Six scientists at the U.S. Department of Energy's Brookhaven National Laboratory have received prestigious Early Career Research Awards totaling approximately $2.75 million each over five years, with funding directed toward AI-driven materials discovery, quantum computing, and particle physics research. The awards, part of the DOE's 16-year-old Early Career Research Program, support researchers at a critical stage in their careers when many make their most transformative contributions to science .

Why Should Scientists Care About AI in Materials Discovery?

The race to develop new quantum materials is accelerating because current technologies are hitting performance walls. Energy-efficient electronics, next-generation data storage, and faster quantum computers all depend on discovering materials that behave according to quantum mechanics, not classical physics. Niraj Aryal, a computational condensed matter physicist at Brookhaven Lab, is tackling exactly this challenge. His award-winning research combines machine learning, high-performance computing, and electronic-structure calculations to efficiently search through candidate topological materials and predict their properties under different conditions .

"Each leap in human progress has followed a leap in materials. With smarter algorithms and powerful computers, we can uncover novel quantum materials that make future electronics and information processing more capable while using far less energy," said Aryal.

Niraj Aryal, Computational Condensed Matter Physicist, Brookhaven Lab

The computational challenge is substantial. Discovering quantum materials typically requires solving high-dimensional, coupled integro-differential equations, which demand enormous computational resources and extended processing times. By automating this search with AI, researchers can dramatically accelerate the discovery timeline and reduce costs .

How Are These Scientists Using AI to Advance Physics and Materials Science?

• Real-Time Particle Detection: Syed Haider Abidi is developing AI and machine learning algorithms that work in real-time at the ATLAS detector at CERN's Large Hadron Collider, using analog computing to reduce memory transfers and capture rare Higgs boson decay events that would otherwise be lost in the noise of millions of collisions.
• Quantum Materials Prediction: Niraj Aryal is deploying machine learning methods on world-class supercomputers to investigate topological materials, quantify their stability and transport responses, and guide targeted experimental discovery of materials for ultra-low-power devices.
• Accelerator Optimization: Kiel Hock is exploring strategies to maintain the spin alignment, or polarization, of helium-3 nuclei as they are accelerated to high energies at the Electron-Ion Collider, a critical requirement for precision nuclear physics experiments.

Syed Haider Abidi's work represents a particularly novel application of AI in high-energy physics. He is integrating modern machine learning into the real-time event selection systems that determine which particle collisions are worth saving for analysis. His research targets an unexplored decay channel called Higgs to ZZ* that involves tau leptons, particles that are notoriously difficult to detect amid the background noise of billions of collisions. By introducing AI-based tagging algorithms and low-power analog computing into the ATLAS trigger system, Abidi aims to extract these rare signals in real-time, sharpen sensitivity to unusual Higgs boson behavior, and expand tests of the Standard Model .

"Having the Early Career Award to test these technologies in a realistic environment is super exciting. This application of AI and machine learning is unique and has tons of potential for the future and long-term implications for pushing real-time data analysis closer to the detector," said Abidi.

Syed Haider Abidi, Experimental Particle Physicist, Brookhaven Lab

What Does This Mean for the Future of Energy and Computing?

The six awardees represent a broader shift in how fundamental science is conducted. Rather than relying solely on traditional computational methods or experimental trial-and-error, researchers are now combining AI algorithms with massive computing power to explore vast design spaces that would be impossible to search manually. This approach is particularly valuable in materials science, where the number of possible material combinations is essentially infinite .

Brookhaven Lab Interim Director John Hill emphasized the significance of the awards for the institution and the nation's scientific competitiveness. "These are very prestigious grants. Having six awardees at Brookhaven speaks highly to the talent we attract," Hill stated. "I'm very excited for them to begin their projects and to see the exciting discoveries they will make in the next few years" .

John Hill

The DOE's investment in these early-career researchers aligns with broader national priorities in quantum information science and AI-driven discovery. By supporting scientists at the outset of their careers, when they are most likely to pursue bold, unconventional research directions, the program aims to cement America's position as a global leader in science and innovation while growing a skilled STEM workforce .

Each of the six awardees will receive approximately $2.75 million distributed over five years, enabling them to pursue ambitious research projects that might otherwise be too risky or resource-intensive for early-career scientists to undertake independently. The awards represent a significant vote of confidence in the next generation of researchers who are reshaping how science is done at the intersection of AI, materials discovery, and fundamental physics.