Date: Sunday, March 23
Time: 1:00 p.m. to 5:30 p.m.
Location: MGM Grand Las Vegas Hotel & Casino
Sponsored by: Integrated Computational Materials Engineering Committee
Course Description and Scope
This half-day short course provides a hands-on introduction to GPU-accelerated tools for modeling grain growth using Python. Participants will explore innovative techniques that combine computational efficiency with cutting-edge machine learning to simulate grain growth phenomena.
The course will cover two primary approaches:
- Mode-Filter Based Grain Growth Models: Explore the physics-based model that uses a model filter to predict grain growth.
- Machine Learning-Driven Grain Growth Models: Discover how machine learning can predict and simulate grain growth behavior.
Participants will work directly with Python-based tools that leverage GPU acceleration for rapid simulations, making it possible to analyze and visualize grain growth with unprecedented speed. This hands-on workshop ensures attendees not only understand the theoretical background but also gain practical skills to apply these tools in their own research.
All attendees will receive access to the tools during the course and retain their use afterward, allowing them to seamlessly integrate these methods into their workflow. Whether you’re a seasoned modeler or new to grain growth simulations, this course will empower you with state-of-the-art techniques for fast, accurate, and scalable modeling.
Course notes and materials will be provided electronically to participants. Participants will receive a post-event digital credential.
Who Should Attend?
The target audience for this course includes graduate students, scientists, and engineers interested in grain growth modeling.
Instructors
Michael Tonks
Department of Materials Science & Engineering
University of Florida (Lead Instructor)
About the Instructor
Michael Tonks is a professor and the Alumni Professor of Materials Science and Engineering at the University of Florida (UF). Prior to joining UF in Fall 2017, he was an assistant professor of Nuclear Engineering at the Pennsylvania State University for 2 years and a staff scientist in the Fuels Modeling and Simulation Department at Idaho National Laboratory for 6 years. Tonks was the original creator of the mesoscale fuel performance tool MARMOT and lead its development for five years. He helped to pioneer the approach taken in the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program to use multiscale modeling and simulation (both atomistic and mesoscale) to inform the development of materials models for the BISON tool that are based on microstructure rather than burn-up, and he won the NEAMS Excellence Award for that work in 2014 and the Presidential Early Career Award for Scientists and Engineers in 2017. He won the TMS Brimacombe Medal in 2022. His research uses mesoscale modeling and simulation coupled with experimental data to investigate the impact of irradiation induced microstructure evolution on material performance. He is also investigating and applying advanced methods for verification and validation with statistical uncertainty quantification.
Joel Harley
Department of Electrical & Computer Engineering
University of Florida
About the Instructor
Joel Harley is an associate professor and Kent and Linda Fuchs Faculty Fellow in the Department of Electrical and Computer Engineering at the University of Florida. His research interests integrate physical knowledge with machine learning to advance fundamental science and engineering. Harley has received numerous department and college teaching awards at the University of Florida. He also received the 2021 Achenbach Medal from the International Workshop on Structural Health Monitoring, the 2020 IEEE Ultrasonics, Ferroelectrics, and Frequency Control Society Star Ambassador Award, and a 2020 and 2018 Air Force Summer Faculty Fellowship. He has published over 80 technical journal papers and over 90 conference proceedings. He has previously taught a short course on artificial intelligence for the Review of Quantitative Nondestructive Evaluation Conference. He is also a member of the IEEE Frequency Control Society, the IEEE Signal Processing Society, and the Acoustical Society of America.
Zhihui Tian
Department of Electrical & Computer Engineering
University of Florida
Bio coming soon
Course Outline
- 1:00 p.m. to 1:30 p.m. Grain growth modeling summary (Tonks)
- 1:30 p.m. to 3:15 p.m. Mode filter model (Harley, Tian)
- 3:15 p.m. to 3:30 p.m. Break
- 3:30 p.m. to 5:30 p.m. Machine learning models (Harley, Tian)
How Do I Register?
Courses and workshops are open exclusively to registrants for the TMS 2025 Annual Meeting & Exhibition and are included as part of the conference registration fee. If you wish to participate in one of the offered courses, please make your selection when you register for TMS2025. All courses are held on Sunday, March 23, so make your travel plans accordingly.
Register for TMS2025