Graph convolutional network for predicting abnormal grain growth in Monte Carlo simulations of microstructural evolution
Ryan Cohn, Elizabeth A Holm · 2024
Read Graph convolutional network for predicting abnormal grain growth in Monte Carlo simulations of microstructural evolution by Ryan Cohn, Elizabeth A Holm (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11618464.txt.
Description
Ryan Cohn and Elizabeth Holm forecast abnormal grain growth with graph networks in this 2024 study. In metals, a few grains sometimes balloon while neighbors stay small, a quirk that resists prediction. The team generated a large set of Monte Carlo simulations of the process.
Simple graph convolution networks learned to flag which starting microstructures would turn abnormal. They beat a standard image-based method with better accuracy and fewer false alarms. The networks also revealed which features matter and at what scale. Doubt analysis of the simulations adds guidance for later work, the authors note.
Catalog record
| CREATOR | Ryan Cohn, Elizabeth A Holm |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |