Data-driven design of high pressure hydride superconductors using DFT and deep learning
Daniel Wines, Kamal Choudhary
Abstract
Abstract The observation of superconductivity in hydride-based materials under ultrahigh pressures (for example, H 3 S and LaH 10 ) has fueled the interest in a more data-driven approach to discovering new high-pressure hydride superconductors. In this work, we performed density functional theory (DFT) calculations to predict the critical temperature ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"><mml:mrow><mml:msub><mml:mi>T</mml:mi><mml:mrow><mml:mrow><mml:mi mathvariant="normal">c</mml:mi></mml:mrow></mml:mrow></mml:msub></mml:mrow></mml:math> ) of over 900 hydride materials under a pressure range of (0–500) GPa, where we found 122 dynamically stable structures with a <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"><mml:mrow><mml:msub><mml:mi>T</mml:mi><mml:mrow><mml:mrow><mml:mi mathvariant="normal">c</mml:mi></mml:mrow></mml:mrow></mml:msub></mml:mrow></mml:math> above MgB 2 (39 K). To accelerate screening, we trained a graph neural network (GNN) model to predict <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"><mml:mrow><mml:msub><mml:mi>T</mml:mi><mml:mrow><mml:mrow><mml:mi mathvariant="normal">c</mml:mi></mml:mrow></mml:mrow></mml:msub></mml:mrow></mml:math> and demonstrated that a universal machine learned force-field can be used to relax hydride structures under arbitrary pressures, with significantly reduced cost. By combining DFT and GNNs, we can establish a more complete map of hydrides under pressure.