Institute for Advanced Study Informal Astrophysics Seminar

The interactions between forming stars and their environment shapes the natal cloud evolution, the efficiency at which stars form and the stellar initial mass function. Commonly, signatures of stellar feedback are identified “by eye.” However, this approach is challenging, time-consuming and subjective. Machine learning, a sub-field of computer science in which algorithms can learn and evolve without explicit programming, provides a powerful alternative to visual identification. In this talk I will show how a combination of state-of-the-art numerical simulations and citizen science together with machine learning can be harnessed to identify and study features created by stellar winds. I will describe different machine learning approaches and show the results of these approaches applied to dust emission and CO observations of nearby star-forming regions.