Author Topic: MTP initial training set  (Read 1368 times)

0 Members and 1 Guest are viewing this topic.

Offline korandofficial

  • Regular QuantumATK user
  • **
  • Posts: 6
  • Country: us
  • Reputation: 0
    • View Profile
MTP initial training set
« on: June 24, 2022, 21:34 »
Hi dear ATK technicians,

I am trying to use mtp to generate potential of Bi2Se3. Should I use initial training sets from database from those have similar chemical compounds (i.e. Bi2Se3) or other compounds of Bi and Se like Bi8Se9 are acceptable?

Also, how many initial training set is enough for accurate result?

Thanks in advance

Offline Julian Schneider

  • QuantumATK Staff
  • QuantumATK Guru
  • *****
  • Posts: 160
  • Country: dk
  • Reputation: 25
    • View Profile
Re: MTP initial training set
« Reply #1 on: July 6, 2022, 12:20 »
Hi Korand,

Ideally, you should use similar compounds in the training data, so if you would like to generate a MTP for Bi2Se3, then the training data should contain some Bi2Se3 configurations, e.g. from our database, or from the materials project database, which QuamtumATK has a interface to. IT can also make sense to include other compunds, then the trained MTP would be applicable to a broader range of compositions.

For a given crystal structure, we recommend that you use our crystal training protocol https://docs.quantumatk.com/manual/Types/crystalTrainingRandomDisplacements/crystalTrainingRandomDisplacements.html.
A total number of 100-200 configurations per crystal structure are usually enough. The example https://docs.quantumatk.com/manual/Types/crystalTrainingRandomDisplacements/crystalTrainingRandomDisplacements.html#usage-examples should be a good starting point.
You should run this protocol for the relevant crystal structures that you want to include in the training. Then you can combine all these training sets to train a MTP, which should already work well to describe the crystal phases.

To extend the training data to other configurations (e.g. amoprhous, or high temperature) you can run active learning simulations, which generates additional training configurations. This process is described here: https://docs.quantumatk.com/tutorials/mtp_hfo2/mtp_hfo2.html

Hope this helps!

Best regards,
Julian