Graduate Student Brown Bag Seminar

Speaker:         Sheila Whitman, Graduate Student, Applied Mathematics

Title:              Computer Vision for Materials Science        

Abstract:       Machine learning of microstructure–property relationships from data is an emerging approach in computational materials science. Most existing machine learning efforts focus on the development of task-specific models for each microstructure–property relationship. We propose utilizing pre-trained foundational vision models for the extraction of task-agnostic microstructure features and subsequent lightweight machine learning. We demonstrate our approach on two case studies: elastic stiffness of synthetic two-phase microstructures learned from simulation data and Vicker's hardness of Ni-base and Co-base superalloys learned from experimental data. Our results show the potential of foundational vision models for robust microstructure representation and efficient machine learning of microstructure–property relationships without the need for expensive task-specific training or fine-tuning.