Recent advances in artificial intelligence are transforming the way new materials are discovered. Traditionally, identifying materials with targeted properties has relied on slow trial-and-error experimentation combined with expensive first-principles calculations. With the emergence of generative AI, large materials databases, and automated knowledge extraction from the scientific literature, it is now becoming possible to accelerate materials discovery by orders of magnitude. In this talk, I will present our recent research on using generative artificial intelligence and machine learning to design novel functional materials for next-generation technologies. I will begin with a brief introduction to the fundamentals of quantum computing and the role of quantum materials in enabling scalable quantum technologies. I will then discuss our recent work demonstrating how generative AI can discover new candidate materials for energy storage applications, including porous oxide materials for next-generation batteries. This work illustrates how AI can explore vast compositional and structural design spaces that are difficult to navigate using conventional computational approaches. Building on these developments, I will present our ongoing research aimed at developing a multi-agent AI framework for discovering novel quantum materials relevant to quantum computing hardware. In this approach, multiple AI agents collaborate within an integrated discovery pipeline that combines literature mining, retrieval-augmented generation, first-principles simulations, thermodynamic modeling, and experimental feedback. The system is designed to identify promising candidate materials, predict their key physical properties, and guide experimental synthesis in a closed-loop discovery process. By integrating artificial intelligence with physics-based modeling and experimental validation, this research aims to establish a new paradigm for AI-driven materials discovery, enabling the rapid identification of materials that could power future advances in quantum computing, energy storage, and other emerging technologies.
📅 April 22, 2026
⏰ 9:00 AM (CDT)
🎙 Generative AI for Discovering Novel Materials for Next-Generation Quantum Computing and Energy Applications
👤 Speaker: Dr. Dibakar Datta
🎛 Moderator: Dr. Steven Samoil, PhD
Biography:
Dr. Dibakar Datta is an Associate Professor in the Department of Mechanical and Industrial Engineering at the New Jersey Institute of Technology (NJIT). He earned his Ph.D. in 2015 from Brown University, where he specialized in Solid Mechanics with minors in Physics and Chemistry. His current research focuses on applying AI to discover novel materials for next-generation energy, quantum, and biomedical applications. His research on AI for materials discovery has received international media coverage. He is a recipient of the National Science Foundation (NSF) CAREER Award.
Steven Samoil is an applied scientist who recently completed his PhD in Chemical and Petroleum Engineering from the University of Calgary. His research focus is on the intersection of classical and quantum computing for history matching and reservoir simulation. For this research Steven built and deployed a hybrid cloud architecture integrating quantum algorithms, high performance compute clusters, and classical resources for comparative performance analysis of classical and quantum Bayesian optimization. He previously worked as the technical project manager for the Reservoir Simulation Group at the University of Calgary where he led research projects on applied quantum computing, applied artificial intelligence, and the development of virtual reality tools for reservoir simulation interpretation. Steven received both his MSc in Electrical Engineering and BSc in Computer Engineering from the University of Calgary.