NSF-BSF: Choreographing Astrophysical Turbulence Using Machine Learning, Simulations, and Novel Analytic Modeling

Turbulence is widespread in cosmic environments, yet understanding it, especially in star formation, is challenging. This proposal aims to enhance our grasp by combining traditional modeling with machine learning. The focus is on developing an observationally testable star formation model using three approaches: creating machine learning tools, testing analytic models, and applying machine learning to symbolic star formation prescriptions. The broader impacts involve connecting science and art through a dance collaboration and developing an educational program, CATS, to become a gold standard in turbulence machine learning.