Conference Tools for 2023 TMS Annual Meeting & Exhibition

Login

Register as a New User

Help

Submit An Abstract

Propose A Symposium

Presenter/Author Tools

Organizer/Editor Tools

About this Abstract
Meeting	2023 TMS Annual Meeting & Exhibition
Symposium	Algorithm Development in Materials Science and Engineering
Presentation Title	Modular and Scalable Solutions for Training Machine Learned Interatomic Potentials
Author(s)	Mitchell Wood, Andrew Rohskpof, Charles Sievers, Danny Perez, Aidan Thompson
On-Site Speaker (Planned)	Mitchell Wood
Abstract Scope	Model development that utilizes machine learning must define feature sets, model forms, and ultimately if said models are efficient to use for the desired accuracy. Specialized software to develop machine learned interatomic potentials utilized in MD is highlighted herein. The FitSNAP code has evolved quickly in the last few years to accept numerous descriptor sets, model forms (and associated regression techniques), all while ensuring portability into LAMMPS for efficient use. This talk will overview the user friendly FitSNAP code and its integration into the Exascale Computing Project EXAALT software stack with a focus on the challenges and advances made to tackle exascale sized training sets needed to construct robust and truly transferable interatomic potentials. A new method of training set generation that is applicable beyond interatomic potentials will be demonstrated.
Proceedings Inclusion?	Planned:
Keywords	Computational Materials Science & Engineering, Modeling and Simulation, Machine Learning

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A New AI/ML Framework for Materials Innovation

A Non-local Formulation of the Elastoplastic Self-consistent Crystal Plasticity Model: Applications to Modeling Deformation and Recrystallization

A Peridynamic-based Approach to Study the Influence of Oxide on Impact and Bonding in Cold Spray

A Recursive Grain Remapping Scheme for Irregular Morphologies in Phase-Field Models

Algorithms for Computing Diffraction Patterns from Dislocation Networks Generated via Discrete Dislocation Dynamics Simulations

An Automated Approach to Data Extraction for SMAs

An OpenMP GPU-Offload Implementation of a Cellular Automata Solidification Model for Laser Fusion Additive Manufacturing

Applications of Min-cut Algorithms for Image Segmentation and Microstructure Reconstruction

Characterization of the Evolution of the Grain Boundary Network Using Spectral Graph Theory

Characterizing Microstructure Evolution in Latent Space for Machine Learning Applications

Coupling of a Multi-GPU Accelerated Elasto-visco-plastic Fast Fourier Transform Constitutive Model with the Implicit Finite Element Method

Crystal Plasticity Finite Element Analysis of Crystalline Thermo-mechanical Constitutive Response

Data-Driven Bayesian Model-Based Prediction of Fatigue Crack Nucleation in Ni-based Superalloys

Data-driven Plastic Anisotropy Predictions Using Crystal Plasticity and Deep Learning Models

Data Assimilation for Estimation of Microstructural Evolution during Solid-state Sintering: Integration of Phase-field Simulation and In-situ Experimental Observation

Development of Structure-property Linkages for Damage in Crystalline Microstructures Using Bayesian Inference and Unsupervised Learning

Diffuse Interface Technique to Simulate Fluid Flow and Characterize Complex Porous Media

EAM-X: Simple Parameterization of Embedded Atom Method Potentials for FCC Metals and Alloys

EAM-X: Universal trends in FCC Grain Boundary Energies

Enabling Long Timescale Molecular Dynamics Simulation with ab initio Precision

Exascale Fracture Mechanics with Peridynamics

Finite Element Implementation of a Dislocation Thermo-mechanics Model: Application to Study Dislocation Structure Evolution during Laser Scanning

Investigating Magnetic Phase Transitions with Ising Models Accounting for Long-range Spin Interactions

M-14: Differential Property Prediction: A Machine Learning Approach to Experimental Design in Advanced Manufacturing

Machine Learning Models of Effective Properties with Reduced Requirements on Microstructure

Microstructure-Sensitive Calculations of Metal Nanocomposite Electrical Conductivity

Modular and Scalable Solutions for Training Machine Learned Interatomic Potentials

Multifaceted Uncertainty Quantification for Structure-property Relationship

Multiphase Microstructure-based Modeling for Rolling Contact Fatigue Life Prediction

Novel Multi-scale Plasticity Modeling Using Defect Dynamics Element Method (DDEM)

Persistent Homology for Topological Quantification of Microstructure

Prediction of Cutting Surface Parameters in Punching Processes aided by Machine Learning

Prediction of Mechanical Properties in a Bulged and Annealed Steel Tube through a Multiscale Modeling Approach Based on CPFEM

PyEBSDIndex: Fast Indexing of EBSD data

Symmetry Relation Database and Its Application to Ferroelectric Materials Discovery

Thermographic Process Classification in Electron Beam Additive Manufacturing via Stacked Long Short-Term Memory Networks

Training Machine-learned Interatomic Potentials for Chemical Complexity - Application to Refractory CCAs

Questions about ProgramMaster? Contact programming@programmaster.org