Learning how Stars Form: Harnessing Machine Learning to Extract Insights from Noisy Spectral Cubes

Colloquium

Speaker

  • Stella Offner

When

  • – ET

Where

162 Fifth Avenue, 5th Floor Classroom

160 Fifth Avenue

New York, NY 10010

Abstract

For decades astronomers have studied the distribution of gas in the interstellar medium by making 2-d dust emission maps and 3-d spectral line cubes. It is a community tradition to identify salient structures in these complex and noisy data, an undertaking affectionately known as “blob-ology.” In computer science and statistics, this type of data segmentation task is a fundamental algorithmic challenge that boils down to: what is the best way to robustly cluster data? In the star formation content, a variety of algorithms have been developed to identify dense cores and filaments, however, these methods all depend on user-set parameters that are often tuned by hand and validated by-eye.  In this talk I will discuss the pros and cons of supervised ML approaches to data segmentation and present results from a 3-d convolutional neural network model, which can accurately identify stellar feedback features in molecular line spectral cubes. I will introduce a new unsupervised approach to identify cohesive structures in hyperspectral cubes:  Multiview Prototype Embedding and Clustering (MPEC). MPEC learns prototypes of spectral data for efficient sample size reduction, embeds these prototypes in a lower dimensional latent space generated by a Self-Organizing variant of UMAP, and clusters a graph representation of (learned) prototype similarity in both feature and latent spaces.  I will review what such approaches teach us about star formation and discuss the prognosis for addressing outstanding star formation questions: Which gas will form stars? How does star-forming gas evolve? What is the future of observed molecular clouds?

Stella Offner: Learning how Stars Form: Harnessing Machine Learning to Extract Insights
A red, wireframe, spherical shape with wavy edges is centered on a light beige background, resembling a 3D mesh or abstract digital sculpture.

Event Series

CCA Colloquium

A weekly forum in computational astrophysics

Guest lectures on forefront astrophysical research topics aimed at non-expert professional physicists.

See events

More Events

November 19, 2026

11 a.m.–12 p.m. ET

Speaker

Andrea Califano, Ph.D.

Computational Astrophysics

Fast Radio Bursts

Colloquium

December 1, 2026

3–4 p.m. ET

Speaker

Vicky Kaspi

December 11, 2026

3–4 p.m. ET

Speaker

Kyle Kremer