firstnames":["Tobias"],"suffixes":[]},{"propositions":[],"lastnames":["Kruk"],"firstnames":["Sandor"],"suffixes":[]},{"propositions":[],"lastnames":["Krawczyk"],"firstnames":["Coleman"],"suffixes":[]},{"propositions":[],"lastnames":["Willett"],"firstnames":["Kyle","W."],"suffixes":[]},{"propositions":[],"lastnames":["Bamford"],"firstnames":["Steven"],"suffixes":[]},{"propositions":[],"lastnames":["Keel"],"firstnames":["William"],"suffixes":[]},{"propositions":[],"lastnames":["Kelvin"],"firstnames":["Lee","S."],"suffixes":[]},{"propositions":[],"lastnames":["Fortson"],"firstnames":["Lucy"],"suffixes":[]},{"propositions":[],"lastnames":["Masters"],"firstnames":["Karen","L."],"suffixes":[]},{"propositions":[],"lastnames":["Mehta"],"firstnames":["Vihang"],"suffixes":[]},{"propositions":[],"lastnames":["Simmons"],"firstnames":["Brooke","D."],"suffixes":[]},{"propositions":[],"lastnames":["Smethurst"],"firstnames":["Rebecca"],"suffixes":[]},{"propositions":[],"lastnames":["Baeten"],"firstnames":["Elisabeth","M."],"suffixes":[]},{"propositions":[],"lastnames":["Macmillan"],"firstnames":["Christine"],"suffixes":[]}],"month":"February","year":"2021","keywords":"Astrophysics - Astrophysics of Galaxies, Computer Science - Computer Vision and Pattern Recognition","pages":"arXiv:2102.08414","bibtex":"@article{walmsley_galaxy_2021,\n\ttitle = {Galaxy {Zoo} {DECaLS}: {Detailed} {Visual} {Morphology} {Measurements} from {Volunteers} and {Deep} {Learning} for 314,000 {Galaxies}},\n\tvolume = {2102},\n\tshorttitle = {Galaxy {Zoo} {DECaLS}},\n\turl = {http://adsabs.harvard.edu/abs/2021arXiv210208414W},\n\tabstract = {We present Galaxy Zoo DECaLS: detailed visual morphological \nclassifications for Dark Energy Camera Legacy Survey images of galaxies\nwithin the SDSS DR8 footprint. Deeper DECaLS images (r=23.6 vs. r=22.2\nfrom SDSS) reveal spiral arms, weak bars, and tidal features not\npreviously visible in SDSS imaging. To best exploit the greater depth of\nDECaLS images, volunteers select from a new set of answers designed to\nimprove our sensitivity to mergers and bars. Galaxy Zoo volunteers\nprovide 7.5 million individual classifications over 314,000 galaxies.\n140,000 galaxies receive at least 30 classifications, sufficient to\naccurately measure detailed morphology like bars, and the remainder\nreceive approximately 5. All classifications are used to train an\nensemble of Bayesian convolutional neural networks (a state-of-the-art\ndeep learning method) to predict posteriors for the detailed morphology\nof all 314,000 galaxies. When measured against confident volunteer\nclassifications, the networks are approximately 99\\% accurate on every\nquestion. Morphology is a fundamental feature of every galaxy; our human\nand machine classifications are an accurate and detailed resource for\nunderstanding how galaxies evolve.},\n\turldate = {2021-02-24},\n\tjournal = {arXiv e-prints},\n\tauthor = {Walmsley, Mike and Lintott, Chris and Geron, Tobias and Kruk, Sandor and Krawczyk, Coleman and Willett, Kyle W. and Bamford, Steven and Keel, William and Kelvin, Lee S. and Fortson, Lucy and Masters, Karen L. and Mehta, Vihang and Simmons, Brooke D. and Smethurst, Rebecca and Baeten, Elisabeth M. and Macmillan, Christine},\n\tmonth = feb,\n\tyear = {2021},\n\tkeywords = {Astrophysics - Astrophysics of Galaxies, Computer Science - Computer Vision and Pattern Recognition},\n\tpages = {arXiv:2102.08414},\n}\n\n","author_short":["Walmsley, M.","Lintott, C.","Geron, T.","Kruk, S.","Krawczyk, C.","Willett, K. W.","Bamford, S.","Keel, W.","Kelvin, L. S.","Fortson, L.","Masters, K. L.","Mehta, V.","Simmons, B. D.","Smethurst, R.","Baeten, E. M.","Macmillan, C."],"key":"walmsley_galaxy_2021","id":"walmsley_galaxy_2021","bibbaseid":"walmsley-lintott-geron-kruk-krawczyk-willett-bamford-keel-etal-galaxyzoodecalsdetailedvisualmorphologymeasurementsfromvolunteersanddeeplearningfor314000galaxies-2021","role":"author","urls":{"Paper":"http://adsabs.harvard.edu/abs/2021arXiv210208414W"},"keyword":["Astrophysics - Astrophysics of Galaxies","Computer Science - Computer Vision and Pattern Recognition"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/polyphant","dataSources":["7gvjSdWrEu7z5vjjj"],"keywords":["astrophysics - astrophysics of galaxies","computer science - computer vision and pattern recognition"],"search_terms":["galaxy","zoo","decals","detailed","visual","morphology","measurements","volunteers","deep","learning","314","000","galaxies","walmsley","lintott","geron","kruk","krawczyk","willett","bamford","keel","kelvin","fortson","masters","mehta","simmons","smethurst","baeten","macmillan"],"title":"Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies","year":2021}