Levi Galvan L&S Math & Physical Sciences
Physics-Informed Neural Networks (PINN) for Exoplanet Detection
This project aims to create a physics-informed convolutional neural network (CNN) to improve the detection and characterization of Earth-like exoplanets from stellar light curves, especially in the low signal-to-noise regime. Traditional CNNs have shown promising performance in classifying transit signals but often function as “black boxes,” relying solely on data-driven features and ignoring key astrophysical constraints. To address this, my approach embeds analytical transit models and physical priors such as limb-darkening, transit symmetry, and realistic depth-duration relationships directly into the network’s architecture or loss function. These constraints will guide the model toward physically plausible outputs and reduce false positives. The model will be trained on real light curves from Kepler and TESS, with synthetic transits injected to evaluate recovery rates under noisy conditions. While a full detection pipeline is most likely beyond the scope of the summer, this work will lay the foundation for a more interpretable and robust detection method.
Message To Sponsor
I want to express my upmost gratitude for your generous support of my summer research through the SURF Fellowship. This experience has been amazing both academically and personally, I grew so much as an independent scholar by conducting original research on exoplanet detection using machine learning, and I developed the confidence to pursue complex scientific questions without the fear of failure. The fellowship solidified my goal of continuing in astrophysics research, and it gave me a clearer vision of my future in graduate school and beyond. Thank you for making this opportunity possible and for investing in students like me.