RuNNer 2.0: A software suite for high-dimensional neural network potentials
Authors:
- Alexander L. M. KnollAKAlexander L. M. Knoll
- Moritz R. SchäferMSMoritz R. Schäfer
- K. Nikolas LauschKLK. Nikolas Lausch
- Moritz GublerMGMoritz Gubler
- Henry WangHWHenry Wang
- Richard SpringbornRSRichard Springborn
- Redouan El HaouariRHRedouan El Haouari
- Alea Miako LiebetrauALAlea Miako Liebetrau
- Jonas A. FinklerJFJonas A. Finkler
- Emir KocerEKEmir Kocer
- Marco EckhoffMEMarco Eckhoff
- Stefan GoedeckerSGStefan Goedecker
- 20 October 2026
- journal article
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 165 (15)
Abstract
We present RuNNer 2.0, the “Ruhr University Neural Network energy representation,” a highly optimized software suite for training and evaluating high-dimensional neural network potentials (HDNNPs) of the second, third, and fourth generations. Long-range electrostatics and charge equilibration (QEq) for the description of non-local charge transfer in fourth-generation (4G) HDNNPs are accelerated by quasi-linear-scaling plane wave methods, reducing QEq computational complexity from O(N3) to O(Nlog2N) such that linear or quasi-linear scaling is achieved across all HDNNP generations. An optimized memory management strategy eliminates the training overhead traditionally associated with long-range interactions, allowing 4G-HDNNPs to be trained with the same efficiency as their local counterparts. Developed in modern Fortran (2003/2008 standards), combined with a hybrid Message Passing Interface (MPI)/Open Multi-Processing (OpenMP) parallelization scheme, RuNNer 2.0 has been designed to run efficiently in any central processing unit (CPU) environment, from cost-effective local workstations to massive high-performance computing (HPC) clusters. Its modular library architecture facilitates straightforward binding to external simulation software; native interfaces to the Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) and the atomic simulation environment (ASE) provide full access to all its features, including built-in committee-based uncertainty quantification. The high efficiency and scalability of the RuNNer 2.0 ecosystem are demonstrated through detailed benchmarks.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (390677874)
- Deutsche Forschungsgemeinschaft (495842446)
- Studienstiftung des Deutschen Volkes
This publication has 63 references indexed in Scilit:
- Molecular Dynamics Simulations of γ‐Belite(010)–Water Interfaces With High‐Dimensional Neural Network PotentialsChemistry – A European Journal, 2026
- Machine Learning Interatomic Potentials as Emerging Tools for Materials ScienceAdvanced Materials, 2019
- First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed SystemsAngewandte Chemie International Edition, 2017
- Amp: A modular approach to machine learning in atomistic simulationsComputer Physics Communications, 2016
- An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2Computational Materials Science, 2016
- Constructing high‐dimensional neural network potentials: A tutorial reviewInternational Journal of Quantum Chemistry, 2015
- PLUMED: A portable plugin for free-energy calculations with molecular dynamicsComputer Physics Communications, 2009
- Fast Parallel Algorithms for Short-Range Molecular DynamicsJournal of Computational Physics, 1995
- Adaptive, global, extended Kalman filters for training feedforward neural networksJournal of Chemometrics, 1994
- Die Berechnung optischer und elektrostatischer GitterpotentialeAnnalen der Physik, 1921