Setting the standard for machine learning in phase field prediction: a benchmark dataset and baseline metrics
Laura Hannemose Rieger, Klemen Zelič, Igor Mele, Tomaž Katrašnik, Arghya Bhowmik · 2024
Read Setting the standard for machine learning in phase field prediction: a benchmark dataset and baseline metrics by Laura Hannemose Rieger, Klemen Zelič, Igor Mele, Tomaž Katrašnik, Arghya Bhowmik (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-11585596.txt.
Description
Laura Hannemose Rieger and four co-authors present a 2024 paper offering a shared testbed for machine learning on phase field models. Phase field models simulate how microstructures evolve, bridging atomic and everyday scales, but they run slowly. Machine learning could speed them up, yet new algorithms need common data to prove themselves. The team publishes an accessible, documented benchmark data set for this task.
They validate the data set by training a U-Net, a popular neural network, to predict the simulations. Its errors matched earlier studies and held up across different domain sizes. The authors frame the release as a standard the field lacked: one data set and baseline numbers that future methods must beat. The resource targets researchers accelerating materials simulations with learning methods.
Catalog record
| CREATOR | Laura Hannemose Rieger, Klemen Zelič, Igor Mele, Tomaž Katrašnik, Arghya Bhowmik |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |