Skip to main content

Fast Learning of Atomistic Rare Events

Project description

Build Status documentation pypi activity codecov

FLARE: Fast Learning of Atomistic Rare Events

FLARE is an open-source Python package for creating fast and accurate interatomic potentials. Documentation of the code can be accessed here:

We have an introductory tutorial in Google Colab available here.

Major Features

  • Gaussian Process Force Fields

    • 2- and 3-body multi-element kernels
    • Maximum likelihood hyperparameter optimization
  • On-the-Fly Training

    • Coupling to Quantum Espresso, CP2K, and VASP DFT engines
  • Mapped Gaussian Processes

    • Mapping to efficient cubic spline models
  • ASE Interface

    • ASE calculator for GP models
    • On-the-fly training with ASE MD engines
  • Module for training GPs from AIMD trajectories

Many-body extension

If you want to train a more accurate many-body potential on the fly, check out our many-body extension flare++, with an introductory tutorial available here.


  1. To train a potential on the fly, you need a working installation of a DFT code compatible with ASE (e.g. Quantum ESPRESSO, CP2K, or VASP).
  2. FLARE requires Python 3 with the packages specified in requirements.txt. This is taken care of by pip.


FLARE can be installed in two different ways.

  1. Download and install automatically:
    pip install mir-flare
  2. Download this repository and install (required for unit tests):
    git clone
    cd flare
    pip install .


We recommend running unit tests to confirm that FLARE is running properly on your machine. We have implemented our tests using the pytest suite. You can call pytest from the command line in the tests directory to validate that Quantum ESPRESSO or CP2K are working correctly with FLARE.

Instructions (either DFT package will suffice):

pip install pytest
cd tests
PWSCF_COMMAND=/path/to/pw.x CP2K_COMMAND=/path/to/cp2k pytest


  • If you use FLARE in your research, or any part of this repo (such as the GP implementation), please cite the following paper:

    [1] Vandermause, J., Torrisi, S. B., Batzner, S., Xie, Y., Sun, L., Kolpak, A. M. & Kozinsky, B. On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events. npj Comput Mater 6, 20 (2020).

  • If you use MGP or LAMMPS pair style, please cite the following paper:

    [2] Xie, Y., Vandermause, J., Sun, L. et al. Bayesian force fields from active learning for simulation of inter-dimensional transformation of stanene. npj Comput Mater 7, 40 (2021).

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for mir-flare, version 0.1.8
Filename, size File type Python version Upload date Hashes
Filename, size mir_flare-0.1.8-py3-none-any.whl (417.2 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size mir-flare-0.1.8.tar.gz (174.0 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page