MM2SF

Jan 1, 2024
Go to Project Site

About

MM2SF automatically generates optimised Atom-Centred Symmetry Functions (ACSFs) for use as descriptors in neural network interatomic potentials. Given a molecular dynamics trajectory or normal-mode sampling, it applies a Gaussian Mixture Model (GMM) to decompose the chemical space into well-defined clusters, then selects symmetry function parameters that accurately describe each region.

Supported symmetry function types:

  • Two-body (radial) — Grad
  • Three-body (angular) — Gang (modified functional form)

Installation

pip install git+https://github.com/m-gallegos/MM2SF.git

Or from a downloaded zip:

pip install MM2SF-main.zip
Machine Learning Neural Network Potentials Symmetry Functions Descriptor Generation
Ángel Martín Pendás
Ángel Martín Pendás
Principal Investigator

Professor of Physical Chemistry at the University of Oviedo. Pioneer of orbital-invariant approaches to chemical bonding, including the Interacting Quantum Atoms (IQA) energy partition and topological electron population statistics.