Synergy of semiempirical models and machine learning in computational chemistry
Nikita Fedik, Benjamin Nebgen, Nicholas Lubbers, Kipton Barros, Maksim Kulichenko, Ying Wai Li, Roman Zubatyuk, Richard Messerly, Olexandr Isayev, Sergei Tretiak
Highlight
Catalyzed by enormous success in the industrial sector, many research programs have been exploring data-driven, machine learning approaches.
Abstract
Catalyzed by enormous success in the industrial sector, many research programs have been exploring data-driven, machine learning approaches. Performance can be poor when the model is extrapolated to new regions of chemical space, e.g., new bonding types, new many-body interactions. Another important limitation is the spatial locality assumption in model architecture, and this limitation cannot be overcome with larger or more diverse datasets. The outlined challenges are primarily associated with the lack of electronic structure information in surrogate models such as interatomic potentials. Given the fast development of machine learning and computational chemistry methods, we expect some limitations of surrogate models to be addressed in the near future; nevertheless spatial locality assumption will likely remain a limiting factor for their transferability. Here, we suggest focusing on an equally important effort—design of physics-informed models that leverage the domain knowledge and employ machine learning only as a corrective tool. In the context of material science, we will focus on semi-empirical quantum mechanics, using machine learning to predict corrections to the reduced-order Hamiltonian model parameters. The resulting models are broadly applicable, retain the speed of semiempirical chemistry, and frequently achieve accuracy on par with much more expensive ab initio calculations. These early results indicate that future work, in which machine learning and quantum chemistry methods are developed jointly, may provide the best of all worlds for chemistry applications that demand both high accuracy and high numerical efficiency.
Keywords
Cite This Paper
@article{Fedik2023synergy,
author = {Fedik, Nikita and Nebgen, Benjamin and Lubbers, Nicholas and Barros, Kipton and Kulichenko, Maksim and Li, Ying Wai and Zubatyuk, Roman and Messerly, Richard and Isayev, Olexandr and Tretiak, Sergei},
title = {Synergy of semiempirical models and machine learning in computational chemistry},
year = {2023},
journal = {J. Chem. Phys.},
volume = {159},
number = {11},
pages = {110901},
doi = {10.1063/5.0151833},
keywords = {semiempirical methods, machine learning},
researchAreas = {quantum-chemistry, ml-potentials},
highlight = {Catalyzed by enormous success in the industrial sector, many research programs have been exploring data-driven, machine learning approaches.}
} Copied to clipboard!
Related Research Areas
Related Publications
Teaching a neural network to attach and detach electrons from molecules
Nature Communications, 12 (2021)
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.
The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules
Scientific Data, 7 (2020)
Abstract Maximum diversification of data is a central theme in building generalized and accurate machine learning (ML) models.
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning
Nature Communications, 10 (2019)
Abstract Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist’s toolset.
ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules
Scientific Data, 4 (2017)
AbstractOne of the grand challenges in modern theoretical chemistry is designing and implementing approximations that expedite ab initio methods without loss of accuracy.
Learning molecular potentials with neural networks
WIREs Comput. Mol. Sci., 12, e1564 (2022)
AbstractThe potential energy of molecular species and their conformers can be computed with a wide range of computational chemistry methods, from molecular mechanics to ab initio quantum chemistry.