News

Snigdaa Sethuram selected as Argonne’s Margaret Butler Fellow

Accelerating Astrophysics with AI: A Q&A with Snigdaa Sethuram, Argonne’s Margaret Butler Fellow

Author: Logan Ludwig. Published 06/30/2025 (original link)

In this Q&A, Sethuram shares insights into how she is using machine learning to study the early universe, the mentors who inspired her journey, and her aim to develop scalable tools for the scientific community.

The Argonne Leadership Computing Facility (ALCF), a U.S. Department of Energy (DOE) user facility located at DOE’s Argonne National Laboratory, has named postdoctoral researcher Snigdaa Sethuram the latest recipient of its Margaret Butler Fellowship in Computational Science. 

Sethuram, a computational astrophysicist, specializes in developing machine learning (ML) models to accelerate complex simulations of cosmic phenomena—from star formation to radiative transfer. She completed her graduate studies at Georgia Tech as a NASA FINESST fellow in Dr. John Wise’s computational cosmology group. Her work has led to performance improvements in modeling stellar feedback and spectral energy distributions, making simulation processing faster without sacrificing accuracy. 

The Margaret Butler Fellowship honors the legacy of Dr. Margaret Butler, a pioneering leader in computational science and nuclear energy who broke barriers as Argonne’s National Energy Software Center director and the first woman named a Fellow of the American Nuclear Society. 

In this Q&A, Sethuram reflects on her early inspiration from her mother’s love of coding, her research journey through the cosmos, and her vision for fostering scientific collaboration during her time at ALCF. 

Q: What drew you to apply for the Margaret Butler Fellowship? 

What drew me to the Margaret Butler Fellowship was how well it matched my goal of doing meaningful, high-impact work in computational science. Argonne’s leadership in high-performance computing (HPC) offers an incredible chance to work on transformative, exciting problems while learning from some of the best in the field. 

I was also really inspired by Dr. Margaret Butler’s legacy; not just as a pioneer in computational science, but as someone who opened doors for women in STEM. Being a recipient of a fellowship named after her feels both professionally meaningful and personally motivating. It reminds me of the kind of researcher and collaborator I hope to be—curious, rigorous, and committed to making science more inclusive. 

This fellowship felt like a great opportunity to grow as a scientist while contributing to work that matters. I’m excited to be part of something that blends technical challenge with broader impact. 

Q: What initially sparked your interest in the field of computer science? 

My interest in computer science started with my mom. She had a master’s in computer applications and, even while raising me and my brother, never stopped learning. I’d watch her casually mess with Python and C, which made me curious. In middle school, I tried reading her C manual, was completely lost, and swore coding wasn’t for me. But that changed in high school when I took a computer science course where we made small JavaScript programs, like a crab solving math puzzles to fight a starfish, and coding started to make sense. It felt like a game where logic and creativity came together. 

By college, I was hooked on the puzzle-solving side of programming and joined a computational astrophysics research group under Dr. Rachel Somerville, where I got to use code to study real science. Now, the thing that once intimidated me feels like a tool I can use to build and explore. That spark of turning ideas into solutions is what still drives my excitement for computer science. 

Q: What do you plan to do during your time in the fellowship?  

During my graduate research in Dr. John Wise’s group, I focused on using ML to make cosmological simulations, like those modeling the formation of the first stars and galaxies during the universe’s ‘epoch of reionization’, more efficient. By applying ML techniques, my work helped cut down on the heavy computational cost and time these simulations usually require, which has already shown promise in specific projects within my research group. 

Through the fellowship, I’d love to scale these approaches to tackle even bigger astrophysical challenges to benefit the wider community—like developing tools to streamline the comparison of simulations directly with real observational data. Bridging that gap between simulation experts and observers could help us all speak the same scientific ‘language,’ making collaborations smoother and insights faster and facilitating accelerated theory validation as we continue to launch more cutting-edge observatories. I’m very excited to learn from the expertise of the scientists at Argonne who have worked on similar projects with great success! 

Beyond the technical work, I’m eager to dive into Argonne’s collaborative culture. I hope to organize or contribute to workshops that share these computational tools with others, mentor students, and get involved in local Chicago outreach, especially with younger students still exploring their interests. Science communication is something I care deeply about, and I want to make complex topics like cosmic evolution feel accessible and exciting. 

This fellowship feels like the perfect launchpad to grow my technical toolkit, collaborate across fields, and turn research into real-world impact—all while honoring Margaret Butler’s legacy of innovation and mentorship. 

Q: Can you tell us about your current research project(s)? 

My current research focuses on using machine learning to speed up astrophysical simulations and data processing. The project I most recently worked on involved training a spatiotemporally-aware neural network to emulate stellar feedback—how stars inject energy into their surroundings. In traditional simulations, this process is handled by subgrid algorithms that rely on recursive PDEs and numerical integration to represent unresolved physics. These methods can become very computationally taxing as simulations progress and more stars form. The ML-based emulator I developed offers a faster, lower-cost alternative. 

During my predoctoral fellowship at the Flatiron Institute’s Center for Computational Astrophysics, I also developed a radiative transfer emulator. This model takes in global galaxy properties like stellar mass and star formation rate and outputs spectral energy distributions (SEDs) across UV to IR wavelengths. It achieves up to 91% accuracy and runs about 10 million times faster than traditional SED codes—cutting months of compute time down to seconds. 

Outside of these, I’ve had the opportunity to work on projects probing different astrophysical regimes and have found my niche in ML applications to astrophysical simulations, modeling, and data analysis. What excites me is how these tools let us ask bigger questions. Instead of waiting for simulations to finish, we can iterate faster, test varied ideas, and compare models to observations in real time to draw stronger connections between theory and observation. 

Q: Can you tell us about your research and use of HPC before coming to ALCF? 

HPC has been central to my research from the beginning. As an undergrad, I got my start running radiative transfer calculations, and in grad school, HPC became essential to everything from training ML models that emulate star formation to analyzing terabytes of simulation data and running full-suite radiative transfer. 

As my work has scaled, so has HPC. The tools that once felt cutting-edge now seem basic compared to today’s systems with smarter resource management, improved energy efficiency, and more user-friendly interfaces. Modern environments have made it easier to focus on the science rather than troubleshooting infrastructure.  

Looking ahead, I’m excited by the chance to work with ALCF’s next-gen systems. Access to this kind of hardware isn’t just a technical advantage. It’s an opportunity to accelerate research, streamline workflows, and contribute to a sustainable, collaborative future for computational science. 

Q: What are you most looking forward to while working at the ALCF? 

I am most eager to engage with the vibrant intellectual community and cutting-edge resources at the ALCF. While the opportunity to work with world-class supercomputing infrastructure is undeniably thrilling, I am equally motivated by the prospect of collaborating with Argonne’s exceptional scientists and engineers. In my few interactions with Argonne scientists thus far, I’ve been struck by the culture of openness, interdisciplinary curiosity, and shared commitment to advancing both computational science and its real-world applications. 

Learning from leaders at the forefront of HPC and computational modeling will be invaluable to my growth. I look forward to absorbing insights through collaborative projects, thoughtful dialogue, and observing how experts navigate complex technical and scientific challenges. My goal is to contribute meaningfully to this ecosystem by leveraging ALCF’s resources to tackle problems in astrophysics and beyond.  

I am excited to grow as a researcher within this environment and to help push the boundaries of what computational science can achieve. 

Q: Outside of the professional sphere, what can you tell us about yourself – unique hobbies, favorite places, etc.? Is there anything about you your colleagues might be surprised to learn? 

Outside of research, my life has been shaped by a blend of cultural exploration, creative pursuits, and a deep love for animals. I’ve been fortunate to experience diverse communities and traditions which have instilled both adaptability and a curiosity for connecting with people across cultures—a skill I cherish in collaborative environments. 

One constant throughout my journeys has been my passion for Indian classical dance and music, which I’ve practiced for over two decades. Today, I channel this creativity by teaching dance in my spare time to keep the creative juices flowing, but art, in all forms, is a grounding force for me—whether I’m (amateurly) experimenting with calligraphy, sculpting clay, or sewing handmade gifts. 

Another meaningful part of my life is fostering rescue dogs and cats. Over the past six years, caring for animals in transition has given me so much joy. While I once dreamed of veterinary medicine, I found my calling in astrophysics, where I can channel my care for ‘living systems’ into studying cosmic ones. 

CRA Gravitational Wave Open Data Workshop: May 12-14, 2025

Georgia Tech is hosting a local Study Hub for this workshop in the CRA Viz Lab (Room 1-44) from 1:00-5:00pm on each of these days. Participants will learn how to access publicly available gravitational-wave data from the LIGO and Virgo interferometers and get hands-on experience in basic data analysis techniques. Certificates will be awarded to those who complete the course and data challenge. For more details, please visit https://gw-odw.thinkific.com/courses/odw2025 

To attend the workshop, please sign up Here by May 8, 2025. Or use QR Code below.

Hope to see a lot of you there!

Hosted by: Dr. C. Rose, U. Shah, S. Ranjan, B. Vizzone, S. Ashley and Dr. S. Sachdev

Center for Relativistic Astrophysics.

College of Sciences Welcomes New Astrophysics Major, Minor

The School of Physics will launch the new B.S. in Astrophysics program in summer 2025. This new major is the latest addition to the College of Sciences’ academic offerings and responds to increased student demand for courses and research opportunities in astrophysics. A minor in astrophysics will also be offered starting next summer.

According to David Ballantyne, associate chair for Academic Programs and professor in the School of Physics, the new major is unique because it focuses on the future of astronomy and astrophysics, especially in the era of discoveries made by the James Webb Space Telescope and the Laser Interferometer Gravitational-Wave Observatory (LIGO).

“We made a concerted effort when crafting this degree to make it modern and forward-facing,” says Ballantyne. “It is very much focused on the next decade of astronomy and astrophysics, providing a strong emphasis on computational skills, data analysis, and big data.”

The new degree includes coursework on the fundamental physical processes and laws that govern planetary systems, stars, galaxies, and the Universe as a whole. These core topics are complemented by training in computational and data analysis techniques that can be applied to a variety of disciplines. 

For Ballantyne, the degree program should appeal to students who are interested in pursuing careers in space science research as well as those interested in non-research career paths. 

“This program prepares students to solve complex problems in a very quantitative, rigorous way. Such problem solving and computational skills are highly marketable for a range of career paths,” he adds.

The evolution of astrophysics at Tech 

While astronomy coursework and outreach have long existed at the Institute, astrophysics officially began in 2008, when the School of Physics launched the Center for Relativistic Astrophysics (CRA). Today, the Center boasts more than a dozen faculty and research scientists, with expertise spanning high-energy astrophysics, extrasolar planets, gravitational-wave astronomy, and astroparticle physics.

As the CRA’s faculty roster grew, the School expanded its offering of astrophysics courses. A concentration in astrophysics for physics majors was launched during the 2013-14 academic year. A short time later, the School introduced an astrophysics certificate for non-majors. The new astrophysics major and minor — which will replace the concentration and certificate, respectively — reflects a new chapter in the history of astrophysics education and research at Georgia Tech.  

“Most of our peer institutions have an astronomy or astrophysics degree so the creation of this program at Georgia Tech was a natural fit,” says Ballantyne. “Our program fills a critical need considering that there are few options in the U.S. Southeast for students to obtain this type of training at an institution of Georgia Tech’s caliber.”

Declaring the astrophysics major and minor

Current students

Current students can declare the astrophysics major starting next semester, following the standard major change process for undergraduates. The astrophysics minor will be available to all Georgia Tech undergraduates starting summer 2025.

Incoming students

Astrophysics will be added to the list of majors beginning with the admissions application for Summer 2025 (transfer students) and the 2026-27 academic year (first-year students). 

In the interim, transfer students enrolling for the Spring 2025 semester should follow the standard major change process for undergraduates. Students applying to Georgia Tech for the 2025-26 academic year should select “physics” as their major during the application process and choose “astrophysics” once admitted, during the major confirmation process. 

Ph.D. Student Julia Speicher Awarded KITP Graduate Fellowship

Julia Speicher has been awarded the KITP Graduate Fellowship.

Julia Speicher, a fifth-year Ph.D. graduate student of Professor David Ballantyne, has received the competitive Kavli Institute for Theoretical Physics (KITP) Graduate Fellowship. As a part of Speicher’s fellowship, she will be a fully-funded resident of KITP from January to June 2024. There she will broaden her knowledge of the latest advances in astrophysics, overlapping with several long-term programs held at KITP at the University of California at Santa Barbara, under the mentorship of Prof. Omar Blaes.

Speicher studies the X-ray bursts from neutron stars, using sophisticated simulations on high-performance computing platforms. These simulations evolve the accretion disk around a neutron star, including the effects of general relativity, radiation transport, and hydrodynamics. Speicher has published three journal articles to date and has presented her work at several international conferences. Her research on X-ray bursts is essential to explain and interpret these observed extreme events and to understand the inner workings of accretion flows in a strong gravity regime near neutron stars.

Georgia Tech’s Aloha Telescope brings thrilling images to K-12 classrooms

Retired engineer Tom Crowley proves that you can play around with a hobby you love and see it grow into something extraordinary.

The 80-year-old has turned his love of astronomy into consulting work with the Georgia Institute of Technology’s Aloha Telescope outreach program. He operates the robotic telescope on Maui through high-speed internet connections from his home in Park Springs, a senior life plan community in Stone Mountain.

  • Tom Crowley operates a telescope located in Hawaii from his home in Park Springs Life Plan Community in Stone Mountain
    Tom Crowley operates a telescope located in Hawaii from his home in Park Springs Life Plan Community in Stone Mountain. He works with James Sowell of Georgia Tech to help run the the Aloha Telescope program as well as to maintain the telescope.
  1. 1
  2. 2
  3. 3

Crowley works in partnership with James Sowell, a Georgia Tech principal academic professional and astronomer in the School of Physics, and director of the university’s observatory.

Together, they’re bringing live video images of the moon into Georgia K-12 classrooms.

The oohs and ahhs they get in return are priceless.

James Sowell, director of the Observatory, during a previous public night. Photo: Rob Felt
James Sowell, Director of the Observatory

“I tell kids this is almost as close as operating the Hubble Space Telescope or the rover on Mars,” Crowley said. “This telescope is almost a quarter of a way around the world.”

When he’s at home, Crowley runs the telescope through his computer and keeps the image online throughout the day. He also helps with maintenance, sometimes with a trip to its location at the U.S. Air Force Research Lab on Maui.

“It’s the same as if I were sitting at the telescope and using it,” Crowley said. “The fact that it’s 6,000 miles away is not a big deal. I typically get on somewhere between 1 or 2 in the morning (Hawaiian time) and run it to about 6 o’clock.”

Crowley had a long career as an electrical engineer and retired early from IBM. At age 55, he became interested in radio astronomy, studying celestial objects at radio frequencies.

Now, “it’s an obsession,” said Crowley, the past president of the Society of Amateur Radio Astronomers. “This allows me to get back to the purity of engineering.”

Sowell and Crowley met 15 years ago at the Atlanta Astronomy Club. Sowell was the guest speaker and sat across from Crowley during the dinner. Crowley offered to fix the professor’s problems with his telescopes, and they’ve been working together ever since.

“I couldn’t do this without him,” Sowell said.

IceCube neutrinos give us first glimpse into the inner depths of an active galaxy

A gigantic observatory buried in the Antarctic ice has helped scientists trace elusive particles called neutrinos back to their origins at the heart of a nearby galaxy—offering a new way to study a supermassive black hole shrouded from view.

The IceCube Collaboration, spring 2022. Credit: IceCube Collaboration
The IceCube Collaboration, spring 2022. Credit: IceCube Collaboration

For the first time, an international team of scientists have found evidence of high-energy neutrino emission from NGC 1068, also known as Messier 77, an active galaxy in the constellation Cetus and one of the most familiar and well-studied galaxies to date. First spotted in 1780, this galaxy, located 47 million light-years away from us, can be observed with large binoculars. The results, also published (Nov. 4, 2022) in Science, were shared today in an online scientific webinar that gathered experts, journalists, and scientists from around the globe

The detection was made at the National Science Foundation-supported IceCube Neutrino Observatory, a massive neutrino telescope encompassing 1 billion tons of instrumented ice at depths of 1.5 to 2.5 kilometers below Antarctica’s surface near the South Pole. This unique telescope, which explores the farthest reaches of our universe using neutrinos, reported the first observation of a high-energy astrophysical neutrino source in 2018. The source, TXS 0506+056, is a known blazar located off the left shoulder of the Orion constellation and 4 billion light-years away.

One of the more than 5,000 sensors that collect data at the IceCube Neutrino Observatory in Antarctica. PHOTO: MARK KRASBERG, ICECUBE/NSF

“One neutrino can single out a source. But only an observation with multiple neutrinos will reveal the obscured core of the most energetic cosmic objects,” says Francis Halzen, a professor of physics at the University of Wisconsin–Madison and principal investigator of IceCube. He adds, “IceCube has accumulated some 80 neutrinos of teraelectronvolt energy from NGC 1068, which are not yet enough to answer all our questions, but they definitely are the next big step towards the realization of neutrino astronomy.”

Unlike light, neutrinos can escape in large numbers from extremely dense environments in the universe and reach Earth largely undisturbed by matter and the electromagnetic fields that permeate extragalactic space. Although scientists envisioned neutrino astronomy more than 60 years ago, the weak interaction of neutrinos with matter and radiation makes their detection extremely difficult. Neutrinos could be key to our queries about the workings of the most extreme objects in the cosmos.

“Answering these far-reaching questions about the universe that we live in is a primary focus of the U.S. National Science Foundation,” says Denise Caldwell, director of NSF’s Physics Division.

As is the case with our home galaxy, the Milky Way, NGC 1068 is a barred spiral galaxy, with loosely wound arms and a relatively small central bulge. However, unlike the Milky Way, NGC 1068 is an active galaxy where most radiation is not produced by stars but due to material falling into a black hole millions of times more massive than our Sun and even more massive than the inactive black hole in the center of our galaxy.

Hubble image of the spiral galaxy NGC 1068. Credit: NASA/ESA/A. van der Hoeven
Hubble image of the spiral galaxy NGC 1068. Credit: NASA/ESA/A. van der Hoeven

NGC 1068 is an active galaxy—a Seyfert II type in particular—seen from Earth at an angle that obscures its central region where the black hole is located. In a Seyfert II galaxy, a torus of nuclear dust obscures most of the high-energy radiation produced by the dense mass of gas and particles that slowly spiral inward toward the center of the galaxy.

“Recent models of the black hole environments in these objects suggest that gas, dust, and radiation should block the gamma rays that would otherwise accompany the neutrinos,” says Hans Niederhausen, a postdoctoral associate at Michigan State University and one of the main analyzers of the paper. “This neutrino detection from the core of NGC 1068 will improve our understanding of the environments around supermassive black holes.”

NGC 1068 could become a standard candle for future neutrino telescopes, according to Theo Glauch, a postdoctoral associate at the Technical University of Munich (TUM), in Germany, and another main analyzer.

“It is already a very well-studied object for astronomers, and neutrinos will allow us to see this galaxy in a totally different way. A new view will certainly bring new insights,” says Glauch.

These findings represent a significant improvement on a prior study on NGC 1068 published in 2020, according to Ignacio Taboada, a physics professor at the Georgia Institute of Technology and the spokesperson of the IceCube Collaboration.

Ignacio Taboada, CRA Professor
Ignacio Taboada, CRA Professor

“Part of this improvement came from enhanced techniques and part from a careful update of the detector calibration,” says Taboada. “Work by the detector operations and calibrations teams enabled better neutrino directional reconstructions to precisely pinpoint NGC 1068 and enable this observation. Resolving this source was made possible through enhanced techniques and refined calibrations, an outcome of the IceCube Collaboration’s hard work.”

The improved analysis points the way toward superior neutrino observatories that are already in the works.

“It is great news for the future of our field,” says Marek Kowalski, an IceCube collaborator and senior scientist at Deutsches Elektronen-Synchrotron, in Germany. “It means that with a new generation of more sensitive detectors there will be much to discover. The future IceCube-Gen2 observatory could not only detect many more of these extreme particle accelerators but would also allow their study at even higher energies. It’s as if IceCube handed us a map to a treasure trove.”

Ph.D. Student Snigdaa Sethuram Receives NASA Future Investigators Award

Snigdaa Sethura selected for NASA FINESST award.
Snigdaa Sethuram selected for NASA FINESST award.

Snigdaa Sethuram, a Ph.D. graduate student of professor John Wise, has been selected for the Future Investigators in NASA Earth and Space Science and Technology (FINESST) program. The FINESST program awards funding for research projects that are designed and executed by graduate students and contribute to NASA’s science, technology and exploration goals.

Sethuram is the second student in Dr. Wise’s Computational Cosmology group to receive the FINESST award. This fellowship will cover three years of funding for her to complete her thesis project, AI-enhanced Simulations and Synthetic Observations of the First Galaxies and Active Galactic Nuclei. She will be using machine learning techniques to speed up cosmological hydrodynamic simulations of the first galaxies and resolve them further in post-processing, and will be running a large-volume cosmological simulation with her final model.

The final machine learning network is intended for use by anyone simulating early galaxy formation, and synthetic observations of the large-volume simulation should aid in interpreting the James Webb Space Telescope (JWST) observations. Sethuram hopes that the end products will be impactful in generating more resources to understand galactic evolution.

Ph.D. Student Kunyang Li Awarded Prestigious Gruber Foundation Fellowship from the IAU

Ph.D. Student Kunyang (Lily) Li
CRA Ph.D. Student Kunyang (Lily) Li

Congratulations to CRA Ph.D. student Kunyang (Lily) Li who was awarded a Gruber Foundation (GF) Fellowship from the International Astronomical Union (IAU). Lily was one of only three winners of this prestigious Fellowship. The title of her winning research proposal is “Implementation of Massive Black Hole Binary Dynamics in Cosmological Simulations”.

This Fellowship will support Lily’s research during her upcoming postdoctoral position at the Institut d’Astrophysique de Paris.

Well done, Lily! We are all proud of you.

The LIGO GWTC-3 is featured as the NASA Astronomy Picture of the Day

The LIGO GWTC-3 is featured as the NASA Astronomy Picture of the Day 12/7/2021
The LIGO GWTC-3 is featured as the NASA Astronomy Picture of the Day 12/7/2021

Ninety Gravitational Wave Spectrograms and Counting
Image Credit: NSFLIGOVIRGOKAGRAGeorgia TechVanderbilt U.; Graphic Sudarshan Ghonge & Karan Jani

Every time two massive black holes collide, a loud chirping sound is broadcast out into the universe in gravitational waves. Humanity has only had the technology to hear these unusual chirps for the past seven years, but since then we have heard about 90 — during the first three observing runs. Featured above are the spectrograms — plots of gravitational-wave frequency versus time — of these 90 as detected by the giant detectors of LIGO (in the USA), VIRGO (in Europe), and KAGRA (in Japan). The more energy received on Earth from a collision, the brighter it appears on the graphic. Among many science firsts, these gravitational-radiation chirps are giving humanity an unprecedented inventory of black holes and neutron stars, and a new way to measure the expansion rate of our universe. A fourth gravitational wave observing run with increased sensitivity is currently planned to begin in 2022 December.