Two Hopkins-led research teams have each been awarded $750,000 in funding through Phase I of the U.S. Department of Energy’s (DOE) Genesis Mission, a national initiative bringing together laboratories, universities, and industry partners to develop AI-enabled scientific workflows to accelerate scientific breakthroughs in energy, discovery science, and national security.
The Johns Hopkins scientists are among 278 teams selected for this phase to develop new AI models and frameworks to address some of the nation’s most pressing challenges in energy, scientific, and engineering challenges.
Data Center Cooling
Ján Drgoňa, associate professor in the Department of Civil and Systems Engineering with a secondary appointment in Electrical and Computer Engineering, has received $750,000 in funding through the U.S. Department of Energy’s Genesis Mission to fund his research project, “From Chip to Chiller: Verifiable Edge AI Agents for Data Center Thermal Management.”
Ján Drgoňa
A member of both the Ralph S. O’Connor Sustainable Energy Institute and the Data Science and Artificial Intelligence Institute, Drgoňa’s research centers on using AI to make complex systems safer and more efficient. His DOE-funded project aims to reduce the energy needed to cool data centers while maintaining reliable operation.
Data centers support many of the digital services people use every day, such as online communication and streaming, but their cooling systems can be expensive to operate. Drgoňa and his team will develop AI agents that can predict and optimize cooling in data centers, from individual computer chips all the way to the physical cooling equipment that helps keeps data centers running.
“The AI agents that we develop will guide thermal management in real-time to improve efficiency while maintaining the necessary temperatures for the facilities to function. The technology has the potential to lower energy use and operating costs of the digital infrastructure people rely on every day,” says Drgoňa. “More efficient cooling also supports broader efforts to reduce electricity demand and improve sustainability.”
Project collaborators include Yury Dvorkin, Dennice Gayme, and Somdatta Goswami from the Whiting School of Engineering, Draguna Vrabie and Aaron Tuor from Pacific Northwest National Laboratory, Ulrich Muenz, Suat Gumussoy, Tao Cui, and Sudhir Rajagopalan from Siemens, and Vedavyas Panneershelvam from Phaidra.
Fast, Reliable, Accessible Scientific Computing
Ziyang Li, an assistant professor of computer science and a member of Johns Hopkins’ Information Security (ISI) and Data Science and AI Institutes (DSAI), is principal investigator on the awarded project “Hierarchical Neuro-Symbolic Synthesis of Verifiable Computational Physics Code for Scientific Discovery.”
Ziyang Li
Fellow CS faculty member Yinzhi Cao, the technical director of the ISI and a member of both the DSAI and the university’s Institute for Assured Autonomy, joins him as a co-investigator, with additional support provided by Nengkun Yu of Stony Brook University and Meifeng Lin of Brookhaven National Laboratory.
The goal of their project is to transform high-performance computing software development from an expert craft requiring years of specialized knowledge into a structured, reproducible, AI-assisted scientific workflow.
“Scientific breakthroughs increasingly depend on sophisticated simulation software, but developing that software often takes years,” says Li. “Our goal is to build AI systems that not only generate scientific code but also verify that it faithfully reflects the underlying physics. By combining AI with formal reasoning, we hope to make scientific computing faster, more reliable, and more accessible to researchers.”
Initially, the project will curate high-quality data for verified computational physics code and focus on applications in high-performance computing for particle physics before extending to other areas of computational science.
Ultimately, this work could enable scientists to move more quickly from new scientific ideas to reliable computational tools, thus accelerating discoveries in energy, materials science, and physics.
In addition to the two projects led by Johns Hopkins, Genesis Mission grants led by other groups include the following Hopkins faculty:
Julie Kay Lundquist
Bloomberg Distinguished Professor of Atmospheric Science and Wind Energy
Department of Mechanical Engineering, Whiting School of Engineering
Department of Earth and Planetary Sciences, Krieger School of Arts and Sciences
Project: Turbulence-Microphysics-Land Nexus (TML-Nexus): Unlocking Predictive Power for the Coupled Water Cycle using Weather Foundation Models, led by Manajit Sengupta, National Laboratory of the Rockies
Description: The team will work to improve forecasts of weather, water availability, and severe storms that affect transmission and distribution of energy on power grids that fuel thermal and nuclear plants, data centers, and hydropower facilities. They aim to use large-eddy simulations (finely resolved atmospheric simulations), instrument simulators developed by the team, and Department of Energy data to improve AI tools that model air turbulence and cloud microphysics.