HOME > aenet

aenet

ænet (The Atomic Energy Network) is a software package for the calculation of atomic interaction potentials. Neural network potentials can be generated from energy and material structure data. ænet also provides C and Fortran libraries that allow integration of the generated potentials into molecular dynamics simulation software such as Atomic Simulation Environment (ASE).

Information

Official site	http://ann.atomistic.net/
Openness	★★★
Manual	http://ann.atomistic.net/documentation/
Download	http://ann.atomistic.net/download/
License	Mozilla Public License
Core Developers	Main developers – Dr. Nongnuch Artrith (Columbia University and Brookhaven National Laboratory, USA) – Dr. Alexander Urban (Columbia University, USA) Other contributors http://ann.atomistic.net/contributors/](http://ann.atomistic.net/contributors/
Availability	Following libraries are necessary. – BLAS (Basic Linear Algebra Subprograms), – LAPACK (Linear Algebra PACKage), – L-BFGS-B optimization routines by Nocedal et al.
Related Papers	– N. Artrith and A. Urban, “An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2” [Comput. Mater. Sci. 114 (2016) 135-150.](https://doi.org/10.1016/j.commatsci.2015.11.047) – N. Artrith and A. Urban, C. Gerbrand “Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species” [Phys. Rev. B 96(2017) 014112](https://doi.org/10.1103/PhysRevB.96.014112) – A. Cooper, J. Kästner, A. Urban, N. Artrith, [npj Comput. Mater. 6 (2020) 54.](https://doi.org/10.1038/s41524-020-0323-8)
Related Sites	MateriApps: https://ma.issp.u-tokyo.ac.jp/en/app/4952