ProgramMaster Logo
Conference Tools for 2024 TMS Annual Meeting & Exhibition
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Symposium
Meeting 2024 TMS Annual Meeting & Exhibition
Symposium AI/Data Informatics: Computational Model Development, Verification, Validation, and Uncertainty Quantification
Sponsorship TMS Materials Processing and Manufacturing Division
TMS: Computational Materials Science and Engineering Committee
Organizer(s) Kamal Choudhary, National Institute of Standards and Technology
Saaketh Desai, Sandia National Laboratories
Dennis M. Dimiduk, BlueQuartz Software LLC
Shreyas J. Honrao, Aionics
Dehao Liu, Binghamton University
Darren C. Pagan, Pennsylvania State University
Saurabh Puri, Microstructure Engineering
Ashley D. Spear, University of Utah
Francesca M. Tavazza, National Institute of Standards and Technology
Anh Tran, Sandia National Laboratories
Huseyin Ucar, California Polytechnic University,Pomona
Yan Wang, Georgia Institute of Technology
Houlong Zhuang, Arizona State University
Scope A critical component of the development and deployment of new technologies is the discovery, characterization, optimization, and transition of materials. Computational investigations at various spatio-temporal scales have proven to be effective tools for all components of this material design process. Recently, both high-throughput computational and experimental approaches have facilitated characterization of selected incredibly large spaces of possible materials and contributed to the formation of large materials databases. Furthermore, text mining methods applied to vast sets of scientific literature are emerging for machine-learned synthesis methods. Finally, advanced scientific machine learning (SciML) approaches increasingly reveal their values for developing surrogate material models, and for improving predictive capabilities for material processing and performance. Thus, integrating computed data with experiments supports viewing artificial intelligence (AI) and data informatics as a means to accelerate the search for new materials and advance engineered systems, as well as to understand and predict complex behavior of existing materials. However, all these computational frameworks, including those physics-based or data-driven methods, need a careful assessment of their uncertainties at different scales. Beyond uncertainty quantification, efficacy of any simulation method needs to be validated using experimental or other high-fidelity computational approaches.

This symposium will focus on AI methods for materials, AI-ready materials data issues, computational methodology validation, as well as uncertainty quantification, verification, and validation of computational materials models across various scales. The goal of the symposium is to cover these research topics from an interdisciplinary perspective that connects theory and experiment, having a view towards materials applications.

Topics addressed in this symposium will include (but not be limited to):

• Machine learning and artificial intelligence approaches applied to materials science: model development, applications, and validation

• Physics-based regularization of machine learning models

• Data mining: difficulties, techniques, and applications; including development of mineable data features

• Validation and uncertainty quantification

• Materials design under uncertainty

Abstracts Due 07/15/2023
Proceedings Plan Planned:

A Data-driven Active Learning Paradigm to Model Dislocation Mobility From Atomistics
A Data-driven Approach for Predicting the Stress-strain Curves of FCC Polycrystalline Metals
A Dataset of CFD Simulated Industrial Furnace Images for Conditional Automatic Generation with GANs
A Deep Learning Framework for Designing BCC Refractory Multi-principal Element Alloys with Optimized Strength
A Needed Bridge Between the Microscopy and Data Science Communities: Electron Backscatter Diffraction and Machine Learning Case
A Practical Deep Learning Fiber Segmentation Approach in a Manufacturing Setting
Accelerating Defect Predictions in Semiconductors Using Crystal Graphs
Active Learning for Inverse Problems: Bridging Anisotropy to Materials Structure
An Explanatory Model for Microhardness in Friction Stir Processing of 316L Stainless Steel
Automated Analysis of Crystal Structures in X-ray Diffraction Data Using Deep Learning
Automation of Void Identification in Microstructure With Computer Vision
Autonomous Learning of Atomistic Structural Transitions via Physics-inspired Graph Neural Networks
Biases and Limitations in Reported Data of Laser Powder Bed Fusion: Implications for the Learning
Big Microstructure Datasets for Materials Informatics: Using Statistically Conditioned Generative Models to Curate Big Datasets
Calibration of RAFM Steel Micro Mechanical Model for Creep Using Bayesian Optimization and Design of Experiments
Cluster Expansion Approximation Accelerated by a Graph Neural Network Regressor.
Data-Driven Modeling of Performance Degradation in Optoelectronic and Electronic Materials in a High Performance Computing Environment
Enhancing Corrosion Resistant Alloy Design Through Natural Language Processing and Deep Learning
Enhancing Materials Discovery in Vast Composition Spaces: Integrating ML Techniques with FUSE
Experimentally Validated High-dimensional Bayesian Optimization of Dental Adhesives via Adaptive Design
Finding “Trigger Sites” of Reactions Among Heterogeneous Materials From X-ray Microscopic Big Data Using Persistent Homology
Generalizable Graph Neural Network Surrogate Models for Microstructure Analysis
Generalizable Graph Neural Network to Describe the Local Atomic Environment in High Entropy Alloys
Generative Model for Closed-loop Multi-property Materials Predictions and Discovery
Genetic Programming Derived Stress-rupture Model for Lifetime Estimation of Alloy 617
Global Uncertainty Reduction Through Efficient Acquisition Function Candidate Selection in Predefined Design Spaces for Predicting NMR Peak Positions
Harnessing Equivariant Neural Networks for High-throughput Screening of Novel Superconductors
High-throughput Micromechanical Simulations Framework and Its Applications to Predict Microstructure-property Relationships Using a Machine Learning Approach
High-throughput Screening of Li Solid-State Electrolytes with Bond Valence Methods and Graph Neural Networks
How Solid is Your Ground Truth? Interdisciplinary Application of Uncertainty Quantification to Experimental Indentation Testing
Improving Prediction of Microstructures Using Physics-informed Machine Learning
Inferring Defect Distributions in Additive Manufacturing - A Stochastic Inverse Approach to Multiscale Direct Numerical Simulations
Invertible Temper Modeling Using Normalizing Flows
Investigation of In-liquid Ordering Mediated Transformations in Al-Sc via Ab Initio Molecular Dynamics and Unsupervised Learning
J-1: Accelerating Materials Discovery Using Conditional Generative Adversarial Networks
J-4: Development of Machine Learning Interatomic Potentials for Complex Ceramics
J-5: Modeling the Precipitation of Ni4Ti3 in Near-equiatomic NiTi Alloys
J-6: Annotating Materials Science Text: A Semi-Automated Approach for Crafting Outputs with Gemini Pro
Learning Incremental Forging Policies for Robotic Blacksmithing
Leveraging Machine Learning to Increase Computational Efficiency in Electrochemical Systems: An Application to Galvanic Corrosion
Machine Learning-guided Investigation of the Impacts of Grain Geometry on Twin Formation in MgY Alloys
Machine Learning Guided Friction Stir Welding of AA7075-T6 Aluminum Alloy
Machine Learning Guided Selection of High Temperature High Entropy Refractory Ceramics
Machine Learning Towards Predicting Hot Crack Susceptibility
Mapping Anisotropic Yield Surface Models to Surrogate Isotropic Models Using Strongly Typed Interpretable Machine Learning
Microstructural Analysis of Stainless Steel Backscatter Electron Images by Combining EBSD Data and Deep Learning
Modeling the Microstructure Evolution of a 3D Polycrystal Using a Recurrent Neural Network With Physics Informed Loss Functions
Natural Language Processing and Large Language Models for Automated Extraction of Materials Chemistry Data from Literature
Not as Simple as We Thought: A Rigorous Examination of Data Aggregation in Materials Informatics
Optimizing the Thermal Management of Hot Metal Ladle Cars Through Artificial Intelligence
Physics-constrained Bayesian Neural Networks to Predict Grain Evolution
Physics-Informed Convolutional Neural Networks for Modeling Structure-property Relationships of Fiber-reinforced Composite Materials
Physics-informed Machine Learning Model for Plasticity-mediated Void Growth in FCC Single Crystals
Physics-Informed Machine Learning Prediction of Fe-C Solidification
Predicting Fracture Toughness with Microstructure Sensitivity Using an Elasto-viscoplastic Fast Fourier Transform Model
Reduced-Dimension Surrogate Modeling for Microstructure Prediction
Refractory Oxidation Database (RefOxDB): A FAIR Approach to Analyzing Oxidation Kinetics and Enhancing Oxidation Resistance
Research on the Model of Matching Inventory Plates with Order Contracts of Steel Enterprises
Role of Training Dataset on Machine Learning Based Grain Growth Model
Simulating Castable Aluminum Alloy Microstructures With AlloyGAN Deep Learning Model
Size Estimation of Sintered Alumina by Deep Leaning
Stochastic Inverse Microstructure Design
Temperature Prediction of Continuous Casting Slab Based on Improved Extreme Learning Machine
Thermal Conductivity Homogenization of Composites via Deep Material Network
Thermodynamics and Kinetics of Point Defects in Alloys: A Physics-informed Machine Learning Approach
Towards Rapid Validation and Dynamic Standardisation of Advanced Manufactured Parts
Uncertainty Quantification and Propagation in Modeling Hierarchy for Solidification of Metals and Alloys
Uncertainty Quantification for Accelerated Production of ChIMES ML Force-fields
Understanding the Effects of Environment Gas and Sample Properties on Sample Temperature Distribution in an Optical Floating-zone Crystal-Growth Furnace through Modeling of Heat Transfer
Universal Machine Learning System for Material Properties Prediction
Using Deep Learning to Predict Microstructurally Small Crack Growth Behavior in Three-dimensional Microstructures
Using Unsupervised Learning to Cluster Fatigue Life Based on Small Crack Characteristics

Questions about ProgramMaster? Contact