By Jennifer T. Allen, Hannah Edelen, Jenny Wells-Hosley and Richard LeComte
As humans search for intelligent life–or any life at all—in the universe, they’re using their own intelligence to craft new ways of exploring galaxies. They’re even starting to use artificial intelligence, itself a new frontier, to deepen science’s understanding of what lies beyond.
That’s where Yuanyuan Su, an assistant professor in the Department of Physics and Astronomy, is applying her own intelligence. She and her group are using artificial intelligence to analyze images gathered from the space and ground telescopes to figure out what’s actually there.
Su has received the 2024 Early Career Prize from the High Energy Astrophysics Division of the American Astronomical Society. The HEAD Early Career Prize recognizes a significant advance or accomplishment (observational or theoretical) in High Energy Astrophysics by an individual astrophysicist within 10 years of receiving a doctorate.” The citation reads “for innovative contributions in understanding baryon physics in galaxy groups and clusters."
Two years ago, Su and her team trained and tested their machine learning algorithm on astronomy images taken from cosmological simulations. Since then, they have published a paper led by Sheng-Chieh Lin, a graduate student in the Department of Physics and Astronomy, where the machine learning algorithm was trained and tested on real astronomy images taken from the Sloan Digital Sky Survey.
“The transition from using simulated data to real observational data is a big milestone in applying AI/ML to astronomy,” Su said.
They didn’t stop there.
By applying a few tools to interpret the algorithm, instead of treating it like a black box, they realized that the AI/ML algorithm has learned to ignore the artifact in astronomy images, despite never being deliberately trained to do so.
“We think this is very interesting and can be used to facilitate image preprocessing for many different purposes,” Su said.
Su is collaborating with faculty at UK and recently initiated the “University of Kentucky Hub for Artificial Intelligence and Machine Learning” which is supported by the Provost IMPACT Award. The team is comprised of faculty from three colleges – Arts and Sciences, Gatton College of Business and Economics and Pigman College of Engineering.
“I look forward to collaborating with faculty at UK through the UK Hub for AI/ML as well as applying for observation time of a new X-ray space telescope, XRISM, launched in 2023,” she said. “It is going to enhance our understanding of big cosmic questions like how the largest structures in the universe came to be.”
Su’s group primarily studies clusters of galaxies using multiwavelength observations. In addition to member galaxies and the hot plasma between galaxies, clusters of galaxies contain a large amount of invisible dark matter. They are one of the most important probes for testing the standard cosmological models and dark energy.
“We are entering an era of big data in astronomy as many sky surveys come online,” Su said. “Applying AI/ML methods will help us maximize the scientific returns of the flood of data.”
Su came to UK in 2019 after serving as a postdoctoral fellow at the Harvard-Smithsonian Center for Astrophysics.
"My office (at Harvard) was next to ‘the great refractor,’ probably the first telescope that took photographs,” Su said. “Annie Jump Cannon, and many other women astronomers, used it to classify the stars."
Now a professor, Su says her proudest moment is seeing early-career scientists in her group grow and thrive. In 2022, Su graduated her first Ph.D. student, Arnab Sarkar, who is now a postdoc at MIT and has recently been awarded a large Chandra observation program as the PI. Her first postdoc, Valeria Olivares, is the first Hispanic female scientist in the department and led a multiwavelength campaign to study the interaction between multiphase gas and the supermassive black hole at the centers of galaxy clusters. Olivares recently accepted a postdoc position at NASA starting January 2024.
“It has been the most rewarding experience for me to work with these great young minds,” Su said.
Su became interested in astrophysics at a young age. However, her path to becoming an astrophysicist wasn’t always smooth.
“When I was in school, it wasn’t considered an ideal path for girls to study physics,” Su said. “I felt isolated and doubted my choice when I became the only female physics major in my class. But I was fortunate to get to know great women scientists in my career. I have been deeply influenced and encouraged by them.”
She is originally from Sichuan, China, the hometown of giant pandas. Su received her Ph.D. from the University of Alabama and went on to a postdoc in California before moving to Harvard.
“I want to be a female role model for my students and my baby girl,” Su said. “I am so glad to be at UK. I am grateful for talented colleagues, hard-working students, and I found my collaborators.”