[astro-ph.IM] The astronomical community’s ability to use modern machine learning shapes the science return of upcoming facilities.
Recent community assessments single out education as the principal barrier to adoption, because what limits uptake is the uneven understanding of these methods rather than their availability.
The NASA Cosmic Origins Artificial Intelligence and Machine Learning Science and Technology Interest Group (AI/ML STIG) was formed to address this gap through short, domain-specific tutorials and community discussion. We present Deep Learning for Astrophysics, a freely available textbook at this https URL, curated from the group’s lecture series.
It collects 23 chapters across six parts from 17 lecturers, running from computational foundations and deep-learning architectures through generative modeling, simulation-based inference, and reinforcement learning to large-language-model agents, and closing with the practice of AI-laden science.
Many chapters include executable notebooks. We also outline the group’s plan for the coming year, centered on agentic research and on NASA’s ASTRA mission-concept initiative.
Yuan-Sen Ting, Digvijay Wadekar, Phill Cargile, Carol Cuesta-Lazaro, André Curtis-Trudel, Gregory Green, Ryan McClelland, Daniel Muthukrishna, Tri Nguyen, Helen Qu, Tomasz Rozanski, Anna Scaife, Jesse Thaler, Licia Verde, Francisco Villaescusa-Navarro, John F. Wu, Duo Xu, Siyu Yao, Alex Gagliano, Siddharth Mishra-Sharma, Andrew K. Saydjari, Georgios Valogiannis, Peter Kurczynski, Swara Ravindranath
Comments: 4 pages, 1 figure; Submitted to Research Notes of the AAS (RNAAS)
Subjects: Instrumentation and Methods for Astrophysics (astro-ph.IM)
Cite as: arXiv:2606.30855 [astro-ph.IM] (or arXiv:2606.30855v1 [astro-ph.IM] for this version)
https://doi.org/10.48550/arXiv.2606.30855
Focus to learn more
Submission history
From: Yuan-Sen Ting Assoc. Prof.
[v1] Mon, 29 Jun 2026 19:37:39 UTC (751 KB)
https://arxiv.org/abs/2606.30855
Astrobiology, Astrophysics,
