| About this Abstract |
| Meeting |
2025 TMS Annual Meeting & Exhibition
|
| Symposium
|
Atomistic Simulations Linked to Experiments to Understand Mechanical Behavior: A MPMD Symposium in Honor of Professor Diana Farkas
|
| Presentation Title |
Universal Interatomic Potential and Simulation of Kinetics |
| Author(s) |
Ju Li |
| On-Site Speaker (Planned) |
Ju Li |
| Abstract Scope |
I will describe the recent development of a universal neural interatomic potential (UNIP) that covers 96 elements on the periodic table, from Hydrogen to Curium. More than two thousand GPU years were used to generate the ab initio training data guided by active learning. Diverse test simulations have shown this universal potential has outstanding performance, with energy error significantly less than the chemical accuracy (43 meV/atom) for even chemically very complex systems. Going from a few hundred atoms in DFT to up to 50,000 atoms with UNIP, one can study realistic microstructures such as extended defects with curvatures and their interactions, realistic phase transformations, plastic deformation and damage evolution, electrochemical interfaces, etc. I will use reinforcement learning (RL) guided long-timescale simulation of hydrogen transport in a medium entropy alloy as an example. [J Materiomics 9 (2023) 447; Advanced Science 11 (2024) 2304122] |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, Machine Learning, |