calorine
calorine is a Python library for constructing and sampling neuroevolution potential (NEP) models via the GPUMD package. It provides ASE calculators, IO functions for reading and writing GPUMD input and output files, as well as a Python interface that allows inspection of NEP models. Tutorials with common usage examples can be found under Tutorials, and a detailed function reference can be found under Function reference.
The following snippet illustrates how a CPUNEP calculator instance can be created given a NEP potential file, and how it can be used to predict the potential energy, forces, and stress for a structure.
from ase.io import read
from ase.build import bulk
from calorine.calculators import CPUNEP
structure = bulk('PbTe', crystalstructure='rocksalt', a=6.7)
calc = CPUNEP('nep-PbTe.txt')
structure.calc = calc
print('Energy (eV):', structure.get_potential_energy())
print('Forces (eV/Å):\n', structure.get_forces())
print('Stress (GPa):\n', structure.get_stress())
If you use calorine in any of your publications, please follow the citation instructions for how to properly cite this work.
calorine and its development are hosted on gitlab.