High throughput inverse design and Bayesian optimization of functionalities: spin splitting in two-dimensional compounds

The development of spintronic devices demands the existence of materials with some kind of spin splitting (SS). In this work, we have built a database of ab initio calculated SS in 2D materials. More than that, we propose a workflow for materials design integrating an inverse design approach and a Bayesian inference optimization. We use the prediction of SS prototypes for spintronic applications as an illustrative example of the proposed workflow. The prediction process starts with the establishment of the design principles (the physical mechanism behind the target properties), that are used as filters for materials screening, and followed by density functional theory (DFT) calculations. Applying this process to the C2DB database, we identify and classify 315 2D materials according to SS type at the valence and/or conduction bands. The Bayesian optimization captures trends that are used for the rationalized design of 2D materials with the ideal conditions of band gap and SS for potential spintronics applications. This repository then contains the main source of data generated in this work, which encompasses full information regarding the materials structure and band structure calculations results, and a database of all the identified spin splittings for these compounds, available in multiple formats.自旋电子学器件的开发离不开具备某种自旋劈裂(SS)特性的材料。本研究构建了一套基于从头算(ab initio)方法计算得到的二维材料自旋劈裂数据库。不仅如此，本研究还提出了一套融合逆向设计方法与贝叶斯推理优化的材料设计工作流，并以自旋电子学应用所需的自旋劈裂原型预测为例，对所提出的工作流进行了演示。该预测流程首先确立设计原则（即目标物性背后的物理机制），将其作为材料筛选的过滤条件，随后开展密度泛函理论(DFT)计算。将该流程应用于C2DB数据库后，研究团队依据价带和/或导带的自旋劈裂类型，对315种二维材料完成了识别与分类。贝叶斯优化可捕捉相关趋势，用于合理化设计具备理想带隙与自旋劈裂条件的二维材料，以满足潜在自旋电子学应用需求。本数据集仓库包含本研究产生的核心数据，涵盖材料结构、能带结构计算结果的完整信息，以及上述化合物所有已识别自旋劈裂情况的数据库，且支持多种格式获取。