Deep learning Hamiltonians from disordered image data in quantum materials
Deep learning Hamiltonians from disordered image data in quantum materials
复制标题
DOI：
10.1103/physrevb.107.205121
复制
发表时间：
2023-05-10
影响因子：
3.7
通讯作者：
Carlson, E. W.
中科院分区：
文献类型：
--
作者：
Basak, S.;Banguero, M. Alzate;Carlson, E. W.
图像探测实验的能力正在迅速扩大，提供了前所未有的长度和时间尺度上的量子材料的新信息。许多这样的材料具有不均匀的电子特性，在可观察的表面上形成复杂的图案。这种丰富的空间结构包含了关于相互作用、维度、无序的信息--驱动模式形成的哈密顿量的空间编码。来自机器学习的图像识别技术是解释此类图像中空间关系中编码的信息的绝佳工具。在这里，我们开发了一个深度学习框架，用于使用这些空间相关性中可用的丰富信息，以发现驱动模式的底层Hamilton。我们首先在一个已知的案例上验证了该方法，即在VO 2薄膜上扫描近场光学显微镜。然后，我们将我们训练的卷积神经网络架构应用于不同VO 2薄膜的新光学显微镜图像，因为它经历了金属-绝缘体转变。我们发现，一个二维的相互作用，随机场无序的哈密顿量需要解释复杂的，分形的金属和绝缘体域在过渡期间的交织。这种关于底层哈密顿量的详细知识为使用模型来控制图案形成铺平了道路，例如，定制的滞后协议。我们还引入了一个基于分布的置信度的多标签分类器，它不依赖于对抗训练的结果。此外，我们提出了一个基于机器学习的标准，用于诊断物理系统的接近临界。
The capabilities of image probe experiments are rapidly expanding, providing new information about quantum materials on unprecedented length-and timescales. Many such materials feature inhomogeneous electronic properties with intricate pattern formation on the observable surface. This rich spatial structure contains informa-tion about interactions, dimensionality , disorder-a spatial encoding of the Hamiltonian driving the pattern formation. Image recognition techniques from machine learning are an excellent tool for interpreting information encoded in the spatial relationships in such images. Here, we develop a deep learning framework for using the rich information available in these spatial correlations in order to discover the underlying Hamiltonian driving the patterns. We first vet the method on a known case, scanning near-field optical microscopy on a thin film of VO2. We then apply our trained convolutional neural network architecture to new optical microscope images of a different VO2 film as it goes through the metal-insulator transition. We find that a two-dimensional Hamiltonian with both interactions , random field disorder is required to explain the intricate, fractal intertwining of metal and insulator domains during the transition. This detailed knowledge about the underlying Hamiltonian paves the way for using the model to control the pattern formation via, e.g., tailored hysteresis protocols. We also introduce a distribution-based confidence measure on the results of a multilabel classifier, which does not rely on adversarial training. In addition, we propose a machine-learning-based criterion for diagnosing a physical system's proximity to criticality.