ProgramMaster Logo
Conference Tools for Materials Science & Technology 2020
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting Materials Science & Technology 2020
Symposium Materials Design through AI Composition and Process Optimization
Presentation Title Realistic 3D Microstructure Generation via Generative Adversarial Networks
Author(s) Elizabeth A. Holm, Tim Hsu, William K Epting, Hokon Kim, Harry W. Abernathy, Gregory A. Hackett, Anthony D. Rollett, Paul Salvador
On-Site Speaker (Planned) Elizabeth A. Holm
Abstract Scope Generating large data sets of realistic, statistically equivalent, 3D microstructures is a prerequisite for computational surveys and optimization approaches. Using large-scale 3D microstructural data, a Generative Adversarial Network (GAN) model has been implemented to learn and generate realistic 3D polyphase solid oxide fuel cell microstructures. Nearly limitless microstructural instances can be generated at relatively minimal cost compared to conventional simulation/statistical approaches. Besides being visually similar to the experimental microstructures, the GAN-generated microstructures are statistically similar with respect to geometric and topological metrics (e.g., particle size, surface area, triple-phase-boundary density). Furthermore, performance simulations applied to the GAN-synthetic microstructures result in realistic electrochemical response. This suggests the GAN model is capable of learning and generating microstructures that captures all salient aspects of the target system. Intriguingly, limitations of the GAN in resolving outlier structures not only provide materials insight, but also reveal opportunities to understand and improve the GAN approach itself.


A Physics-informed AI Assistant for Atomic Layer Deposition
Accelerating the Discovery of New DP-steel Using Machine Learning-based Multiscale Materials Simulations
AI-driven Discovery of Novel High Entropy Semiconductor Alloys
Artificial Intelligence for Material and Process Design
Deep Materials Informatics: Illustrative Applications of Deep Learning in Materials Science
Enabling Process Optimization Using High-throughput Machine Learning-based Image Analysis
High-fidelity Accelerated Design of High-performance Electrochemical Systems
Investigating Crystallographic Texture Control Using Laser Powder-bed Fusion Additive Manufacturing
Learning Through Domain Knowledge: A Hierarchical Machine Learning Approach Towards the Prediction of Thermoplastic Polyurethane Properties
Machine Learning Prediction of Glass Properties Informed by Synthetic Data
MeltNet: Predicting alloy melting temperature by machine learning
Multi-information Source Batch Bayesian Optimization of Alloys
NEW - Polymer Property Prediction and Design through Multi-task Learning
Realistic 3D Microstructure Generation via Generative Adversarial Networks
Statistics-based Microstructural Digital Image Correlation Method for Estimating Ex-situ Strain from Dissimilar Micrographs
Text and Data Mining for Materials Synthesis

Questions about ProgramMaster? Contact