Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning

Abstract

The Interest in polycyclic aromatic hydrocarbons (PAHs) spans numerous fields and infrared spectroscopy is usually the method of choice to disentangle their molecular structure. In order to compute vibrational frequencies, numerous theoretical studies employ either quantum calculation methods, or empirical potentials, but it remains difficult to combine the accuracy of the first approach with the computational cost of the second. In this work, we employed Machine Learning techniques to develop a potential energy surface and a dipole mapping based on an artificial neural network (ANN) architecture. Altogether, while trained on only 11 small PAH molecules, the obtained ANNs are able to retrieve the infrared spectra of those small molecules, but more importantly of 8 large PAHs different from the training set, thus demonstrating the transferability of our approach.

13 pages, 6 figures

References in corpus (7)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Machine-learning prediction of infrared spectra of interstellar polycyclic aromatic hydrocarbons
• Machine learning potentials for multicomponent systems: The Ti-Al binary system

Cited by in corpus (4)

• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Exploring the formation of gold/silver nanoalloys with gas-phase synthesis and machine-learning assisted simulations
• PDRs4All VI: Probing the Photochemical Evolution of PAHs in the Orion Bar Using Machine Learning Techniques
• Neural Network Approach for Predicting Infrared Spectra from 3D Molecular Structure