Derivative learning of tensorial quantities -- Predicting finite temperature infrared spectra from first principles

TL;DR

This paper introduces a machine learning approach combined with first-principles calculations to accurately predict finite-temperature infrared spectra of complex materials, including water and perovskites, by leveraging derivative learning for polarization data.

Contribution

The novel methodology integrates derivative learning with first-principles calculations to predict infrared spectra at finite temperatures, improving accuracy for complex systems.

Findings

Achieved about 1% polarization prediction accuracy.

Successfully applied to water and MAPbI3 perovskite.

Predicted spectra align well with experimental data.

Abstract

We develop a strategy that integrates machine learning and first-principles calculations to achieve technical accurate predictions of infrared spectra. Specifically, the methodology allows to predict infrared spectra for complex systems at finite temperatures. The method's effectiveness is demonstrated in challenging scenarios, such as the analysis of water and the organic-inorganic halide perovskite MAPbI$_{3}$, where our results consistently align with experimental data. A distinctive feature of the methodology is the incorporation of derivative learning, which proves indispensable for obtaining accurate polarization data in bulk materials and facilitates the training of a machine learning surrogate model of the polarization adapted to rotational and translational symmetries. We achieve polarisation prediction accuracies of about 1 % by training only on the predicted Born effective charges.