Source
Broadening access to Skala creates a faster path to predictive DFT
Microsoft Research released Skala 1.1, a deep-learning tool for density functional theory (DFT) molecular simulations. The update improves accuracy in thermochemistry, reaction kinetics, and molecular structure prediction.
Why it matters
More accurate molecular simulations help scientists in fields like drug discovery and energy technologies design materials more efficiently. Integrating this tool into common software allows researchers to achieve high accuracy without needing expensive computational resources.
The details
- Skala 1.1 was trained on 2.5x more data than the previous version.
- It is available in CP2K and integrating into Psi4, FHI-aims, ORCA, and VASP.
- Skala 1.1 achieved a weighted average error of 2.8 kcal/mol on GMTKN55.
Get the weekly recap
The stories like this one, picked and explained — once a week, straight to your inbox.