Self-assembled InAs/GaAs quantum dots (QDs) have properties highly valuable for developing various optoelectronic devices such as QD lasers and single photon sources. The applications strongly rely on the density and quality of these dots, which has motivated studies of the growth process control to realize high-quality epi-wafers and devices. Establishing the process parameters in molecular beam epitaxy (MBE) for a specific density of QDs is a multidimensional optimization challenge, usually addressed through time-consuming and iterative trial-and-error. Meanwhile, reflective high-energy electron diffraction (RHEED) has been widely used to capture a wealth of growth information in situ. However, it still faces the challenges of extracting information from noisy and overlapping images. Here, based on 3D ResNet, we developed a machine learning (ML) model specially designed for training RHEED videos instead of static images and providing real-time feedback on surface morphologies for process control. We demonstrated that ML from previous growth could predict the post-growth density of QDs, by successfully tuning the QD densities in near-real time from 1.5E10 cm-2 down to 3.8E8 cm-2 or up to 1.4 E11 cm-2. Compared to traditional methods, our approach, with in-situ tuning capabilities and excellent reliability, can dramatically expedite the material optimization process and improve the reproducibility of MBE growth, constituting significant progress for thin film growth techniques. The concepts and methodologies proved feasible in this work are promising to be applied to a variety of material growth processes, which will revolutionize semiconductor manufacturing for microelectronic and optoelectronic industries.

翻译：自组装InAs/GaAs量子点因其在量子点激光器和单光子源等光电器件开发中的重要价值而备受关注。量子点的密度与质量对其应用至关重要，这促使研究者探索生长过程控制方法，以获得高质量外延片与器件。在分子束外延中，针对特定量子点密度确立工艺参数是一个多维优化难题，通常需通过耗时且迭代的试错法解决。与此同时，反射式高能电子衍射已被广泛用于原位捕获丰富的生长信息，但仍面临从含噪和重叠图像中提取信息的挑战。本研究基于3D ResNet开发了一种机器学习模型，该模型专门设计用于处理衍射视频（而非静态图像），并能实时反馈表面形貌以实现过程控制。我们证实，通过利用先前生长的机器学习模型，可在近实时条件下成功调控量子点密度（从1.5E10 cm⁻²降低至3.8E8 cm⁻²或升高至1.4E11 cm⁻²），从而预测生长后量子点密度。与传统方法相比，本方法具备原位调控能力与优异可靠性，可显著加速材料优化进程并提升分子束外延生长的可重复性，标志着薄膜生长技术的重大进展。本工作中验证的概念与方法有望推广至多种材料生长过程，从而革新微电子与光电子产业的半导体制造技术。