Project:	Generative Models for Precision Simulation of Nancy Grace Roman Telescope Imaging (JPL AO No. 16887)
Disciplines:	Astronomy, Computer Science
Mentor:	Eric Huff, (JPL), Eric.M.Huff@jpl.nasa.gov, Phone: (626) 460-9834
Background:	The Nancy Grace Roman Space Telescope is NASA's next flagship mission, slated for launch in the fall of 2026. One of Roman's primary science focuses will be the study of dark matter and dark energy using weak gravitational lensing. The planned Roman data analysis will require large volumes of realistic simulated images, incorporating both the real physical features of simulated galaxies as well as a wide variety of subtle detector and optical effects. Currently, physical models of galaxies cannot produce realistic systems in large enough numbers for this application, but our group's past work suggests that generative AI, trained on simulated images as well as real data from existing observatories, may be able to fill the gap.
Description:	The participant's goal will be to generate simulated images of galaxies as they will appear in the Nancy Grace Roman Space Telescope's High-Latitude Imaging Survey data, to add simulated gravitational lensing to these images, and to test whether the lensing signal can be accurately measured in the simulations. The participant will build on a large base of existing code, including the open-source GalSim image simulation package, as well as diffusion models that were trained for similar simulation purposes by this group in previous year.
References:	Recent paper on simulating Euclid galaxies with diffusion models: https://ui.adsabs.harvard.edu/abs/2025ApJ...985....2S/abstract Overview of the Nancy Grace Roman Space Telescope: https://science.nasa.gov/mission/roman-space-telescope/ GalSim repository: https://github.com/GalSim-developers/GalSim
Student Requirements:	Required: Coursework in machine learning/deep learning/computer vision, experience with Pytorch and scientific python (numpy, pandas, scipy, scikit-learn, etc.) Strongly recommended: Some astronomy background, such as an introductory course. Recommended: Familiarity with developing on remote systems, navigating bash, and high performance computing w/ GPUs.
Location / Safety:	Project building and/or room locations: . Student will need special safety training: .
Programs:	This AO can be done under the following programs:   Program    Available To        SURF@JPL    both Caltech and non-Caltech students  Click on a program name for program info and application requirements.