Deep neural network for the dielectric response of insulators

Fully anharmonic calculations of the dielectric response of insulators require costly $a\phantom{\rule{0}{0ex}}b$ $i\phantom{\rule{0}{0ex}}n\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}t\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}o$ molecular dynamics simulations. Here, the authors show that this electronic response property can be described efficiently by a deep neural network that retains the accuracy of $a\phantom{\rule{0}{0ex}}b$ $i\phantom{\rule{0}{0ex}}n\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}t\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}o$ molecular dynamics. The scheme is demonstrated with calculations of the infrared absorption spectrum of liquid water at standard conditions, and of the evolution of the spectrum of crystalline ice undergoing a pressure-induced structural transformation from molecular ice VII to ionic ice X.