Monomeric machine learning potential for general covalent molecules: linear alkanes as an example

TL;DR

This paper introduces MB-PIPNet, a monomer-based machine learning potential framework that efficiently models covalent molecules, demonstrated on linear alkanes, achieving high accuracy and computational efficiency.

Contribution

The work extends the MB-PIPNet framework to general covalent molecules using a monomer decomposition approach with PIP descriptors and neural networks, improving efficiency and scalability.

Findings

Accurately reproduces ab initio energies for linear alkanes.

Captures torsional, vibrational, and spectral properties reliably.

Outperforms existing models in computational efficiency.

Abstract

Machine-learning potentials (MLPs) have become important tools for modern molecular simulations. However, developing models that simultaneously achieve high accuracy and high computational efficiency remains a significant challenge. In this work, we extend the recently proposed MB-PIPNet framework to general covalently bonded molecular systems by combining monomer-based energy decomposition, permutationally invariant polynomial (PIP) descriptors, and neural networks within a fragmentation-based strategy. Within this framework, the total potential energy is represented as a sum of effective monomeric contributions, where PIPs provide compact and chemically motivated descriptions of both monomer internal structures and their local chemical environments. As a proof-of-concept application, we apply the MB-PIPNet framework to linear alkanes, using n-Tetradecane as a representative system, and benchmark its performance against established atomistic machine-learning models. The resulting MB-PIPNet potential accurately reproduces reference ab initio electronic energies and reliably captures key molecular properties, including torsional potential energy profiles, harmonic vibrational frequencies, and vibrational power spectra obtained from molecular dynamics simulations. Importantly, MB-PIPNet demonstrates a substantial advantage in computational efficiency over other MLP models for combined energy and force evaluations. These results establish MB-PIPNet as a scalable and efficient framework for constructing MLPs, providing an additional route for large-scale quantum and classical simulations of complex molecular systems.