Conference Tools for 2022 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

2022 TMS Annual Meeting & Exhibition

Symposium

AI/Data Informatics: Computational Model Development, Validation, and Uncertainty Quantification

Presentation Title

Accelerating Phase-field Based Predictions via Surrogate Models Trained by Machine Learning Methods

Author(s)

Remi Dingreville, David Montes de Oca Zapiain, James A Stewart, Chongze Hu, Shawn Martin

On-Site Speaker (Planned)

Remi Dingreville

Abstract Scope

The phase-field method is a powerful and versatile computational approach for modeling the evolution of the microstructure and properties of a wide variety of physical, chemical and biological systems. However, existing high-fidelity phase-field models are inherently computationally expensive, requiring high-performance computing resources and sophisticated numerical integration schemes to achieve useful degree of accuracy. In this talk, I will discuss advanced in developing computationally inexpensive and accurate, data-driven surrogate models that directly learn the microstructural evolution of targeted systems by combining phase-field and history-dependent machine-learning techniques. I will discuss the advantages/disadvantages of combining various techniques that integrate low-dimensional description of the microstructure, obtained directly from phase-field simulations, with history-dependent deep neural network. Lasty, I will give examples on the performance and accuracy of the established machine-learning, accelerated framework to predict the non-linear microstructure evolution as compared to high-fidelity phase-field. SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525.

Proceedings Inclusion?

Planned:

Keywords

Computational Materials Science & Engineering, Machine Learning, Phase Transformations

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

10 Years of the Materials Genome Initiative

A Data-driven Approach for Improving the Existing Gurson Material Damage Model Using Genetic Programming for Symbolic Regression

A Novel Approach for Rapid Alloy Development Leveraging Machine Learning

A Physics-informed Regularization Approach for Machine Learning Derivation of Constitutive Models

A Statistical-physical Framework for the Analysis of Uncertainties due to Material Parameters in Multi-physics Modelling

A Statistical Perspective for Predicting Polycrystalline Strength with Machine Learning

Accelerated Alloy Design by Batch Constrained Multiobjective Optimization Using Surrogate Models

Accelerated Genetic Algorithm via a Pre-trained Crystal Graph Convolutional Neural Network

Accelerating Phase-field Based Predictions via Surrogate Models Trained by Machine Learning Methods

AI/ML/DL Approaches for Accelerating Materials Discovery and Design

Applicability Domain for Prediction Models of Thermoelectric Properties Based on Similarity to Known Materials

Application of Compositionally-restricted Attention-based Network (CrabNet) for Screening Candidate Dispersed Phases for Designing High Strength Alloys

Austenitic Parent Grain Reconstruction in Martensitic Steel Using Deep Learning

Automatic Segmentation and Quantification of Microscopy Data Using Transfer Learning from a Large Microscopy Database

Autonomous Research Systems

Balancing Data for Generalizable Machine Learning to Predict Glass-forming Ability of Ternary Alloys

Band Gap Predictions of Novel Double Perovskite Oxides

Closed-loop Discovery of the Composition-structure-properties Relationships of Superconductors

Combined Clustering and Regression for Predicting Melting Temperatures of Solids

Comparison of Human, Machine Learning, and Common Optimization Approaches on Grain Boundary Networks

Convolutional Neural Networks to Expedite Predictions of Volume Requirements in Studies of Microstructurally Small Cracks

Coping with Materials Variance Using Transfer Learning

Data Driven Approach to Design/Discover Intercalating Ions and Layered Materials for Metal-ion Batteries

Deep Learning-based Algorithms for X-ray Microtomography Analysis: Unravelling Challenges for 4D Experiments

Deep Neural Network Regressor for Phase Fraction Estimation on the High Entropy Alloy System Al-Co-Cr-Fe-Mn-Nb-Ni

Density-based Monte Carlo Consensus Clustering (DMC3) for Feature Extraction from Atom Probe Tomographs

Design of a Scalable Interatomic Potential for GST+C Device Modeling

Digital Image Correlation Based Machine Learning Predictions for Grain-boundary Strain Accumulation in a Polycrystalline Metal

Direct Prediction of Mechanical Properties from X-ray Diffraction Patterns Using Machine Learning

DiSCoVeR Algorithm for Identifying Promising Unlikely Candidates for New Materials

Efficient Generation of Arbitrary N-field Microstructures from 2-point Statistics Using Multioutput Gaussian Random Fields

Efficient Optimization of Variable and Uncertain Additive Manufacturing Processes Using Machine Learning

Ensemble of State-of-the-art Property Prediction Machine Learning Algorithms

Extracting and Making Use of Materials Data from Millions of Journal Articles via Natural Language Processing Techniques

Feature Selection and Interpretation for Machine Learning Models: Reducing the Dimensionality of Complex Concentrated Alloys

Graph Neural Network Framework to Emulate Multiple Crack Propagation and Coalescence

Importance of the Choice of Constitutive Model for Full Field Crystal Plasticity Simulations: A Comparison of Predictions of the Voce and the Dislocation Density Based Hardening Laws

Inference, Uncertainty Quantification, and Uncertainty Propagation for Grain Boundary Structure-property Models

Investigation of Microstructure Image Segmentation via Deep Learning with Limited Data Annotations

Learning from 2D: Data-driven Model Predicting Bulk Properties Based on 2D Microstructure Sections

M-10: Investigating the Suitability of Tableau Dashboards and Decision Trees for Particulate Materials Science and Engineering Data Analysis

M-11: Machine Learning Based Prediction of Melting Temperature and Coefficient of Thermal Expansion Coefficient Using SciGlass Datasets

M-9: Determination of Aluminum Mechanical Properties Using Small Punch Test and Advanced Numerical Methods

Making the Most of What We’ve Got: Designing Microstructural Data Sets for AI Applications

Mining Structure-property Linkage in Nanoporous Materials Using an Interpretative Deep Learning Approach

Multi-fidelity Surrogate Modeling of Epistemic Uncertainty Arising from Microstructure Reconstruction

Neural Message Passing for Prediction of Abnormal Grain Growth in Monte Carlo Simulations of Polycrystalline Materials

Now On-Demand Only - Data-driven Approaches for Understanding Fatigue Damage Initiation

NOW ON-DEMAND ONLY – M-8: A Data-driven Surrogate Model for Fast Predicting the U-10Mo Fuel Grain Structures during the Hot Rolling and Annealing Processes

NOW ON-DEMAND ONLY – Physics Based Analytical Models for the Design of New Metastable Rare-earth Compounds

NOW ON-DEMAND ONLY - Ultra-fast and Interpretable Machine-learning Potentials with Application to Structure Prediction

NOW ON-DEMAND ONLY – Uncertainty Quantification and Propagation in Prediction of Solid-liquid Interfacial Properties and Solidification Microstructures

One-stage Simulation of EBSD Patterns over Multiple Parameters through a CVAE-GAN Model

Optimizing Thermoelectric Compositions to Achieve Extraordinary Properties

Orchestrating Multi-task Material Design Campaigns with Artificial Intelligence

Physics-informed Data-driven Surrogate Modeling for Advancing Experiments and the Study of Novel Materials

Semi-mechanistic Gaussian Process Model for Disentangling Structural and Chemical Influences on Material Properties

Spatiotemporal Prediction of Microstructure by Deep Learning

Synthesizing Realistic Images of Material Microstructures Using Convolutional Neural Networks

Thermodynamic Analysis for the Design of High-strength Aluminum Alloys at High Temperatures

Topological Class Detection with Attention-based Neural Network

Uncertainty Prediction for a Variety of Material Properties Modelled via Machine Learning

Uncertainty Quantification Framework for Robust Design of Fatigue Critical Alloys

Uncertainty Quantified Parametrically Homogenized Constitutive Models for Multi-scale Predictions of Fatigue Crack Nucleation in Ti Alloys

Understanding Fission Gas Bubble Distribution, Lanthanide Transportation, and Thermal Conductivity Degradation in Neutron-irradiated α-U Using Machine Learning

Using Machine Learning to Improve Melt Pool Prediction in Additive Manufacturing: Data Denoising and Predictive Modeling

Using Polycrystals for Bayesian Inference and Uncertainty Quantification of Grain Boundary Structure-property Models

Variational System Identification of the Partial Differential Equations Governing Microstructure Evolution in Materials: Inference over Sparse and Spatially Unrelated Data

Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement