Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
This work addresses the difficulty of combining accuracy and computational efficiency in predicting PAH infrared spectra, which is incremental as it applies existing machine learning methods to a specific domain problem.
The authors tackled the challenge of accurately computing infrared spectra for polycyclic aromatic hydrocarbons (PAHs) by developing a machine learning-based potential energy surface and dipole mapping using an artificial neural network, achieving transferability to 8 large PAHs not in the training set.
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.