论文标题
查看Moiré：适用于Twistronics的卷积网络学习
Seeing moiré: convolutional network learning applied to twistronics
论文作者
论文摘要
由二维（2D）材料制成的Moiré图案代表高度可调的电子哈密顿量，使各种量子相可以在单个材料中出现。 Moiré电子的当前建模技术需要针对每种材料的大量技术工作，并阻碍大规模搜索有用的Moiré材料。为了解决这一难度，我们开发了一种材料不足的机器学习方法，并在此处对其进行测试，以典型的一维（1D）Moiré紧密结合模型进行测试。我们利用状态的局部密度（SD-LDOS）的堆叠依赖性将有关电子带结构的信息转换为与物理相关的图像。然后，我们训练一个神经网络，该神经网络从易于计算的对齐双层的SD-LDOS中成功预测了Moiré电子结构。该网络可以令人满意地预测Moiré电子结构，即使对于未包含在培训数据中的材料也是如此。
Moiré patterns made of two-dimensional (2D) materials represent highly tunable electronic Hamiltonians, allowing a wide range of quantum phases to emerge in a single material. Current modeling techniques for moiré electrons requires significant technical work specific to each material, impeding large-scale searches for useful moiré materials. In order to address this difficulty, we have developed a material-agnostic machine learning approach and test it here on prototypical one-dimensional (1D) moiré tight-binding models. We utilize the stacking dependence of the local density of states (SD-LDOS) to convert information about electronic bandstructure into physically relevant images. We then train a neural network that successfully predicts moiré electronic structure from the easily computed SD-LDOS of aligned bilayers. This network can satisfactorily predict moiré electronic structures, even for materials that are not included in its training data.
