NOTE: This is the latest release 1.3.3 which includes significant changes compared to the previous version 0.2.4. Please check the updated tutorials and documentations from the links below.
FLARE is an open-source Python package for creating fast and accurate interatomic potentials.
Note:
We implement Sparse GP, all the kernels and descriptors in C++ with Python interface.
We implement Full GP, Mapped GP, RBCM, Squared Exponential kernel and 2+3-body descriptors in Python.
Please do NOT mix them.
Documentation of the code can be accessed here: https://mir-group.github.io/flare
Applications using FLARE and gallery
FLARE (ACE descriptors + sparse GP). The tutorial shows how to run flare with ACE and SGP on energy and force data, demoing "offline" training on the MD17 dataset and "online" on-the-fly training of a simple aluminum force field. All the trainings use yaml files for configuration.
FLARE (ACE descriptors + sparse GP) with LAMMPS. The tutorial shows how to compile LAMMPS with FLARE pair style and uncertainty compute code, and use LAMMPS for Bayesian active learning and uncertainty-aware molecular dynamics.
FLARE (ACE descriptors + sparse GP) Python API. The tutorial shows how to do the offline and online trainings with python scripts. A video walkthrough of the tutorial, including detailed discussion of expected outputs, is available here.
FLARE (2+3-body + GP). The tutorial shows how to use flare 2+3 body descriptors and squared exponential kernel to train a Gaussian Process force field on-the-fly.
Compute thermal conductivity from FLARE and Boltzmann transport equations. The tutorial shows how to use FLARE (LAMMPS) potential to compute lattice thermal conductivity from Boltzmann transport equation method, with Phono3py for force constants calculations and Phoebe for thermal conductivities.
Using your own customized descriptors with FLARE. The tutorial shows how to attach your own descriptors with FLARE sparse GP model and do training and testing.
All the tutorials take a few minutes to run on a normal desktop computer or laptop (excluding installation time).
Please check the installation guide here. This will take a few minutes on a normal desktop computer or laptop.
For developers, please check the installation guide.
See documentation on compiling LAMMPS with FLARE
If you have problem compiling and installing the code, please check the FAQs to see if your problem is covered. Otherwise, please open an issue or contact us.
- GCC 9
- Python 3
- pip>=20
MKL is recommended but not required. All other software dependencies are taken care of by pip.
The code is built and tested with Github Actions using the GCC 9 compiler. (You can find a summary of recent builds here.) Other C++ compilers may work, but we can't guarantee this.
flare++ is tested on a Linux operating system (Ubuntu 20.04.3), but should also be compatible with Mac and Windows operating systems. If you run into issues running the code on Mac or Windows, please post to the issue board.
There are no non-standard hardware requirements to download the software and train simple models—the introductory tutorial can be run on a single cpu. To train large models (10k+ sparse environments), we recommend using a compute node with at least 100GB of RAM.
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.
Instructions (either DFT package will suffice):
pip install pytest
cd tests
pytest
-
If you use FLARE++ including B2 descriptors, NormalizedDotProduct kernel and Sparse GP, please cite the following paper:
[1] Vandermause, J., Xie, Y., Lim, J.S., Owen, C.J. and Kozinsky, B., 2021. Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics. arXiv preprint arXiv:2106.01949.
-
If you use FLARE active learning workflow, full Gaussian process or 2-body/3-body kernel in your research, please cite the following paper:
[2] 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). https://doi.org/10.1038/s41524-020-0283-z
-
If you use FLARE LAMMPS pair style or MGP (mapped Gaussian process), please cite the following paper:
[3] 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). https://doi.org/10.1038/s41524-021-00510-y