About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Computational Thermodynamics and Kinetics
|
Presentation Title |
Machine-Learning Assisted Design of Hydrogen-Storage Materials |
Author(s) |
Tanumoy Banerjee, Kevin Ji, Prashant Singh |
On-Site Speaker (Planned) |
Prashant Singh |
Abstract Scope |
The transition to a low-carbon economy necessitates efficient and sustainable energy storage solutions, with hydrogen emerging as a key contender due to its clean energy carrier potential. Metal hydrides, known for their high storage capacities, have become key considerations for hydrogen storage research. This presentation focuses on our recent developments of data-driven machine learning (ML) approaches for predicting hydrogen storage and solution energy in chemically complex alloys, crucial to advance the design of novel energy storage technologies. We also elucidate on underlying principles controlling metal-hydrogen interaction, diffusion, and energy-barrier in chemically complex alloys through molecular and first-principles simulations. Our findings underscore the importance of feature selection in designing new energy storage materials, which offers valuable insights for future experimental efforts. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, Modeling and Simulation, High-Entropy Alloys |