Machine Learning Interatomic Potentials for Reactive Hydrogen Dynamics at Metal Surfaces Based on Iterative Refinement of Reaction Probabilities
Wojciech · 2023
Read Machine Learning Interatomic Potentials for Reactive Hydrogen Dynamics at Metal Surfaces Based on Iterative Refinement of Reaction Probabilities by Wojciech (2023) 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-10749455.txt.
Description
Wojciech Stark and co-authors train machine learning potentials for hydrogen striking metal surfaces in two thousand twenty-three. Whether hydrogen splits or bounces at a surface drives fuel cells and storage, but exact simulations are far too slow: each chance estimate needs tens of thousands of runs.
The team uses ensemble learning: a pack of neural networks trains together, and their spread flags where the model is unsure. Fresh exact data is then added at those shaky spots, round by round. Two network designs were tested on hydrogen scattering off copper faces. The loop yields reaction chances with honest error bars. The method gives a recipe for trustworthy training data in surface chemistry.
Catalog record
| CREATOR | Wojciech |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |