Department of Mechanical and Industrial Engineering, The University of Illinois at Chicago, 842 W. Taylor Street, Chicago, Illinois 60607, United States.
Center for Nanoscale Materials, Argonne National Lab, Argonne, Illinois 60439, United States.
ACS Appl Mater Interfaces. 2023 Apr 26;15(16):20520-20530. doi: 10.1021/acsami.3c01161. Epub 2023 Apr 11.
Grain boundaries (GBs) in two-dimensional (2D) materials are known to dramatically impact material properties ranging from the physical, chemical, mechanical, electronic, and optical, to name a few. Predicting a range of physically realistic GB structures for 2D materials is critical to exercising control over their properties. This, however, is nontrivial given the vast structural and configurational (defect) search space between lateral 2D sheets with varying misfits. Here, in a departure from traditional evolutionary search methods, we introduce a workflow that combines the Graph Neural Network (GNN) and an evolutionary algorithm for the discovery and design of novel 2D lateral interfaces. We use a representative 2D material, blue phosphorene (BP), and identify 2D GB structures to test the efficacy of our GNN model. The GNN was trained with a computationally inexpensive machine learning bond order potential (Tersoff formalism) and density functional theory (DFT). Systematic downsampling of the training data sets indicates that our model can predict structural energy under 0.5% mean absolute error with sparse (<2000) DFT generated energy labels for training. We further couple the GNN model with a multiobjective genetic algorithm (MOGA) and demonstrate strong accuracy in the ability of the GNN to predict GBs. Our method is generalizable, is material agnostic, and is anticipated to accelerate the discovery of 2D GB structures.
晶界（GBs）在二维（2D）材料中被广泛认为会对材料性能产生显著影响，包括物理、化学、机械、电子和光学等方面。预测一系列物理上可行的 2D 材料晶界结构对于控制其性能至关重要。然而，由于具有不同失配的横向 2D 片之间存在巨大的结构和构型（缺陷）搜索空间，这并非易事。在这里，我们摒弃了传统的进化搜索方法，引入了一种将图神经网络（GNN）和进化算法相结合的工作流程，用于发现和设计新型 2D 横向界面。我们使用代表性的 2D 材料蓝色磷烯（BP）来识别 2D 晶界结构，以测试我们的 GNN 模型的效果。GNN 是使用计算成本较低的机器学习键序势（Tersoff 形式）和密度泛函理论（DFT）进行训练的。对训练数据集的系统降采样表明，我们的模型可以在 0.5%的平均绝对误差下预测结构能量，并且对于稀疏（<2000）的 DFT 生成的能量标签进行训练。我们进一步将 GNN 模型与多目标遗传算法（MOGA）相结合，并展示了 GNN 预测晶界的强大准确性。我们的方法具有通用性，对材料没有偏见，预计将加速 2D 晶界结构的发现。
