[CP2K-user] [CP2K:20645] System Exploded During MD Simulation with NequIP Potential

['Kam-Tung Chan (Tonybill)' via cp2k]

Dear CP2K users,

I ran an MD simulation with a trained machine learning potential, NequIP, 
using CP2K. However, the system was not stable, and starting the first step 
of the MD run, the temperature increased from 300 K to 534 K. 

I was following the documentation and the tutorial on Google Colab to 
construct my input file:
https://manual.cp2k.org/trunk/methods/machine_learning/nequip.html
https://colab.research.google.com/github/gabriele16/cp2k/blob/nequip-cp2k-colab/colab/allegro-cp2k-tutorial.ipynb
I am unsure if it is due to the problem of units, as my trained NequIP 
model has the units in angstrom, eV, and eV/angstrom.

I really appreciate any help you can provide!

Best,
Tonybill

-- 
You received this message because you are subscribed to the Google Groups "cp2k" group.
To unsubscribe from this group and stop receiving emails from it, send an email to cp2k+unsubscribe at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/cp2k/f4f9aadf-2afe-4d5e-aedd-597ac0b3671cn%40googlegroups.com.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20240831/3909bc8b/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Nitrate_Solution_NequIP_MD.out
Type: application/octet-stream
Size: 78172 bytes
Desc: not available
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20240831/3909bc8b/attachment-0001.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Nitrate_Solution_NequIP_MD.inp
Type: chemical/x-gamess-input
Size: 1402 bytes
Desc: not available
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20240831/3909bc8b/attachment-0001.inp>