Direct feature extraction from two-dimensional X-ray diffraction images of semiconductor thin films for fabrication analysis

We built a workflow for the fabrication analysis of thin films by applying machine-learning (ML) techniques directly to the measurement data. This will lower the problem in cost of synthesizing and analyzing samples to improve the fabrication conditions. The workflow combines two ML techniques: non-negative matrix factorization (NMF) and variational autoencoder (VAE). The measurement data were two-dimensional X-ray diffraction of indium-gallium oxide system thin films. The thin films were fabricated by physical vapor techniques under multiple conditions. First, the workflow was applied to the data of the thin films fabricated through pulsed laser deposition as a proof of concept. We found that our workflow extracted features that represented crystallinity differences in addition to substrate differences. Second, VAE was analyzed to determine whether it could generate new data from its latent space. The latent space of the VAE, which learned the extracted features, represented the relationship between the fabrication conditions such as laser intensities and crystallinity. Third, the inference ability of the new data fabricated through sputtering was evaluated. The capability of the workflow we confirmed will support researchers in improving fabrication conditions by visually comparing various fabricated samples.本研究将机器学习（Machine Learning，ML）技术直接应用于测量数据，构建了一套用于薄膜制备分析的工作流。该工作流可降低样品合成与分析的成本，助力优化薄膜制备工艺条件。该工作流融合了两类机器学习技术：非负矩阵分解（Non-negative Matrix Factorization，NMF）与变分自编码器（Variational Autoencoder，VAE）。本次研究的测量数据为铟镓氧化物体系薄膜的二维X射线衍射数据，上述薄膜通过物理气相沉积技术在多种工艺条件下制备得到。首先，本研究以脉冲激光沉积法制备的薄膜数据为对象开展验证，以证明该工作流的可行性。结果表明，本工作流不仅可提取出与衬底差异相关的特征，还能提取表征薄膜结晶度差异的特征。其次，本研究对变分自编码器进行分析，以验证其能否从隐空间生成全新的数据集。在学习提取得到的特征后，变分自编码器的隐空间可表征诸如激光强度与结晶度等制备工艺参数之间的关联关系。最后，本研究评估了该工作流对溅射法制备的新型样品数据的推断能力。本研究验证的该工作流性能，可支持研究人员通过可视化对比不同制备条件下的样品数据，从而优化薄膜制备工艺条件。