Accelerating Computational Materials Design with CALPHAD, DFT, MLIPs, and AI Agents

This webinar presents recent advances in integrating CALPHAD, density functional theory (DFT), machine learning interatomic potentials (MLIPs), and AI-assisted simulation workflows for accelerated materials discovery and design. 

The talk will highlight how modern computational frameworks can bridge thermodynamics, atomistic simulations, and machine learning to address complex materials problems across structural alloys, functional oxides, and energy-storage materials.

Who should attend

• Computational Materials Scientists utilizing thermodynamic modeling
• Alloy Designers working on steels, superalloys, or HEAs (High-Entropy Alloys)
• Metallurgists focused on solidification and heat treatment processes
• Battery Researchers investigating phase stability in cathode/anode materials

Outline

The presentation will begin with examples of high-throughput CALPHAD and ab initio studies on high-entropy alloys and complex oxide systems, demonstrating how computational thermodynamics and first-principles calculations can provide insights into phase stability, thermodynamic behavior, defect energetics, diffusion, and temperature-dependent properties. Representative studies include investigations of VEC criteria in high-entropy alloys, magnetic and thermodynamic properties of Fe-based alloys, and oxygen transport mechanisms in layered nickelate and perovskite oxides.

The webinar will then focus on recent developments in machine learning-accelerated atomistic simulations using MLIPs and the Matlantis platform. Several case studies from the speaker’s research group will be discussed, including high-entropy perovskites, interface design in oxide systems, active-learning-assisted simulations of doping effects, and large-scale atomistic modeling enabled by machine learning potentials. The integration of AI-assisted workflows through the Masgent simulation agent will also be introduced, illustrating how autonomous or semi-autonomous simulation pipelines can significantly reduce the cost and complexity of large computational campaigns.

Finally, the talk will highlight emerging applications in battery materials, including high-entropy cathodes, solid-state electrolytes, sodium-ion batteries, and interface engineering. The webinar aims to demonstrate how the combination of CALPHAD, DFT, MLIPs, active learning, and AI agents is creating a new paradigm for scalable and physics-informed materials design.

Speaker

Mechanical and Materials Engineering, Worcester Polytechnic Institute

Yu (Michael) Zhong, Ph.D.

Dr. Yu Zhong is a Professor in Mechanical and Materials Engineering at Worcester Polytechnic Institute (WPI). He received his Ph.D. from Penn State University (2005). After a short-term working as Research Associate, he joined Saint-Gobain High-Performance Materials Research Center. He had built up his career there as an internal technical consultant focusing on applying thermodynamics and kinetics to various R&D projects. In 2013, he moved to Florida International University (FIU) as Assistant Professor and joined WPI as an Associate Professor in 2017 and promoted as Full Professor in 2024.

Dr. Zhong received the TMS FMD Young Leaders Professional Development Award in 2016 and the ONR summer faculty fellowship in 2015, 2016, and 2017. He has more than 95 peer-reviewed journal papers published/accepted, 2 book chapters, and 3 patents. His research is currently supported by the Department of Energy (DOE) National Energy Technology Lab (NETL), Nuclear Energy University Program (NEUP), Solar Energy Technology Office (SETO), and Office of Energy Efficiency and Renewable Energy (EERE), Defense Advanced Research Projects Agency (DARPA), Department Of The Air Force (DAF), Army Research Laboratory (ARL), National Science Foundation (NSF), American Chemical Society (ACS), Massachusetts Clean Energy Center (MassCEC), Draper, Physical Science, Inc. (PSI), and Advance Casting Research Center (ACRC).

Webinar Details

Apply here