pantea 0.9.2

Defining an ACSF descriptor

This script demonstrates the process of evaluating an array of atomic-centered symmetry functions (ACSF) for a specific element, which can be utilized to evaluate the descriptor values for any structure. The resulting values can then be used to construct a machine learning potential.

from pantea.datasets import Dataset
from pantea.descriptors import ACSF
from pantea.descriptors.acsf import CutoffFunction, G2, G3

# Read atomic structure dataset (e.g. water molecules)
structures = Dataset.from_runner('input.data')
structure = structures[0]
print(structure)
# >> Structure(natoms=12, elements=('H', 'O'), dtype=float64)

# Define an ACSF descriptor for hydrogen
# It includes two radial (G2) and angular (G3) symmetry functions
descriptor = ACSF('H')
cfn = CutoffFunction.from_cutoff_type(r_cutoff=12.0, cutoff_type='tanh')
descriptor.add(G2(cfn, eta=0.5, r_shift=0.0), 'H')
descriptor.add(G3(cfn, eta=0.001, zeta=2.0, lambda0=1.0, r_shift=12.0), 'H', 'O')
print(descriptor)
# >> ACSF(central_element='H', symmetry_functions=2)

values = descriptor(structure)
print("Descriptor values:\n", values)
# >> Descriptor values:
# [[0.01952943 1.13103234]
#  [0.01952756 1.04312263]
# ...
#  [0.00228752 0.41445455]]

gradient = descriptor.grad(structure, atom_index=0)
print("Descriptor gradient:\n", gradient)
# >> Descriptor gradient:
# [[ 0.04645236 -0.05037861 -0.06146214]
# [-0.10481855 -0.01841708  0.04760214]]

Training an NNP potential

This example illustrates how to quickly create a high-dimensional neural network potential (HDNNP) instance from an in input setting files and train it on input structures. The trained potential can then be used to evaluate the energy and force components for new structures.

from pantea.datasets import Dataset
from pantea.potentials import NeuralNetworkPotential

structures = Dataset.from_runner("input.data")
structure = structures[0]

nnp = NeuralNetworkPotential.from_file("input.nn")

nnp.fit_scaler(structures)
nnp.fit_model(structures)

total_energy = nnp(structure)
print(total_energy)

forces = nnp.compute_forces(structure)
print(forces)

Example files: input.data and input.nn