astronolan/legacysurveys-dr10-embeddings

---
pretty_name: "Legacy Survey DR10 Embeddings for 100M+ Galaxies"
license: mit

tags:
- astronomy
- galaxy-embeddings
- clip
- aion
- semantic-search

size_categories:
- 10M<n<100M

datasets:
- legacy

citation: |
@inproceedings{koblischke2025why,
title={Why wait for human annotations when you have AI? Semantic searching scientific images with synthetic labels},
author={Nolan Koblischke and Liam Parker and Francois Lanusse and Irina Espejo Morales and Jo Bovy and Shirley Ho},
booktitle={NeurIPS 2025 AI for Science Workshop},
year={2025},
url={https://openreview.net/forum?id=j8Qxvb37HQ}
}
---

# Legacy DR10 Embeddings
[](https://arxiv.org/abs/2512.11982)

AION-Search and AION-1-B embeddings for 100M+ Legacy DR10 galaxies in the Multimodal Universe. 110,204,390 galaxies to be exact.

# License & data source
The embeddings and packaging in this repository are released under the MIT License.
The underlying catalog data are derived from the Legacy Survey DR10 and remain subject to the original Legacy Survey data-use policy and required acknowledgements.

# Embeddings Citation
```
@misc{koblischke2025semantic,
title={Semantic search for 100M+ galaxy images using AI-generated captions},
author={Nolan Koblischke and Liam Parker and Francois Lanusse and Irina Espejo Morales and Jo Bovy and Shirley Ho},
year={2025},
eprint={2512.11982},
archivePrefix={arXiv},
primaryClass={astro-ph.IM},
url={https://arxiv.org/abs/2512.11982},
}
```

# Legacy Dataset Citation
Data Release 10 (DR10) is the tenth public data release of the Legacy Surveys.

When using data from the Legacy Surveys in papers, please use the following acknowledgment:

The Legacy Surveys consist of three individual and complementary projects: the Dark Energy Camera Legacy Survey (DECaLS; Proposal ID #2014B-0404; PIs: David Schlegel and Arjun Dey), the Beijing-Arizona Sky Survey (BASS; NOAO Prop. ID #2015A-0801; PIs: Zhou Xu and Xiaohui Fan), and the Mayall z-band Legacy Survey (MzLS; Prop. ID #2016A-0453; PI: Arjun Dey). DECaLS, BASS and MzLS together include data obtained, respectively, at the Blanco telescope, Cerro Tololo Inter-American Observatory, NSF’s NOIRLab; the Bok telescope, Steward Observatory, University of Arizona; and the Mayall telescope, Kitt Peak National Observatory, NOIRLab. Pipeline processing and analyses of the data were supported by NOIRLab and the Lawrence Berkeley National Laboratory (LBNL). The Legacy Surveys project is honored to be permitted to conduct astronomical research on Iolkam Du’ag (Kitt Peak), a mountain with particular significance to the Tohono O’odham Nation.

NOIRLab is operated by the Association of Universities for Research in Astronomy (AURA) under a cooperative agreement with the National Science Foundation. LBNL is managed by the Regents of the University of California under contract to the U.S. Department of Energy.

This project used data obtained with the Dark Energy Camera (DECam), which was constructed by the Dark Energy Survey (DES) collaboration. Funding for the DES Projects has been provided by the U.S. Department of Energy, the U.S. National Science Foundation, the Ministry of Science and Education of Spain, the Science and Technology Facilities Council of the United Kingdom, the Higher Education Funding Council for England, the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign, the Kavli Institute of Cosmological Physics at the University of Chicago, Center for Cosmology and Astro-Particle Physics at the Ohio State University, the Mitchell Institute for Fundamental Physics and Astronomy at Texas A&M University, Financiadora de Estudos e Projetos, Fundacao Carlos Chagas Filho de Amparo, Financiadora de Estudos e Projetos, Fundacao Carlos Chagas Filho de Amparo a Pesquisa do Estado do Rio de Janeiro, Conselho Nacional de Desenvolvimento Cientifico e Tecnologico and the Ministerio da Ciencia, Tecnologia e Inovacao, the Deutsche Forschungsgemeinschaft and the Collaborating Institutions in the Dark Energy Survey. The Collaborating Institutions are Argonne National Laboratory, the University of California at Santa Cruz, the University of Cambridge, Centro de Investigaciones Energeticas, Medioambientales y Tecnologicas-Madrid, the University of Chicago, University College London, the DES-Brazil Consortium, the University of Edinburgh, the Eidgenossische Technische Hochschule (ETH) Zurich, Fermi National Accelerator Laboratory, the University of Illinois at Urbana-Champaign, the Institut de Ciencies de l’Espai (IEEC/CSIC), the Institut de Fisica d’Altes Energies, Lawrence Berkeley National Laboratory, the Ludwig Maximilians Universitat Munchen and the associated Excellence Cluster Universe, the University of Michigan, NSF’s NOIRLab, the University of Nottingham, the Ohio State University, the University of Pennsylvania, the University of Portsmouth, SLAC National Accelerator Laboratory, Stanford University, the University of Sussex, and Texas A&M University.

BASS is a key project of the Telescope Access Program (TAP), which has been funded by the National Astronomical Observatories of China, the Chinese Academy of Sciences (the Strategic Priority Research Program “The Emergence of Cosmological Structures” Grant # XDB09000000), and the Special Fund for Astronomy from the Ministry of Finance. The BASS is also supported by the External Cooperation Program of Chinese Academy of Sciences (Grant # 114A11KYSB20160057), and Chinese National Natural Science Foundation (Grant # 12120101003, # 11433005).

The Legacy Survey team makes use of data products from the Near-Earth Object Wide-field Infrared Survey Explorer (NEOWISE), which is a project of the Jet Propulsion Laboratory/California Institute of Technology. NEOWISE is funded by the National Aeronautics and Space Administration.

The Legacy Surveys imaging of the DESI footprint is supported by the Director, Office of Science, Office of High Energy Physics of the U.S. Department of Energy under Contract No. DE-AC02-05CH1123, by the National Energy Research Scientific Computing Center, a DOE Office of Science User Facility under the same contract; and by the U.S. National Science Foundation, Division of Astronomical Sciences under Contract No. AST-0950945 to NOAO.

CITATION
```
@ARTICLE{2019AJ....157..168D,
author = {{Dey}, Arjun and {Schlegel}, David J. and {Lang}, Dustin and {Blum}, Robert and {Burleigh}, Kaylan and {Fan}, Xiaohui and {Findlay}, Joseph R. and {Finkbeiner}, Doug and {Herrera}, David and {Juneau}, St{\'e}phanie and {Landriau}, Martin and {Levi}, Michael and {McGreer}, Ian and {Meisner}, Aaron and {Myers}, Adam D. and {Moustakas}, John and {Nugent}, Peter and {Patej}, Anna and {Schlafly}, Edward F. and {Walker}, Alistair R. and {Valdes}, Francisco and {Weaver}, Benjamin A. and {Y{\`e}che}, Christophe and {Zou}, Hu and {Zhou}, Xu and {Abareshi}, Behzad and {Abbott}, T.~M.~C. and {Abolfathi}, Bela and {Aguilera}, C. and {Alam}, Shadab and {Allen}, Lori and {Alvarez}, A. and {Annis}, James and {Ansarinejad}, Behzad and {Aubert}, Marie and {Beechert}, Jacqueline and {Bell}, Eric F. and {BenZvi}, Segev Y. and {Beutler}, Florian and {Bielby}, Richard M. and {Bolton}, Adam S. and {Brice{\~n}o}, C{\'e}sar and {Buckley-Geer}, Elizabeth J. and {Butler}, Karen and {Calamida}, Annalisa and {Carlberg}, Raymond G. and {Carter}, Paul and {Casas}, Ricard and {Castander}, Francisco J. and {Choi}, Yumi and {Comparat}, Johan and {Cukanovaite}, Elena and {Delubac}, Timoth{\'e}e and {DeVries}, Kaitlin and {Dey}, Sharmila and {Dhungana}, Govinda and {Dickinson}, Mark and {Ding}, Zhejie and {Donaldson}, John B. and {Duan}, Yutong and {Duckworth}, Christopher J. and {Eftekharzadeh}, Sarah and {Eisenstein}, Daniel J. and {Etourneau}, Thomas and {Fagrelius}, Parker A. and {Farihi}, Jay and {Fitzpatrick}, Mike and {Font-Ribera}, Andreu and {Fulmer}, Leah and {G{\"a}nsicke}, Boris T. and {Gaztanaga}, Enrique and {George}, Koshy and {Gerdes}, David W. and {Gontcho}, Satya Gontcho A. and {Gorgoni}, Claudio and {Green}, Gregory and {Guy}, Julien and {Harmer}, Diane and {Hernandez}, M. and {Honscheid}, Klaus and {Huang}, Lijuan Wendy and {James}, David J. and {Jannuzi}, Buell T. and {Jiang}, Linhua and {Joyce}, Richard and {Karcher}, Armin and {Karkar}, Sonia and {Kehoe}, Robert and {Kneib}, Jean-Paul and {Kueter-Young}, Andrea and {Lan}, Ting-Wen and {Lauer}, Tod R. and {Le Guillou}, Laurent and {Le Van Suu}, Auguste and {Lee}, Jae Hyeon and {Lesser}, Michael and {Perreault Levasseur}, Laurence and {Li}, Ting S. and {Mann}, Justin L. and {Marshall}, Robert and {Mart{\'\i}nez-V{\'a}zquez}, C.~E. and {Martini}, Paul and {du Mas des Bourboux}, H{\'e}lion and {McManus}, Sean and {Meier}, Tobias Gabriel and {M{\'e}nard}, Brice and {Metcalfe}, Nigel and {Mu{\~n}oz-Guti{\'e}rrez}, Andrea and {Najita}, Joan and {Napier}, Kevin and {Narayan}, Gautham and {Newman}, Jeffrey A. and {Nie}, Jundan and {Nord}, Brian and {Norman}, Dara J. and {Olsen}, Knut A.~G. and {Paat}, Anthony and {Palanque-Delabrouille}, Nathalie and {Peng}, Xiyan and {Poppett}, Claire L. and {Poremba}, Megan R. and {Prakash}, Abhishek and {Rabinowitz}, David and {Raichoor}, Anand and {Rezaie}, Mehdi and {Robertson}, A.~N. and {Roe}, Natalie A. and {Ross}, Ashley J. and {Ross}, Nicholas P. and {Rudnick}, Gregory and {Safonova}, Sasha and {Saha}, Abhijit and {S{\'a}nchez}, F. Javier and {Savary}, Elodie and {Schweiker}, Heidi and {Scott}, Adam and {Seo}, Hee-Jong and {Shan}, Huanyuan and {Silva}, David R. and {Slepian}, Zachary and {Soto}, Christian and {Sprayberry}, David and {Staten}, Ryan and {Stillman}, Coley M. and {Stupak}, Robert J. and {Summers}, David L. and {Sien Tie}, Suk and {Tirado}, H. and {Vargas-Maga{\~n}a}, Mariana and {Vivas}, A. Katherina and {Wechsler}, Risa H. and {Williams}, Doug and {Yang}, Jinyi and {Yang}, Qian and {Yapici}, Tolga and {Zaritsky}, Dennis and {Zenteno}, A. and {Zhang}, Kai and {Zhang}, Tianmeng and {Zhou}, Rongpu and {Zhou}, Zhimin},
title = "{Overview of the DESI Legacy Imaging Surveys}",
journal = {\aj},
keywords = {catalogs, surveys, Astrophysics - Instrumentation and Methods for Astrophysics},
year = 2019,
month = may,
volume = {157},
number = {5},
eid = {168},
pages = {168},
doi = {10.3847/1538-3881/ab089d},
archivePrefix = {arXiv},
eprint = {1804.08657},
primaryClass = {astro-ph.IM},
adsurl = {https://ui.adsabs.harvard.edu/abs/2019AJ....157..168D},
adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}
```

pretty_name: "1亿+星系的遗产巡天DR10嵌入向量（Legacy Survey DR10 Embeddings for 100M+ Galaxies）
license: MIT许可证

tags:
- 天文学
- 星系嵌入向量
- CLIP
- AION
- 语义搜索

size_categories:
- 10M<n<100M

datasets:
- 遗产巡天（legacy）

citation: |
@inproceedings{koblischke2025why,
title={拥有AI时何必等待人工标注：基于AI生成标注的1亿+科学图像语义搜索},
author={Nolan Koblischke and Liam Parker and Francois Lanusse and Irina Espejo Morales and Jo Bovy and Shirley Ho},
booktitle={NeurIPS 2025 AI for Science Workshop},
year={2025},
url={https://openreview.net/forum?id=j8Qxvb37HQ}
}

# 遗产DR10嵌入向量
[](https://arxiv.org/abs/2512.11982)

多模态宇宙中1亿以上遗产DR10星系的AION-Search与AION-1-B嵌入向量，准确数量为110,204,390个星系。

# 许可证与数据源
本仓库中的嵌入向量与打包文件采用MIT许可证发布。底层目录数据源自遗产巡天DR10，仍需遵守遗产巡天原始数据使用政策与致谢要求。

# 嵌入向量引用

@misc{koblischke2025semantic,
title={基于AI生成标注的1亿+星系图像语义搜索},
author={Nolan Koblischke and Liam Parker and Francois Lanusse and Irina Espejo Morales and Jo Bovy and Shirley Ho},
year={2025},
eprint={2512.11982},
archivePrefix={arXiv},
primaryClass={astro-ph.IM},
url={https://arxiv.org/abs/2512.11982},
}

# 遗产数据集引用
数据发布10（DR10）是遗产巡天的第十次公开数据发布。

当在论文中使用遗产巡天的数据时，请使用以下致谢语：

遗产巡天包含三个独立且互补的项目：暗能量相机遗产巡天（DECaLS；项目编号#2014B-0404；首席研究员：David Schlegel与Arjun Dey）、北京-亚利桑那巡天（BASS；美国国家光学天文台（NOAO）项目编号#2015A-0801；首席研究员：徐周（Zhou Xu）与范晓辉（Xiaohui Fan）），以及梅奥尔z波段遗产巡天（MzLS；项目编号#2016A-0453；首席研究员：Arjun Dey）。DECaLS、BASS与MzLS分别使用位于托洛洛山美洲际天文台（Cerro Tololo Inter-American Observatory）的布兰科（Blanco）望远镜、亚利桑那大学斯图尔德天文台（Steward Observatory）的伯克（Bok）望远镜，以及基特峰国家天文台（Kitt Peak National Observatory）的梅奥尔（Mayall）望远镜获取数据，上述天文台均隶属于美国国家科学基金会（NSF）的NOIRLab。数据的流水线处理与分析由NOIRLab与劳伦斯伯克利国家实验室（Lawrence Berkeley National Laboratory, LBNL）提供支持。遗产巡天项目十分荣幸能够获准在托霍诺奥奥哈姆民族（Tohono O’odham Nation）具有特殊意义的伊奥卡姆杜阿格（Iolkam Du’ag，即基特峰）开展天文研究。

NOIRLab由大学天文研究协会（Association of Universities for Research in Astronomy, AURA）依据与美国国家科学基金会合作运营。LBNL由加州大学董事会依据与美国能源部签订的合同管理。

本项目使用了暗能量相机（Dark Energy Camera, DECam）获取的数据，该相机由暗能量巡天（Dark Energy Survey, DES）合作项目建造。暗能量巡天项目的资金由美国能源部、美国国家科学基金会、西班牙科学与教育部、英国科学与技术设施理事会、英格兰高等教育拨款委员会、伊利诺伊大学厄巴纳-香槟分校国家超级计算应用中心、芝加哥大学卡夫利宇宙物理研究所、俄亥俄州立大学宇宙学与天体粒子物理中心、德克萨斯农工大学基础物理与天文学米切尔研究所、Financiadora de Estudos e Projetos、卡洛斯·查加斯·菲洛·里奥热内卢州研究资助基金会、Conselho Nacional de Desenvolvimento Cientifico e Tecnologico与巴西科学、技术与创新部、德国研究基金会，以及暗能量巡天合作机构提供。暗能量巡天合作机构包括：阿贡国家实验室、加州大学圣克鲁兹分校、剑桥大学、马德里能源环境与技术研究中心、芝加哥大学、伦敦大学学院、DES-巴西联盟、爱丁堡大学、苏黎世联邦理工学院（ETH Zurich）、费米国家加速器实验室、伊利诺伊大学厄巴纳-香槟分校、加泰罗尼亚空间研究所（IEEC/CSIC）、高能物理研究所、劳伦斯伯克利国家实验室、慕尼黑路德维希马克西米利安大学及其卓越宇宙集群、密歇根大学、NSF旗下NOIRLab、诺丁汉大学、俄亥俄州立大学、宾夕法尼亚大学、朴茨茅斯大学、SLAC国家加速器实验室、斯坦福大学、萨塞克斯大学，以及德克萨斯农工大学。

BASS是望远镜访问计划（Telescope Access Program, TAP）的核心项目，该计划由中国国家天文台、中国科学院（"The Emergence of Cosmological Structures"战略优先研究计划编号XDB09000000）以及财政部天文专项资助。BASS同时得到中国科学院对外合作项目（编号114A11KYSB20160057）与中国国家自然科学基金（编号12120101003、11433005）支持。

遗产巡天团队使用了近地天体广角红外巡天探测器（Near-Earth Object Wide-field Infrared Survey Explorer, NEOWISE）的数据产品，该项目由喷气推进实验室/加州理工学院运营。NEOWISE由美国国家航空航天局（NASA）资助。

遗产巡天对DESI天区的成像工作由美国能源部科学办公室高能物理办公室依据合同DE-AC02-05CH1123提供支持，同时由美国能源部科学用户设施国家能源研究科学计算中心（National Energy Research Scientific Computing Center, NERSC）依据同一合同提供支持，并由美国国家科学基金会天文科学分部依据合同AST-0950945向NOAO提供支持。

正式引用

@ARTICLE{2019AJ....157..168D,
author = {{Dey}, Arjun and {Schlegel}, David J. and {Lang}, Dustin and {Blum}, Robert and {Burleigh}, Kaylan and {Fan}, Xiaohui and {Findlay}, Joseph R. and {Finkbeiner}, Doug and {Herrera}, David and {Juneau}, Stéphanie and {Landriau}, Martin and {Levi}, Michael and {McGreer}, Ian and {Meisner}, Aaron and {Myers}, Adam D. and {Moustakas}, John and {Nugent}, Peter and {Patej}, Anna and {Schlafly}, Edward F. and {Walker}, Alistair R. and {Valdes}, Francisco and {Weaver}, Benjamin A. and {Yèche}, Christophe and {Zou}, Hu and {Zhou}, Xu and {Abareshi}, Behzad and {Abbott}, T.~M.~C. and {Abolfathi}, Bela and {Aguilera}, C. and {Alam}, Shadab and {Allen}, Lori and {Alvarez}, A. and {Annis}, James and {Ansarinejad}, Behzad and {Aubert}, Marie and {Beechert}, Jacqueline and {Bell}, Eric F. and {BenZvi}, Segev Y. and {Beutler}, Florian and {Bielby}, Richard M. and {Bolton}, Adam S. and {Briceño}, César and {Buckley-Geer}, Elizabeth J. and {Butler}, Karen and {Calamida}, Annalisa and {Carlberg}, Raymond G. and {Carter}, Paul and {Casas}, Ricard and {Castander}, Francisco J. and {Choi}, Yumi and {Comparat}, Johan and {Cukanovaite}, Elena and {Delubac}, Timothée and {DeVries}, Kaitlin and {Dey}, Sharmila and {Dhungana}, Govinda and {Dickinson}, Mark and {Ding}, Zhejie and {Donaldson}, John B. and {Duan}, Yutong and {Duckworth}, Christopher J. and {Eftekharzadeh}, Sarah and {Eisenstein}, Daniel J. and {Etourneau}, Thomas and {Fagrelius}, Parker A. and {Farihi}, Jay and {Fitzpatrick}, Mike and {Font-Ribera}, Andreu and {Fulmer}, Leah and {Gänsicke}, Boris T. and {Gaztanaga}, Enrique and {George}, Koshy and {Gerdes}, David W. and {Gontcho}, Satya Gontcho A. and {Gorgoni}, Claudio and {Green}, Gregory and {Guy}, Julien and {Harmer}, Diane and {Hernandez}, M. and {Honscheid}, Klaus and {Huang}, Lijuan Wendy and {James}, David J. and {Jannuzi}, Buell T. and {Jiang}, Linhua and {Joyce}, Richard and {Karcher}, Armin and {Karkar}, Sonia and {Kehoe}, Robert and {Kneib}, Jean-Paul and {Kueter-Young}, Andrea and {Lan}, Ting-Wen and {Lauer}, Tod R. and {Le Guillou}, Laurent and {Le Van Suu}, Auguste and {Lee}, Jae Hyeon and {Lesser}, Michael and {Perreault Levasseur}, Laurence and {Li}, Ting S. and {Mann}, Justin L. and {Marshall}, Robert and {Martínez-Vázquez}, C.~E. and {Martini}, Paul and {du Mas des Bourboux}, Hélion and {McManus}, Sean and {Meier}, Tobias Gabriel and {Ménard}, Brice and {Metcalfe}, Nigel and {Muñoz-Gutiérrez}, Andrea and {Najita}, Joan and {Napier}, Kevin and {Narayan}, Gautham and {Newman}, Jeffrey A. and {Nie}, Jundan and {Nord}, Brian and {Norman}, Dara J. and {Olsen}, Knut A.~G. and {Paat}, Anthony and {Palanque-Delabrouille}, Nathalie and {Peng}, Xiyan and {Poppett}, Claire L. and {Poremba}, Megan R. and {Prakash}, Abhishek and {Rabinowitz}, David and {Raichoor}, Anand and {Rezaie}, Mehdi and {Robertson}, A.~N. and {Roe}, Natalie A. and {Ross}, Ashley J. and {Ross}, Nicholas P. and {Rudnick}, Gregory and {Safonova}, Sasha and {Saha}, Abhijit and {Sánchez}, F. Javier and {Savary}, Elodie and {Schweiker}, Heidi and {Scott}, Adam and {Seo}, Hee-Jong and {Shan}, Huanyuan and {Silva}, David R. and {Slepian}, Zachary and {Soto}, Christian and {Sprayberry}, David and {Staten}, Ryan and {Stillman}, Coley M. and {Stupak}, Robert J. and {Summers}, David L. and {Sien Tie}, Suk and {Tirado}, H. and {Vargas-Magaña}, Mariana and {Vivas}, A. Katherina and {Wechsler}, Risa H. and {Williams}, Doug and {Yang}, Jinyi and {Yang}, Qian and {Yapici}, Tolga and {Zaritsky}, Dennis and {Zenteno}, A. and {Zhang}, Kai and {Zhang}, Tianmeng and {Zhou}, Rongpu and {Zhou}, Zhimin},
title={DESI遗产成像巡天概述},
journal={《天文期刊》（AJ）},
keywords={星表、巡天、天体物理学 - 仪器与方法},
year = 2019,
month = may,
volume = {157},
number = {5},
eid = {168},
pages = {168},
doi = {10.3847/1538-3881/ab089d},
archivePrefix = {arXiv},
eprint = {1804.08657},
primaryClass = {astro-ph.IM},
adsurl = {https://ui.adsabs.harvard.edu/abs/2019AJ....157..168D},
adsnote = {由SAO/NASA天体物理学数据系统提供}
}