Coupling a Crystal Graph Multilayer Descriptor to Active Learning for Rapid Discovery of 2D Ferromagnetic Semiconductors/Half‐Metals/Metals. Issue 29 (15th June 2020)

• Record Type: Journal Article
• Authors: Lu, Shuaihua; Zhou, Qionghua; Guo, Yilv; Zhang, Yehui; Wu, Yilei; Wang, Jinlan
• Is Part Of: Advanced materials. Volume 32:Issue 29(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-06-15
• Subjects: first‐principle methods -- machine learning -- material descriptors -- 2D ferromagnetic materials; Materials -- Periodicals; Chemical vapor deposition -- Periodicals; 620.11
• DOI: 10.1002/adma.202002658
• Languages: English
• ISSNs: 0935-9648

Abstract

Abstract: 2D ferromagnetic (FM) semiconductors/half‐metals/metals are the key materials toward next‐generation spintronic devices. However, such materials are still rather rare and the material search space is too large to explore exhaustively. Here, an adaptive framework to accelerate the discovery of 2D intrinsic FM materials is developed, by combining advanced machine‐learning (ML) techniques with high‐throughput density functional theory calculations. Successfully, about 90 intrinsic FM materials with desirable bandgap and excellent thermodynamic stability are screened out and a database containing 1459 2D magnetic materials is set up. To improve the performance of ML models on small‐scale datasets like diverse 2D materials, a crystal graph multilayer descriptor using the elemental property is proposed, with which ML models achieve prediction accuracy over 90% on thermodynamic stability, magnetism, and bandgap. This study not only provides dozens of compelling FM candidates for future spintronics, but also paves a feasible route for ML‐based rapid screening of diverse structures and/or complex properties. Abstract : An adaptive framework with the combination of machine‐learning (ML) techniques and high‐throughput density functional theory calculations is designed to discover novel 2D ferromagnetic semiconductors, half‐metals, and metals. Additionally, a new universal material descriptor is proposed for thermal, magnetic, and electronic properties of diverse 2D materials, with which ML models achieve high prediction accuracy over 90%.