-
Notifications
You must be signed in to change notification settings - Fork 10
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add interface for NEP potential #54
Comments
A great idea, but I agree it's likely not high priority (as we have interfaces for other potentials already, and the most timely thing in my mind is to get the phonon and RSS workflows ready). I would mark this as an "enhancement" in the list of issues. @YuanbinLiu is in the process of merging the fitting routines into the main branch – once that is done you could look at how to easily integrate the NEP interface? |
Hi @vlderinger , small update here -> We have added NEP makers to atomate2 now and should be merged soon. Thus we can add a fitting interface for this potential to autoplex soon 😄 |
Also I might just add here that anything beyond the fitting process has only been properly implemented for GAP until now. Just to keep this in mind. |
Hi , just a small update: if anyone wants to pick up integrating NEP fitting in autoplex, now it should be possible as a new version of calorine has been released that supports the latest ASE version. materialsproject/atomate2#1026 https://gitlab.com/materials-modeling/calorine/-/merge_requests/167 |
Nep is low-priority from my side. I will try to improve some of the fitting interfaces at first (see #178 ) |
Already ase interface exists for this potential in python packages along with training.
See for example :
PyNEP
calorine
So, it should be easy to add it to our workflow as well, without much effort on the coding side, I feel.
Some recent publication on this potential : General-purpose machine-learned potential for 16 elemental metals and their alloys
Authors have already shown applicability for harmonic phonons and MD simulations. I feel it could fit nicely in our package.
Any thoughts on this @JaGeo, @vlderinger, @QuantumChemist ,@YuanbinLiu?
Also, I won't prioritize this as of now. It is not necessary to add it for the initial release.
I just wanted to add it as a note here so I don't forget it 😄
The text was updated successfully, but these errors were encountered: