Predicting novel superconducting hydrides using machine learning approaches

Searching for superconducting hydrides has so far largely focused on finding materials exhibiting the highest possible critical temperatures ($T_c$). This has led to a bias towards materials stabilised at very high pressures, which introduces a number of technical difficulties in experiment. Here we apply machine learning methods in an effort to identify superconducting hydrides which can operate closer to ambient conditions. The output of these models informs structure searches, from which we identify and screen stable candidates before performing electron-phonon calculations to obtain $T_c$. Hydrides of alkali and alkaline earth metals are identified as particularly promising; a $T_c$ of up to 115 K is calculated for RbH$_{12}$ at 50 GPa and a $T_c$ of up to 90 K is calculated for CsH$_7$ at 100 GPa.