Image de couverture de livre

Discovering Strong Gravitational Lenses in the Dark Energy Survey with Interactive Machine Learning and Crowd-sourced Inspection with Space Warps

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gonzalez, J., Holloway, P., Collett, T., Verma, A., Bechtol, K., Marshall, P., More, A., Barroso, J. Acevedo, Cartwright, G., Martinez, M., Li, T., Rojas, K., Schuldt, S., Birrer, S., Diehl, H. T., Morgan, R., Drlica-Wagner, A., O'Donnell, J. H., Zaborowski, E., Nord, B., Baeten, E. M., Johnson, L. C., Macmillan, C., Roodman, A., Pieres, A., Walker, A. R., Malagón, A. A. Plazas, Rosell, A. Carnero, Santiago, B., Flaugher, B., Gruen, D., Brooks, D., Burke, D. L., James, D. J., Cid, D. Sanchez, Hollowood, D. L., Tucker, D. L., Buckley-Geer, E., Gaztanaga, E., Suchyta, E., Sanchez, E., Gutierrez, G., Giannini, G., Tarle, G., Sevilla-Noarbe, I., Marshall, J. L., Carretero, J., Frieman, J., De Vicente, J., García-Bellido, J., Mena-Fernández, J., Myles, J., Honscheid, K., Kuehn, K., Lima, M., Pereira, M. E. S., Smith, M., Aguena, M., Weaverdyck, N., Lahav, O., Doel, P., Miquel, R., Gruendl, R. A., Cawthon, R., Hinton, S. R., Allam, S. S., Desai, S., Samuroff, S., Everett, S., Lee, S., Davis, T. M., Abbott, T. M. C., Vikram, V.
Format:	Preprint
Publié:	2025
Sujets:	Astrophysics of Galaxies
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

_version_	1866909587629670400
author	Gonzalez, J. Holloway, P. Collett, T. Verma, A. Bechtol, K. Marshall, P. More, A. Barroso, J. Acevedo Cartwright, G. Martinez, M. Li, T. Rojas, K. Schuldt, S. Birrer, S. Diehl, H. T. Morgan, R. Drlica-Wagner, A. O'Donnell, J. H. Zaborowski, E. Nord, B. Baeten, E. M. Johnson, L. C. Macmillan, C. Roodman, A. Pieres, A. Walker, A. R. Malagón, A. A. Plazas Rosell, A. Carnero Santiago, B. Flaugher, B. Gruen, D. Brooks, D. Burke, D. L. James, D. J. Cid, D. Sanchez Hollowood, D. L. Tucker, D. L. Buckley-Geer, E. Gaztanaga, E. Suchyta, E. Sanchez, E. Gutierrez, G. Giannini, G. Tarle, G. Sevilla-Noarbe, I. Marshall, J. L. Carretero, J. Frieman, J. De Vicente, J. García-Bellido, J. Mena-Fernández, J. Myles, J. Honscheid, K. Kuehn, K. Lima, M. Pereira, M. E. S. Smith, M. Aguena, M. Weaverdyck, N. Lahav, O. Doel, P. Miquel, R. Gruendl, R. A. Cawthon, R. Hinton, S. R. Allam, S. S. Desai, S. Samuroff, S. Everett, S. Lee, S. Davis, T. M. Abbott, T. M. C. Vikram, V.
author_facet	Gonzalez, J. Holloway, P. Collett, T. Verma, A. Bechtol, K. Marshall, P. More, A. Barroso, J. Acevedo Cartwright, G. Martinez, M. Li, T. Rojas, K. Schuldt, S. Birrer, S. Diehl, H. T. Morgan, R. Drlica-Wagner, A. O'Donnell, J. H. Zaborowski, E. Nord, B. Baeten, E. M. Johnson, L. C. Macmillan, C. Roodman, A. Pieres, A. Walker, A. R. Malagón, A. A. Plazas Rosell, A. Carnero Santiago, B. Flaugher, B. Gruen, D. Brooks, D. Burke, D. L. James, D. J. Cid, D. Sanchez Hollowood, D. L. Tucker, D. L. Buckley-Geer, E. Gaztanaga, E. Suchyta, E. Sanchez, E. Gutierrez, G. Giannini, G. Tarle, G. Sevilla-Noarbe, I. Marshall, J. L. Carretero, J. Frieman, J. De Vicente, J. García-Bellido, J. Mena-Fernández, J. Myles, J. Honscheid, K. Kuehn, K. Lima, M. Pereira, M. E. S. Smith, M. Aguena, M. Weaverdyck, N. Lahav, O. Doel, P. Miquel, R. Gruendl, R. A. Cawthon, R. Hinton, S. R. Allam, S. S. Desai, S. Samuroff, S. Everett, S. Lee, S. Davis, T. M. Abbott, T. M. C. Vikram, V.
contents	We conduct a search for strong gravitational lenses in the Dark Energy Survey (DES) Year 6 imaging data. We implement a pre-trained Vision Transformer (ViT) for our machine learning (ML) architecture and adopt Interactive Machine Learning to construct a training sample with multiple classes to address common types of false positives. Our ML model reduces 236 million DES cutout images to 22,564 targets of interest, including around 85% of previously reported galaxy-galaxy lens candidates discovered in DES. These targets were visually inspected by citizen scientists, who ruled out approximately 90% as false positives. Of the remaining 2,618 candidates, 149 were expert-classified as 'definite' lenses and 516 as 'probable' lenses, with 147 of these candidates being newly identified. Additionally, we trained a second ViT to find double-source plane lens systems, finding at least one double-source system. Our main ViT excels at identifying galaxy-galaxy lenses, consistently assigning high scores to candidates with high confidence. The top 800 ViT-scored images include around 100 of our `definite' lens candidates. This selection is an order of magnitude higher in purity than previous convolutional neural network-based lens searches and demonstrates the feasibility of applying our methodology for discovering large samples of lenses in future surveys.
format	Preprint
id	arxiv_https___arxiv_org_abs_2501_15679
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Discovering Strong Gravitational Lenses in the Dark Energy Survey with Interactive Machine Learning and Crowd-sourced Inspection with Space Warps Gonzalez, J. Holloway, P. Collett, T. Verma, A. Bechtol, K. Marshall, P. More, A. Barroso, J. Acevedo Cartwright, G. Martinez, M. Li, T. Rojas, K. Schuldt, S. Birrer, S. Diehl, H. T. Morgan, R. Drlica-Wagner, A. O'Donnell, J. H. Zaborowski, E. Nord, B. Baeten, E. M. Johnson, L. C. Macmillan, C. Roodman, A. Pieres, A. Walker, A. R. Malagón, A. A. Plazas Rosell, A. Carnero Santiago, B. Flaugher, B. Gruen, D. Brooks, D. Burke, D. L. James, D. J. Cid, D. Sanchez Hollowood, D. L. Tucker, D. L. Buckley-Geer, E. Gaztanaga, E. Suchyta, E. Sanchez, E. Gutierrez, G. Giannini, G. Tarle, G. Sevilla-Noarbe, I. Marshall, J. L. Carretero, J. Frieman, J. De Vicente, J. García-Bellido, J. Mena-Fernández, J. Myles, J. Honscheid, K. Kuehn, K. Lima, M. Pereira, M. E. S. Smith, M. Aguena, M. Weaverdyck, N. Lahav, O. Doel, P. Miquel, R. Gruendl, R. A. Cawthon, R. Hinton, S. R. Allam, S. S. Desai, S. Samuroff, S. Everett, S. Lee, S. Davis, T. M. Abbott, T. M. C. Vikram, V. Astrophysics of Galaxies We conduct a search for strong gravitational lenses in the Dark Energy Survey (DES) Year 6 imaging data. We implement a pre-trained Vision Transformer (ViT) for our machine learning (ML) architecture and adopt Interactive Machine Learning to construct a training sample with multiple classes to address common types of false positives. Our ML model reduces 236 million DES cutout images to 22,564 targets of interest, including around 85% of previously reported galaxy-galaxy lens candidates discovered in DES. These targets were visually inspected by citizen scientists, who ruled out approximately 90% as false positives. Of the remaining 2,618 candidates, 149 were expert-classified as 'definite' lenses and 516 as 'probable' lenses, with 147 of these candidates being newly identified. Additionally, we trained a second ViT to find double-source plane lens systems, finding at least one double-source system. Our main ViT excels at identifying galaxy-galaxy lenses, consistently assigning high scores to candidates with high confidence. The top 800 ViT-scored images include around 100 of our `definite' lens candidates. This selection is an order of magnitude higher in purity than previous convolutional neural network-based lens searches and demonstrates the feasibility of applying our methodology for discovering large samples of lenses in future surveys.
title	Discovering Strong Gravitational Lenses in the Dark Energy Survey with Interactive Machine Learning and Crowd-sourced Inspection with Space Warps
topic	Astrophysics of Galaxies
url	https://arxiv.org/abs/2501.15679