Optimizing Astrophysical Model Parameters Through Deep Learning Methods

Presenter: Zachary M. Stomski

Faculty Sponsor: Ali Al-Faris

School: Worcester State University

Research Area: Computer Science

Session: Poster Session 2, 11:30 AM - 12:15 PM, Auditorium, A69

ABSTRACT

Determining optimal physical conditions for astrochemical modeling is challenging due to the large number of parameters involved and their strong interdependencies. Many of these parameters influence molecular abundances in complex, nonlinear ways, making manual tuning difficult and often subjective. Traditionally, researchers have addressed this challenge by adjusting only a subset of parameters deemed most important while ignoring others, which often leads to biased or suboptimal results. To address this, I developed and trained a deep learning neural network to optimize physical parameters based on molecular abundances of astrophysical sources. This was done using the three-phase PNAUTILUS codebase, which can produce accurate results of an astronomical source's molecular abundances over time given input parameters. By running PNAUTILUS simulations with the model's predictions and comparing the results with observational data, the neural network iteratively refines parameter estimates to achieve the best possible fit. The model itself was developed in Python, using its robust machine learning and data analysis libraries such as NumPy, pandas, PyTorch, and SKLearn. This approach streamlines the process for producing parameters, reduces human bias in parameter selection, enables more consistent and reliable simulations, and ultimately promotes comparability across publications. While our primary focus was fitting parameters for TMC-1, the model is adaptable to any astronomical source given the appropriate data.

RELATED ABSTRACTS