Deep learning model for finding new superconductors
Deep learning model for finding new superconductors
复制标题
DOI：
10.1103/physrevb.103.014509
复制
发表时间：
2021-01-12
影响因子：
3.7
通讯作者：
Maeda, Atsutaka
中科院分区：
文献类型：
--
作者：
Konno, Tomohiko;Kurokawa, Hodaka;Maeda, Atsutaka
对新超导体的探索仍然依赖于专家的经验和直觉，在很大程度上是一个实验试错的过程。在一项研究中，只有3%的候选材料显示出超导性[Hosono等人，sci.技术高级材料16，（2015）]。在这里，我们报告了一个用于寻找新超导体的深度学习模型。我们介绍了一种名为"阅读周期表"的方法，它以一种允许深度学习学习读取周期表和学习元素定律的方式来表示周期表，以发现训练数据之外的新型超导体。人们认识到，深度学习很难预测训练数据之外的东西。虽然我们只使用材料的化学成分作为信息，但我们在超导体数据库中预测材料的Tc时获得了0.92的R-2值。我们还介绍了名为“垃圾”的方法来创建不存在的非超导体的合成数据。非超导体没有报道，但深度学习必须需要这些数据来区分超导体和非超导体。我们取得了三个显著成果。深度学习可以以62%的精度预测材料的超导性，这表明该模型的有用性;它发现了最近发现的超导体CaBi 2和另一种Hf0.5Nb 0.2V2Zr 0.3，这两种超导体都不在超导体数据库中;它从2008年之前的训练数据中发现了铁基高温超导体（2008年发现）。这些结果为发现新的高温超导体家族开辟了道路。候选材料清单、数据和方法可在互联网上公开获得。
Exploration of new superconductors still relies on the experience and intuition of experts, and is largely a process of experimental trial and error. In one study, only 3% of the candidate materials showed superconductivity [Hosono et al., Sci. Technol. Adv. Mater. 16, (2015)]. Here, we report a deep learning model for finding new superconductors. We introduced the method named "reading periodic table" that represented the periodic table in a way that allows deep learning to learn to read the periodic table and to learn the law of elements for the purpose of discovering novel superconductors which are outside the training data. It is recognized that it is difficult for deep learning to predict something outside the training data. Although we used only the chemical composition of materials as information, we obtained an R-2 value of 0.92 for predicting T-c for materials in a database of superconductors. We also introduced the method named "garbage-in" to create synthetic data of nonsuperconductors that do not exist. Nonsuperconductors are not reported, but the data must be required for deep learning to distinguish between superconductors and nonsuperconductors. We obtained three remarkable results. The deep learning can predict superconductivity for a material with a precision of 62%, which shows the usefulness of the model; it found the recently discovered superconductor CaBi2 and another one Hf0.5Nb0.2V2Zr0.3, neither of which is in the superconductor database; and it found Fe-based high-temperature superconductors (discovered in 2008) from the training data before 2008. These results open the way for the discovery of new high-temperature superconductor families. The candidate materials list, data, and method are openly available on the Internet.