Can LCAO calculator srcipt be input in crystal structure prediction script?

[Lim changmin]

Dear all

Hello, I am trying to make MTP for Carbon-doped Ge(n)Te(m) (n,m are integers).
To start MTP, the tutorial for TiSi MTP indicate to use crystal structure first and then train amorphous.
For amorphous, We can make these structures with packmol, however for crystals, we cannot find structures with C, Te, Ge included.

Therefore I am trying to use crystal structure prediction(i.e. csp). From tutorial, it used forcefield calculator, but I want to use LCAO for more accuracy.
But LCAO requires bulk configuration defined first.
And the script in csp only show elements and the calculator script is prior to elements.
Can someone help me how to revise LCAO for csp?

Thank you

[Lim changmin]

Also, I have additional question

I attempted to create an MTP (Machine Learning Interatomic Potential) for GeTe that could be applied to structures with different Ge and Te ratios.

For the ML-FF (Machine Learning Force Field) crystal training, I only used GeTe structures with a 1:1 ratio, as no other compositions were available.

However, for the ML-FF amorphous training, I generated amorphous GeTe structures using Packmol with varying Ge:Te ratios, including 1:1, 1:4, and 23:77, among others.

My question is:
Since I only used 1:1 ratio GeTe for crystal training, while incorporating various Ge:Te ratios for amorphous training, can the resulting MTP still be considered reliable?

I am currently validating the MTP, and the fitted results seem reasonable(figure posted). However, I am still uncertain whether the difference in training data composition could affect the generalization and accuracy of the MTP.

Would this discrepancy impact the reliability of my potential?
Thank you