MTU Researcher Wins NSF CAREER Award for Machine Learning Advances in Materials Design

For his research in machine learning-based electron density prediction, Michigan Tech
researcher Susanta Ghosh has been recognized with one of the National Science Foundation’s
highest honors.

Susanta Ghosh, an assistant professor in the Department of Mechanical and Aerospace Engineering (MAE) at Michigan Technological University, has won a $669,490 NSF Faculty Early Career Development Program (CAREER) Award for his research project “Bayesian Symmetry-Respecting Machine Learning
Framework for Predicting Electronic Structures in Materials Design.”

The NSF CAREER Award is the National Science Foundation’s most prestigious award in
support of early-career faculty who have the potential to serve as academic role models
in research and education. The honor also recognizes their rising ability to lead
advances in the mission of their department or organization.

The award will support Ghosh’s research through 2030. His project focuses on gaining
fundamental insights to atomic configurations and corresponding electronic structures,
as well as providing cost-effective, large-scale electronic structure calculations
in order to accelerate materials design and discovery. This research can be applied
beyond materials science to projects in fields such as biomedical imaging and continuum
physics problems.

“Professor Ghosh’s NSF CAREER Award draws on his expertise across several disciplines
to converge on solutions for complex problems,” said Michelle Scherer, dean of the College of Engineering. “This is exactly what these prestigious NSF
awards are meant to support — innovative approaches to complex problems. It will be
exciting to see what Prof. Ghosh and his students discover!”

Ghosh’s research group is dedicated to the development of machine learning algorithms
that are not only scalable and informed by the principles of physics, but also endowed
with the capacity for uncertainty quantification and broad generalizability. These
algorithms are designed to function seamlessly across a diverse array of application
domains.

“Accelerating materials modeling and discovery through artificial intelligence can
revolutionize advanced materials research and device design impacting a wide range
of fields,” said Ghosh.

The project also supports educational and outreach activities aimed at promoting machine
learning-based materials design for a wide range of researchers and students. These
activities include sharing machine learning code with public repositories, providing
education through summer youth programming and developing a cyberinfrastructure curriculum.

In addition to his work in mechanical and aerospace engineering, Ghosh is a member
of Michigan Tech’s Institute of Computing and Cybersystems and the institute’s Center for Artificial Intelligence, and heads the Computational Science and Machine Learning Lab. His CAREER Award is jointly funded by the NSF’s Office of Advanced Cyberinfrastructure and Division of Civil, Mechanical and Manufacturing Innovation.

Michigan Technological University is an R1 public research university founded in 1885 in Houghton, and is home to nearly 7,500 students from more than 60 countries around the world. Consistently ranked among the best universities in the country for return on investment, Michigan’s flagship technological university offers more than 120 undergraduate and graduate degree programs in science and technology, engineering, computing, forestry, business, health professions, humanities, mathematics, social sciences, and the arts. The rural campus is situated just miles from Lake Superior in Michigan’s Upper Peninsula, offering year-round opportunities for outdoor adventure.