DOE OSTI · 3018480
Toward Complete Merger Identification at Cosmic Noon with Deep Learning
Abstract
As we enter the era of large imaging surveys such as $\textit{Roman}$, Rubin, and $\textit{Euclid}$, a deeper understanding of potential biases and selection effects in optical astronomical catalogs created with the use of ML-based methods is paramount. This work focuses on a deeper understanding of the performance and limitations of deep learning-based classifiers as tools for galaxy merger identification. We train a ResNet18 model on mock Hubble Space Telescope CANDELS images from the IllustrisTNG50 simulation. Our focus is on a more challenging classification of galaxy mergers and nonmergers at higher redshifts $1
Keep this discovery
Explore connections, maps & timelines
Schechter, Aimee [Colorado U.] (ORCID:0000000171202433), Ciprijanović, Aleksandra [Fermilab; Chicago U., Astron. Astrophys. Ctr.] (ORCID:0000000312817192), Nevin, Rebecca [Fermilab] (ORCID:0000000310568401), Comerford, Julie [Colorado U.] (ORCID:0000000186274907), Shen, Xuejian [Unlisted; MIT] (ORCID:000000026196823X), Stemo, Aaron [Vanderbilt U.], Blecha, Laura [Florida U.] (ORCID:0000000221831087). 2025-11-19. Toward Complete Merger Identification at Cosmic Noon with Deep Learning. https://www.osti.gov/biblio/3018480
Cite the original work for its findings. Save a collection to share your selection of sources.