Data-driven Design of High Pressure Hydride Superconductors using DFT and Deep Learning.

Materials futures Pub Date : 2024-01-01 DOI:10.1088/2752-5724/ad4a94

Daniel Wines, Kamal Choudhary

引用次数: 0

Abstract

The observation of superconductivity in hydride-based materials under ultrahigh pressures (for example, H₃S and LaH₁₀) 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 (T_c) of over 900 hydride materials under a pressure range of (0 to 500) GPa, where we found 122 dynamically stable structures with a T_c above MgB₂ (39 K). To accelerate screening, we trained a graph neural network (GNN) model to predict T_c 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.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用 DFT 和深度学习进行高压氢化物超导体的数据驱动设计。

在超高压下观察到氢化物基材料（例如 H3S 和 LaH10）的超导性，激发了人们对采用数据驱动方法发现新型高压氢化物超导体的兴趣。在这项工作中，我们进行了密度泛函理论（DFT）计算，以预测 900 多种氢化物材料在（0 至 500）GPa 压力范围内的临界温度（Tc），其中我们发现 122 种动态稳定结构的 Tc 高于 MgB2（39 K）。为了加快筛选速度，我们训练了一个图神经网络 (GNN) 模型来预测 Tc，并证明了一个通用的机器学习力场可用于在任意压力下松弛氢化物结构，而且成本大大降低。通过结合 DFT 和 GNN，我们可以建立更完整的压力下氢化物图谱。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Materials futures

自引率

0.00%

发文量

期刊最新文献

Activating Supercooled Electrolytes Microfluidics-derived Microfibers in Flexible Bioelectronics Tailoring esophageal tumor spheroids on a chip with inverse opal scaffolds for drug screening Data-driven Design of High Pressure Hydride Superconductors using DFT and Deep Learning.