# FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials

arXiv: https://arxiv.org/abs/2405.01491 · HTML: https://mlsanity.com/paper/2405.01491/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 94 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 14 of 14)

- [E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials](https://mlsanity.com/paper/2101.03164/) (2021)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects](https://mlsanity.com/paper/2105.00304/) (2021)
- [SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials](https://mlsanity.com/paper/2209.10702/) (2022)
- [Hierarchical modeling of molecular energies using a deep neural network](https://mlsanity.com/paper/1710.00017/) (2017)
- [Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry](https://mlsanity.com/paper/2105.14655/) (2021)
- [SchNetPack 2.0: A neural network toolbox for atomistic machine learning](https://mlsanity.com/paper/2212.05517/) (2022)
- [TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations](https://mlsanity.com/paper/1912.01398/) (2019)
- [Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials](https://mlsanity.com/paper/2109.07421/) (2021)
- [MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows](https://mlsanity.com/paper/2310.20155/) (2023)
- [NNP/MM: Accelerating molecular dynamics simulations with machine learning potentials and molecular mechanic](https://mlsanity.com/paper/2201.08110/) (2022)
- [Multi-scale approach for the prediction of atomic scale properties](https://mlsanity.com/paper/2008.12122/) (2020)
- [End-to-End Differentiable Molecular Mechanics Force Field Construction](https://mlsanity.com/paper/2010.01196/) (2020)
- [Lifelong Machine Learning Potentials](https://mlsanity.com/paper/2303.05911/) (2023)

## Built on by (most cited first, 6 of 6)

- [chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics](https://mlsanity.com/paper/2408.15852/) (2024)
- [Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials](https://mlsanity.com/paper/2509.21647/) (2025)
- [Fast, Modular, and Differentiable Framework for Machine Learning-Enhanced Molecular Simulations](https://mlsanity.com/paper/2503.20541/) (2025)
- [Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces](https://mlsanity.com/paper/2602.14975/) (2026)
- [it Asparagus: A Toolkit for Autonomous, User-Guided Construction of Machine-Learned Potential Energy Surfaces](https://mlsanity.com/paper/2407.15175/) (2024)
- [Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators](https://mlsanity.com/paper/2605.09495/) (2026)

## Abstract (arXiv)

Neural network interatomic potentials (NNPs) have recently proven to be powerful tools to accurately model complex molecular systems while bypassing the high numerical cost of ab-initio molecular dynamics simulations. In recent years, numerous advances in model architectures as well as the development of hybrid models combining machine-learning (ML) with more traditional, physically-motivated, force-field interactions have considerably increased the design space of ML potentials. In this paper, we present FeNNol, a new library for building, training and running force-field-enhanced neural network potentials. It provides a flexible and modular system for building hybrid models, allowing to easily combine state-of-the-art embeddings with ML-parameterized physical interaction terms without the need for explicit programming. Furthermore, FeNNol leverages the automatic differentiation and just-in-time compilation features of the Jax Python library to enable fast evaluation of NNPs, shrinking the performance gap between ML potentials and standard force-fields. This is demonstrated with the popular ANI-2x model reaching simulation speeds nearly on par with the AMOEBA polarizable force-field on commodity GPUs (GPU=Graphics processing unit). We hope that FeNNol will facilitate the development and application of new hybrid NNP architectures for a wide range of molecular simulation problems.