Project Description
Material Parameter Estimation from Microstructure Morphologies with Machine Learning
Faculty Advisor: Dr. Mahmood Mamivand
The goal of this project is to use machine learning (ML) techniques to estimate materials parameters from microstructure morphologies. There are some materials parameters, such as interfacial energies, that are very challenging to measure either experimentally or computationally. In this project, we combine high-fidelity models with deep learning algorithms to enable the estimation of materials parameters from microstructure morphologies.
Role of Participant(s):
In this project, students learn high-fidelity models such as the phase-field method to generate databases for machine learning algorithms. Then students learn to quantify the morphology of the images with deep learning algorithms and finally use the ML techniques to correlate the microstructures to the material parameters. Ideally, we would use the developed algorithms to read experimental transmission electron microscopy images to predict material parameters.