Accurate and Affordable Simulation of Molecular Infrared Spectra with AIQM Models

Infrared (IR) spectroscopy is a potent tool for identifying molecular structures and studying the chemical properties of compounds, and hence, various theoretical approaches have been developed to simulate and predict the IR spectra. However, the theoretical approaches based on quantum chemical calculations suffer from high computational cost (e.g., density functional theory, DFT) or insufficient accuracy (e.g., semi-empirical methods orders of magnitude faster than DFT). Here, we introduce a new approach, based on the universal machine learning (ML) models of the AIQM series targeting CCSD(T)/CBS level, that can deliver molecular IR spectra with accuracy close to DFT (compared to the experiment) and the speed close to a semi-empirical GFN2-xTB method. This approach enables efficient interpretation of the IR bands by clearly assigning them to the vibrational normal modes in contrast to alternative ML models, which can only predict the spectra. Our implementations for calculating IR spectra with ML and quantum mechanical (DFT, semi-empirical, ab initio wavefunction) approaches are available in MLatom as described in https://github.com/dralgroup/mlatom.