User’s Guide

This section describes how to use librascal for a few common tasks in atomistic machine learning, from calculating descriptors, to training and saving a potential energy surface model, to using that model to run molecular dynamics[1].

Contents

• Fitting a Model with Librascal
• Saving and Loading in Librascal
• Running MD Simulations with a Librascal Model
  • i-PI
  • ASE (Python)
  • LAMMPS (under construction)
  • Others

1

Disclaimer: This section is currently under construction. The most complete examples of how to use librascal are currently in the examples/ directory of the main repository.