Conference Logo ProgramMaster Logo
Conference Tools for 2026 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 2026 TMS Annual Meeting & Exhibition
Symposium Artificial Intelligence Applications in Integrated Computational Materials Engineering (AI-ICME)
Presentation Title Analyzing Microstructural Interactions in Materials Using Explainable Neural Networks
Author(s) Benjamin Rhoads, Joseph Hafen, Lars Kotthoff, Samrat Choudhury
On-Site Speaker (Planned) Benjamin Rhoads
Abstract Scope Simulating microstructure evolution in materials relies on governing equations that incorporate energetic contributions derived from physical laws. These simulations provide valuable data, but discovering deeper insight – such as the nature of mutual interactions between features in the microstructure – remains a challenge. In this study, we propose a method to interpret phase field-generated microstructure data using a neural network. Specifically, we train a physics-constrained neural network (PCNN) and apply saliency analysis (SA) to extract the strength of interaction between features and energy components during the microstructure evolution. This approach enables us to quantify both the range and strength of interactions and validate them against known physical behaviors of the material system. This method offers a promising route to uncover meaningful physical mechanisms during the evolution of microstructures.
Proceedings Inclusion? Planned:
Keywords Machine Learning, Modeling and Simulation, Computational Materials Science & Engineering

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

AI Augmented Molecular Dynamics Modeling of Novel Zeolite Nano Resins for Targeted Advanced Water Treatment
AI for Alloy Design in Extreme Environments
AlloyGPT 2.0: Develop A Self-Adaptive Multi-Agent Autonomous Framework for Additive Manufacturable Alloy Design
An Extensible, Data-Driven Platform for Automated Atomic Structure Analysis
Analyzing Microstructural Interactions in Materials Using Explainable Neural Networks
Artificial Intelligence for Additive Manufacturing
Automated Implementation of Axiomatic Design for Materials System Chart Using Large Language Models
Autonomous Fractography Analysis Framework Driven by Large Language Models
Blacksmithing AI: Using a Large Language Model to Predict Workpiece Shapes and Manufacturing Operations for Automated Manufacturing
Breaking Boundaries: Texture-Aware AI for Metallography
Data-Driven Design of Two-Phase Metallic Spinodoids for Thermomechanical Properties
Development of Machine Learning Interatomic Potentials for Ni-Al-Ti Systems to Study γ/γ' Phase Properties in Superalloys
From CALPHAD to AI: High-Throughput Pathways for Functionally Graded Alloy Design and Additive Manufacturing
Generative AI–Driven Process–Structure–Property Optimization for Materials Discovery
Graph Neural Network-Based Forecasting of Atomic Dynamics at Grain Boundaries
H-13: Establishing a Large Language Model-based Systematic Alloy Design Strategy for Advanced Titanium Alloys
H-14: Ionic Transport Properties and Phase Stability of Solid Electrolyte Material Li7La3Zr2O12: A Deep-Neural-Network Molecular Dynamics Investigation
H-15: Machine-Learned Force Field for the Energetic Molecular Crystal LLM-105
Harnessing AI for Prediction of Abnormal Grain Growth Using 3D Experimental Data
Integrating Microstructural, Diffraction, and Compositional Data for Predictive Materials Modeling
Large Language Model Agents for Atomistic Simulation Workflows
Leveraging Large Language Models for Inverse Design of Processing Parameters in Materials Engineering
Machine Learning-Augmented Finite Volume Modeling and Inverse Optimization of Velocity and Pressure Distribution of Bentonite Slurry in Slurry Shield Tunneling Applications
Machine Learning Prediction of Antioxidant Additive Performance from Atomistic Simulations
ML-Accelerated ICME Framework for Solid Phase Processing of Nuclear Cladding Materials
Physics-Constrained Neural Network for Increased Generalizability in Predicting Material Microstructure Evolution
Physics-Informed Neural–Cellular Framework for Predicting Grain Morphology and Microstructural Evolution in Metal Additive Manufacturing Simulation
Quantifying Relationship Between Creep and Microstructure of Metals Using Symbolic Regression
Reward Engineering in AI-Driven Materials Discovery and Design
Robust Physics-Informed Neural Networks for Modeling Oxide Film Growth in Corrosion Science
Toward an Interactive AI-Enabled Platform for Critical Materials Reduction: From Forecasting to Processing
Toward DFT-Accurate Modeling of HfNbTaTiZr High Entropy Alloy Using Moment Tensor Potential
Using Agentic AI Programming Tools for ICME Code Development
Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement