Date of Graduation

5-2026

Document Type

Thesis

Degree Name

Bachelor of Science in Physics

Degree Level

Undergraduate

Department

Physics

Advisor/Mentor

Julia Kennefick

Committee Member

Jason Dittmann

Second Committee Member

Bret Lehmer

Third Committee Member

William Oliver

Abstract

Transmission spectroscopy is a powerful method for studying exoplanet atmospheres. With the recent launch of the James Webb Space Telescope (JWST), several molecules have been successfully detected in hot Jupiter atmospheres at an unprecedented level of precision with transmission spectroscopy. To better understand current detection capabilities and limitations, this project used machine learning techniques to determine which molecules are currently identifiable at the spectral resolution and wavelength range of JWST’s NIRSpec instrument in PRISM mode. A large synthetic dataset of transmission spectra was first generated using the petitRADTRANS radiative transfer Python package. The resulting spectra were then used to train a one-dimensional convolutional neural network that classifies atmospheric molecules. The trained model was first evaluated on synthetic test data and later applied to JWST observations of the hot Saturn exoplanet WASP-39b. The model was able to successfully detect H2O, CO2, and Na across four independent JWST data reduction pipelines and was consistent with the published observations. These results identify which molecules are reliably detectable in JWST’s NIRSpec PRISM mode and demonstrate that machine learning models trained on synthetic spectra can successfully generalize to real observations.

Keywords

Exoplanets; James Webb Space Telescope; Atmospheric Characterization

Download

Share

COinS