ProgramMaster Logo
Conference Tools for 2022 TMS Annual Meeting & Exhibition
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting 2022 TMS Annual Meeting & Exhibition
Symposium Hume-Rothery Symposium on Connecting Macroscopic Materials Properties to Their Underlying Electronic Structure: The Role of Theory, Computation, and Experiment
Presentation Title Building Useful Machine-learned Interatomic Potentials
Author(s) Gus LW Hart
On-Site Speaker (Planned) Gus LW Hart
Abstract Scope Interatomic Potentials have long been used for atomistic modeling where the interesting questions are out of reach by first-principles approaches. Traditional empirical potentials are typically fitted to experimental data. They typically have poor general accuracy but are physically well-behaved. On the other hand, machine-learned interatomic potentials are far more expressive than physically motivated interatomic potentials like Lennard-Jones, Stillinger-Weber, Embedded Atom Potentials, etc., but they are also more likely to be completely wrong outside of the training domain, are more difficult to train reliably, and are computationally expensive. We have developed MLIPs for the Hf-Ni-Ti shape memory alloy. We share cautionary tales, best practices for generating training sets, and demonstrate how community tools make for "easy entry" to realistic thermodynamic modeling with these potentials.
Proceedings Inclusion? Planned:
Keywords Machine Learning, Computational Materials Science & Engineering,


ACE of Spades
Building a Diffusion Mobility Database for γ/γ' Co-superalloys
Building Useful Machine-learned Interatomic Potentials
CALPHAD Modeling of Phase-based Properties
Challenges in Addressing the Silicate Attack Problem in Gas Turbine Coatings
Computational Design of Alloy Nanocatalysts
Construction and Application of Defect Phase Diagrams
Construction and Application of First-principles Parameterized Cluster Expansion Effective Hamiltonians Using CASM
Cross Phenomena and Predictions of Their Coefficients
Diffusion in Stationary and Moving Interfaces in Alloys
First-principles Materials Design for Mechanically-controlled Topological Magnetism
From Layered Oxides to Disordered Rocksalt Cathodes: The Future of Energy Storage by Understanding the Atomistics of Li Diffusion
Grain Boundary Stress and Localized Precipitation during Creep
Integrated Computational Modeling of Solute Segregation to Defect, Segregation Transition, Localized Phase Transformation and Dislocation Transformation, All Starting from Ab Initio Calculations
Integrating Theory, Simulation and Experiment to Accelerate Predictive Materials Science
Leveraging First-principles Theory in the Pursuit of Novel Electrode Materials
Machine Learning in Diffusivity Calculations Using a Variational Principle
Molecular-scale Structure and Dynamics of Molten Salts: Simulations and Implications for Corrosive Processes
NOW ON-DEMAND ONLY - Computational Tools for the Ab-initio Design of Advanced Structural Materials
NOW ON-DEMAND ONLY - High-throughput Discovery of Inorganic Compounds
Phase Field Modeling: A Link Between Atomic-scale Interactions and Microstructures of Multiphase Materials
Phonon Anharmonicity Beyond Perturbation Theory
Precipitate Shearing, Fault Energies and the Design of Superalloys
Prospects of Quantum Computing for Modeling Phase Transformations in Battery Materials
Scale Bridging Materials Physics: Active Learning Workflows and Integrable Deep Neural Networks for Free Energy Function Representations in Alloys
To Mix or Not to Mix? Synthesizability Entropy-descriptors and the Controversial Role of Vibrations in the Stability of High-entropy Ceramics
Towards the Accelerated Exploration of the High Entropy Alloy Space
Turning Ab Initio Simulations into Surprising Bulk Predictions
William Hume-Rothery Award Lecture: Study of Ferroelectricity and Phase Transitions in Hafnia

Questions about ProgramMaster? Contact