Shunshun Liu graduates with a PhD in Materials Science and Engineering
Congratulations to Shunshun Liu, who graduated with a PhD in Spring 2026!
New paper in Scientific Reports: predicting misfit volume in refractory high-entropy alloys
Congratulations to Shunshun Liu on the publication of “An Active Learning Workflow for Predicting Misfit Volume in Body-Centered Cubic Refractory High-Entropy Alloys” in Scientific Reports.
New paper in Scientific Reports: predicting TTT curves in uranium-based alloys
Congratulations to Sunidhi Garg, in collaboration with Dr. Joshi (PNNL), Dr. Bhattacharya (UVA), and Prof. Agnew (UVA), on the publication of “A Physics-Regularized Machine Learning Approach for Predicting Time-Temperature-Transformation Curves in Alloys: Application to Uranium-based Alloys” in Scientific Reports.
New paper in npj Computational Materials: a computational Dieke design map
Congratulations to Shunshun Liu, in collaboration with Prof. Clarke (Harvard), on the publication of “A Computational Dieke Design Map for Near-Infrared Optical Absorption in Transition Metal-Substituted Yttria-Stabilized Zirconia” in npj Computational Materials.
New paper in Digital Discovery: adaptive ensemble sampling for van der Waals epitaxy
Congratulations to Ankita, in collaboration with Dr. Bagchi (ORNL), Dr. Ghosh (ORNL, now at IIT-Madras), and Dr. Panchapakesan (ORNL), on the publication of “Towards ‘on-demand’ van der Waals epitaxy with adaptive ensemble sampling atomistic workflows” in Digital Discovery.
New paper in Integrating Materials and Manufacturing Innovation: LLM-based large-scale data extraction
Congratulations to Shunshun Liu and Talon Booth, in collaboration with Prof. Reinhart (Penn State) and Prof. Ji (UVA, Computer Science), on the publication of “Expert-Grounded Automatic Prompt Engineering for Extracting Lattice Constants of High-Entropy Alloy from Scientific Publications using Large Language Models” in Integrating Materials and Manufacturing Innovation.
Models constrained by known physics and explained through post-hoc explanation methods, with symbolic regression that recovers interpretable governing equations directly from data.
AI
LLMs for Science
Large language models (LLMs) as symbolic regression engines and autonomous agents for materials discovery workflows.
DFT
First-Principles Calculations
Magnetic (non-collinear with SOC), optical (GW-BSE), and electron-phonon coupling (EPW, linear response theory, Phonopy) calculations that ground our AI/ML models in physical reality.
UQ
Uncertainty Quantification
Bayesian and ensemble learning approaches that quantify uncertainty and support principled decision-making.
Accelerated Discovery
Active Learning for Materials Discovery
Closed-loop design strategies that choose the next experiment or simulation, cutting the time and cost of finding new materials.
Materials Systems
Alloys, Oxides, and Advanced Materials
High entropy materials (alloys and ceramics), high-temperature materials, materials with point defects, cements, complex oxides, and metallic alloys.
Principal Investigator
Prasanna V. Balachandran — Heinz and Doris Wilsdorf Research Associate Professor, Department of Materials Science and Engineering, University of Virginia.