SkAI-Funded Research Projects: Year 1 (2024-25) and Year 2 (2025-26)

Lead PIs: Gautham Narayan (UIUC; gsn at illinois.edu), Noelle Samia (NU)
Co-PIs: Daniel Apley (NU), Matthew Krafczyk (UIUC), Adam Miller (NU)
Collaborators: Jesus Carabello Anaya [Massachusetts Institute of Technology (MIT)], Arjun Chainani (UIUC), Alex Gagliano (MIT), Jennifer Li (UIUC), Michael Lukaszyk (UIUC), Daniel Muthukrishna (MIT), Jack O’Brien (UIUC), Este Padilla Gonzalez (Space Telescope Science Institute), Haille Perkins (UIUC), Nabeel Rehmatulla (NU), Ved Shah (NU), Amanda Wasserman (UIUC), Jiezhong Wu (NU), Yuqing Yang (NU)
Project Summary: This project aims to build a foundational AI model that would form a core part of a community pipeline for Rubin to identify (including anomalies) and characterize transients and set priorities for follow-up observations. The foundation model will be based on a new custom variational autoencoder (VAE) architecture, optimized for the sparse, multimodal and irregular data, and both observational data and emulated data from (physical) transient models. In year 2, the VAE will be replaced by a transformer.

Click here to visit the project web page.

Lead PIs: Han Liu (NU), Adam Miller (NU)
Collaborators: Hong-Yu Chen (NU), Weijian Li (NU), Qinjie Lin (NU), Nabeel Rehemtulla (NU), Ved Shah (NU), Padma Venkatraman (UIUC)
Project Summary: This project seeks to predict nonuniformly sampled time-series data using artificial intelligence with uncertainty quantification. The main goal is astronomical time-series data, mainly from stars within the Zwicky Transient Facility (ZTF) survey, but ultimately applicable to Rubin/Legacy Survey of Space and Time (LSST) and even other domains.

Click here to visit the project web page.

Lead PIs: Emma Alexander (NU), Tjitske Starkenburg (NU)
Co-PIs: Chihway Chang (UC), Alex Drlica-Wagner (UC), Joshua Frieman (UC), Aggelos Katsaggelos (NU), Rebecca Willett (UC), Michael Zevin (Adler)
Collaborators: Aadya Agrawal (UIUC), Bilguun Batbayar (UC), Vasilis Charisopoulos (UC), Aleksandra Ćiprijanović (Fermilab), Jimena Gonzalez (UW–Madison), Tianao Li (NU), Travis Rector (U Alaska Anchorage)
Project Summary: This project has the following objectives: (1) remove distortions from astrophysical images by modeling the image formation process, (2) initially focus on simpler distortion models (convolution, noising), and (3) subsequently, develop a system to handle gravitational lensing. These objectives will be met using (1) a differentiable image synthesis pipeline comprising three components: (a) implicit image representations (e.g., SIREN) to act as per-image prior, (b) conditional generative model (normalizing flows or diffusion) to capture data distribution, and (c) differentiable nonlinear forward model to capture physics-based distortions (e.g., lensing); and (2) uncertainty quantification.

Click here to visit the project web page.

Lead PIs: William Moses (UIUC), Joaquin Vieira (UIUC)
Co-PIs: Tom Crawford (UC), Laura Trouille (Adler), Michael Zevin (Adler)
Collaborators: Melanie Archipley (UC), Jennifer Li (UIUC), Felipe Menanteau (UIUC), Sydnee O’Donnell (UIUC), Kedar Phadke (UIUC; kphadke2 at illinois.edu), Siyuan Brant Qian (UIUC), Vimarsh Sathia (UIUC)
Project Summary: This project aims to develop an automated Bayesian inference tool for millimeter source association [cross-matching South Pole Telescope (SPT) sources with other surveys]. Correct associations to observations in different wavelengths are necessary to reconstruct spectral energy distributions (SEDs) and infer properties and redshifts of astrophysical objects. Bayesian inference is one of the methods to do this, but due to large numbers of objects that will be available from the current and future surveys, faster methods are necessary. This project aims to use machine learning (ML) to automate Bayesian inference, focusing on advancements in differentiable and probabilistic programming. Unlike existing differential programming problems, this project will incorporate the use of discrete variables, which are not handled well by existing automatic differentiation (AD) frameworks. The team plans to build a Zooniverse project to confirm source associations via visual inspection by volunteers.

Click here to visit the project web page.

Lead PIs: Rina Foygel Barber (UC), Daniel Holz (UC)
Collaborators: Samuel Dyson (UC), Ruiting Liang (UC)
Project Summary: This project is on coincidence detection for time-domain multiwavelength and multimessenger data. Specifically, the project includes testing assumptions in current coincidence-detection techniques and describing uncertainty quantification for this method. Additionally, options for more robust detection techniques will be explored.

Click here to visit the project website.

Lead PIs: Chihway Chang (UC), Rebecca Willett (UC)
Co-PIs: Joshua Frieman (UC), Moritz Münchmeyer (UW–Madison), Daniel Sanz-Alonso (UC)
Collaborators: Shrihan Agarwal (UC), Dhayaa Anbajagane (UC), Scott Dodelson (UC), Chun-Hao To (UC), Yuuki Omori (UC), Benjamin Remy (Princeton University), Georgios Valogiannis (UC), Shi-Hui Zang (UW–Madison), Roy Zhao (UC), Alan Zhou (UC)
Project Summary: Inverse problems are concerned with estimating model parameters from indirect, noisy measurements. This project will develop novel artificial intelligence (AI) and data science techniques to solve a key inverse problem in cosmology: reconstructing the initial conditions of the universe from present-day measurements. Our new methods will address important challenges present in this and other inverse problems in cosmology, including scalability to large datasets, complexity of the forward model, and the need to quantify the uncertainty in the parameter estimation. On the other hand, this project will curate new datasets and make them publicly available to benchmark AI techniques for a new class of inverse problems, thus paving the way for future AI algorithmic innovation. Our project will bring together cosmologists, computer scientists, statisticians, and computational mathematicians, facilitating interdisciplinary and collaborative training.

Click here to visit the project web page.

Lead PIs: Jeff McMahon (UC), Ermin Wei (NU; ermin.wei at northwestern.edu)
Co-PI: Yuxin Chen (UC)
Collaborator: Juliang Li (ANL)
Project Summary: This project targets AI-informed astronomical instrument design for millimeter-wave spectrometers. The project is broken into two tasks: Task 1 seeks to leverage deep neural networks to more expansively explore the space of demultiplexer spectrometer designs by building a mapping between topology and performance; Task 2 seeks to leverage multifidelity simulations (deep kernel Bayesian optimization) to efficiently explore the design space. Potential impacts would be in the design of new astronomical instrumentation and the AI tools for optimizing instrument design.

Click here to visit the project web page.

Lead PIs: Alex Drlica-Wagner (UC), Aravindan Vijayaraghavan (NU)
Collaborators: Emma Alexander (NU), Paul Chichura (UC), Ani Chiti (UC), Aleksandra Ćiprijanović (Fermilab), Alexander Ji (UC), Guilherme Limberg (UC), Adam Miller (NU), Gautham Narayan (UIUC), Brian Nord (Fermilab), Tanmay Sinha (NU)
Project Summary: This project has the following objectives: (1) develop reinforcement-learning (RL) algorithms for dynamic, real-time astronomical observation scheduling with deferred, multi-objective rewards; and (2) use active learning and weak-to-strong supervision to optimize target selection for population-level parameter inference. These objectives will be met by (1) leveraging state-of-the-art AI techniques, including RL, active learning, and conformal prediction; and (2) using ∼500k observations from the Dark Energy Camera (DECam) for model training and validation.

Click here to visit the project web page.

Lead PIs: Aleksandra Ćiprijanović (Fermilab; aleksand at fnal.gov), Sandeep Madireddy (Argonne National Laboratory)
Co-PIs: Alexander Ji (UC), Aggelos Katsaggelos (NU), Michael Maire (UC), Tjitske Starkenburg (NU), Allison Strom (NU), Michael Zevin (Adler)
Collaborator: Gourav Khullar (U Washington)
Project Summary: This project aims to develop AI methods for studying the evolution of galaxies, including generative models to create synthetic data and inference tools for learning galaxy properties.

Click here to visit the project web page.