pypolymlp 0.19.9

This is the pypolymlp module.

A generator of polynomial machine learning potentials

pypolymlp is a Python code designed for the development of polynomial machine learning potentials (MLPs) based on datasets generated from density functional theory (DFT) calculations. The code provides functionalities for fitting polynomial models to energy, force, and stress data, enabling the construction of accurate and computationally efficient interatomic potentials. In addition to potential development, pypolymlp allows users to compute various physical properties and perform atomistic simulations using the trained MLPs.

Polynomial machine learning potentials

A polynomial MLP represents the potential energy as a polynomial function of linearly independent polynomial invariants of the O(3) group. Developed polynomial MLPs are available in Polynomial Machine Learning Potential Repository.

Citation of pypolymlp

“Tutorial: Systematic development of polynomial machine learning potentials for elemental and alloy systems”, A. Seko, J. Appl. Phys. 133, 011101 (2023)

@article{pypolymlp,
    author = {Seko, Atsuto},
    title = "{"Tutorial: Systematic development of polynomial machine learning potentials for elemental and alloy systems"}",
    journal = {J. Appl. Phys.},
    volume = {133},
    number = {1},
    pages = {011101},
    year = {2023},
    month = {01},
}

Required libraries and python modules

• python >= 3.10
• numpy != 2.0.*
• scipy
• pyyaml
• setuptools
• eigen3
• pybind11
• openmp (recommended)

[Optional]

• phonopy
• phono3py
• symfc
• sparse_dot_mkl
• spglib
• ase
• joblib
• matplotlib, seaborn

How to install pypolymlp

• Install from conda-forge (Recommended)

Version	Last Update	Downloads	Platform	License

conda create -n pypolymlp-env
conda activate pypolymlp-env
conda install -c conda-forge pypolymlp

• Install from PyPI

conda create -n pypolymlp-env
conda activate pypolymlp-env
conda install -c conda-forge numpy scipy pybind11 eigen cmake cxx-compiler
pip install pypolymlp

Building C++ codes in pypolymlp may require a significant amount of time.

• Install from GitHub

git clone https://github.com/sekocha/pypolymlp.git
cd pypolymlp
conda create -n pypolymlp-env
conda activate pypolymlp-env
conda install -c conda-forge numpy scipy pybind11 eigen cmake cxx-compiler
pip install . -vvv

Building C++ codes in pypolymlp may require a significant amount of time.

Using pypolymlp for Polynomial MLP Development

To develop polynomial MLPs from datasets obtained from DFT calculations, both the command-line interface and the Python API are available. Several procedures for generating structures used in DFT calculations are also supported.

• Tutorials

  1. Development of a single on-the-fly MLP
  2. Development of a single general-purpose MLP
  3. Development of convex hull (Pareto-optimal) MLPs

• MLP Developments

  • VASP (Command line interface)
  • VASP (Python API)
  • Structure-Properties general datasets (Python API)
  • Phono3py (Python API)
  • OpenMX
  • Notes on parameter and dataset settings

• Utilities for MLP development

  • Dataset Generation
    • Generator of DFT random structures
    • Compression of vasprun.xml files
    • Automatic division of DFT dataset
  • Convex hull (Pareto-optimal) MLP search
  • Atomic energies
  • Generator of portable model for OpenKIM
  • Other utilities

• Experimental Features

  • SSCHA free energy model
  • Electronic free energy model
  • Substitutional disordered model
  • Spin-dependent model

Using pypolymlp for Polynomial MLP Calculations

In version 0.8.0 and earlier, polymlp files are generated in plain text format as polymlp.lammps. Many polynomial MLPs distributed in the Polynomial MLP Repository are also provided in this plain text format. Starting from version 0.9.0, polymlp files are generated in YAML format as polymlp.yaml. Both formats are supported by the command-line interface and the Python API.

The following calculations can be performed using pypolymlp with either polymlp.yaml or polymlp.lammps files.

• Notes on hybrid polynomial MLPs

• Property calculations and simulation

  • Energy, forces, stress tensor
  • Formation energy
  • Equation of states
  • Local geometry optimization
  • Elastic constants
  • Phonon properties, Quasi-harmonic approximation
  • Force constants
  • Lattice thermal conductivity
  • Polynomial invariants
  • Systematic property calculations
  • Repository entry generation

• Experimental features

  • Self-consistent phonon calculations
  • Finite-temperature local geometry optimization
  • Finite-temperature elastic constants
  • Molecular dynamics
  • Thermodynamic integration using molecular dynamics
  • Thermodynamic property calculation
  • Evaluation of atomic-configuration-dependent electronic free energy

• How to use polymlp in other calculator tools

  • LAMMPS
  • ASE
  • OpenKIM
  • phonopy and phonon3py

Theoretical Background

• Polynomial Invariants and Potential Models