Song Yuqi, Siriwardane Edirisuriya M Dilanga, Zhao Yong, Hu Jianjun
Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States.
ACS Appl Mater Interfaces. 2021 Nov 17;13(45):53303-53313. doi: 10.1021/acsami.1c01044. Epub 2021 May 13.
Two-dimensional (2D) materials have emerged as promising functional materials with many applications such as semiconductors and photovoltaics because of their unique optoelectronic properties. Although several thousand 2D materials have been screened in existing materials databases, discovering new 2D materials remains challenging. Herein, we propose a deep learning generative model for composition generation combined with a random forest-based 2D materials classifier to discover new hypothetical 2D materials. Furthermore, a template-based element substitution structure prediction approach is developed to predict the crystal structures of a subset of the newly predicted hypothetical formulas, which allows us to confirm their structure stability using DFT calculations. So far, we have discovered 267 489 new potential 2D materials compositions, where 1485 probability scores are more then 0.95. Among them, we have predicted 101 crystal structures and confirmed 92 2D/layered materials by DFT formation energy calculation. Our results show that generative machine learning models provide an effective way to explore the vast chemical design space for new 2D materials discovery.
二维（2D）材料因其独特的光电特性，已成为具有诸多应用（如半导体和光伏领域）的有前景的功能材料。尽管在现有材料数据库中已筛选出数千种二维材料，但发现新型二维材料仍然具有挑战性。在此，我们提出一种用于成分生成的深度学习生成模型，并结合基于随机森林的二维材料分类器，以发现新的假设二维材料。此外，还开发了一种基于模板的元素替代结构预测方法，用于预测新预测的假设化学式子集的晶体结构，这使我们能够通过密度泛函理论（DFT）计算来确认其结构稳定性。到目前为止，我们已经发现了267489种新的潜在二维材料成分，其中1485个概率分数大于0.95。在这些成分中，我们预测了101种晶体结构，并通过DFT形成能计算确认了92种二维/层状材料。我们的结果表明，生成式机器学习模型为探索用于发现新型二维材料的广阔化学设计空间提供了一种有效方法。
