article Machine Learning Potentials

AIMNet2: A Neural Network Potential to Meet your Neutral, Charged, Organic, and Elemental-Organic Needs

Dylan Anstine, Roman Zubatyuk, Olexandr Isayev

2023 27 citations

Highlight

Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff.

Abstract

Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff. Despite this attraction, the benefits of such efficiency are only impactful when an MLIP uniquely enables insight into a target system or is broadly transferable outside of the training dataset, where models achieving the latter are seldom reported. In this work, we present the 2nd generation of our atoms-in-molecules neural network potential (AIMNet2), which is applicable to species composed of up to 14 chemical elements in both neutral and charged states, making it a valuable model for modeling the majority of non-metallic compounds. Using an exhaustive dataset of 20 million hybrid quantum chemical calculations, AIMNet2 combines ML-parameterized short-range and physics-based long-range terms to attain generalizability that reaches from simple organics to diverse molecules with “exotic” element-organic bonding. We show that AIMNet2 outperforms semi-empirical GFN-xTB and is on par with reference density functional theory for interaction energy contributions, conformer search tasks, torsion rotation profiles, and molecular-to-macromolecular geometry optimization. Overall, the demonstrated chemical coverage and computational efficiency of AIMNet2 is a significant step toward providing access to MLIPs that avoid the crucial limitation of curating additional quantum chemical data and retraining with each new application.

Keywords

neural network density functional

Cite This Paper

@article{Anstine2023,
  author = {Anstine, Dylan and Zubatyuk, Roman and Isayev, Olexandr},
  title = {AIMNet2: A Neural Network Potential to Meet your Neutral, Charged, Organic, and Elemental-Organic Needs},
  year = {2023},
  doi = {10.26434/chemrxiv-2023-296ch},
  url = {http://dx.doi.org/10.26434/chemrxiv-2023-296ch},
  publisher = {American Chemical Society (ACS)},
  keywords = {neural network, density functional},
  researchAreas = {ml-potentials},
  highlight = {Machine learned interatomic potentials (MLIPs) are reshaping computational chemistry practices because of their ability to drastically exceed the accuracy-length/time scale tradeoff.},
  citations = {27}
}

Related Research Areas

Machine Learning Potentials

Related Publications

2021

cited94

Teaching a neural network to attach and detach electrons from molecules

Zubatyuk R., Smith J. S., Nebgen B. T., Tretiak S., Isayev O.

Nature Communications, 12 (2021)

Ml Potentials

Reactions Reactivity

Drug Discovery

Quantum Chemistry

Abstract Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations.

DOI

2024

cited17