Abstract Number:
1275
Submission Type:
Invited Paper Session
Participants:
Vinay Kashyap (1) (,2), Yang Chen (3), Xiao-Li Meng (4), Cecilia Garraffo (5) (,2), Yang Chen (3), Vinay Kashyap (1) (,2), Kevin Jin (6), V. Ashley Villar (7), Daniel Muthukrishna (8)
Institutions:
(1) Center for Astrophysics , N/A, (2) Harvard & Smithsonian, N/A, (3) University of Michigan, N/A, (4) Harvard University, N/A, (5) Center for Astrophysics , Cambridge, MA, (6) University of Michigan, Ann Arbor, N/A, (7) N/A, N/A, (8) University of Cambridge, N/A
Chair:
Co-Organizer(s):
Discussant(s):
Session Organizer:
Speaker(s):
Session Description:
It is well known that early developments in Statistics were driven by astronomical data and analyses. It is well known, for example, that the motivation for the development of regression analysis by Gauss was the problem of locating the position of minor planet Ceres after emergence from Sun block. In recent times, Astrostatistics has driven new techniques in MCMC and Bayesian methodology. Astronomical data has steadily increased in both quantity and quality, with space telescopes like SDO/AIA, Hubble, Chandra, XMM-Newton, Gaia, TESS, and JWST producing copious data with unprecedented resolutions, and massive ground-based surveys like Rubin LSST and the Square Kilometer Array poised to cause a revolution in both astronomy and data science. Recently, astronomy has also been at the forefront of applications of Machine Learning methods.
We propose an invited session that focuses on the interface between Machine Learning, Statistics, and Astronomy, emphasizing the advances in statistical machine learning driven by astronomical data and analyses. In keeping with the theme of the JSM, this session will focus on the community of AI-aware astronomers bringing their unique perspectives to mesh together these cross-disciplinary topics. This is particularly relevant in Boston, which has one of the largest astrostatistical and astroinformatics communities in the world, and has been buzzing with activity in this field. Boston has several institutions that do space weather and astronomy, and concomitantly work in the overlap between these fields and both astrostatistics and AI (notably the CHASC Astrostatistics collaboration and AstroAI, both centered at the Center for Astrophysics | Harvard & Smithsonian). We will bring in three researchers working at the nexus of these fields to present talks at the session. Additionally, we will have two discussants synthesizing the current state of the art, one from an astronomer's perspective, and one from a statistician's perspective. Our proposed speakers and their nominal titles are:
1. Potentials and risks of adopting generative models in operational solar flare forecasting – Kevin Jin (Michigan)
2. Causally Motivated Foundation Models: Disentangling Physics from Systematics – Daniel Muthukrishna (MIT/CfA)
3. A Poisson Process AutoDecoder for X-ray Sources – Ashley Villar (Harvard)
Discussant 1 (Astro) – Cecilia Garraffo (CfA)
Discussant 2 (Stats) – Yang Chen (Michigan)
Each talk will be for 20 minutes, with 2 minutes each for Q&A. Furthermore, we note that this session is congruous to the aims of the Astrostatistics Interest Group (AIG) of the ASA, which seeks to highlight and advance astrostatistical learning and collaborations. This will be the first foray into AI by AIG.
Sponsors:
Astrostatistics Interest Group 3
Section on Physical and Engineering Sciences 1
Section on Statistical Learning and Data Science 2
Theme:
Communities in Action: Advancing Society
Yes
Applied
Yes
Estimated Audience Size
Small (<80)
I have read and understand that JSM participants must abide by the Participant Guidelines.
Yes
I understand and have communicated to my proposed speakers that JSM participants must register and pay the appropriate registration fee by June 1, 2026. The registration fee is nonrefundable.
I understand