Researchers from Tokyo University of Science have identified machine learning approaches that can aid in the automated examination of RHEED (Reflection High-energy Electron Diffraction) data.Â
Since its inception in the mid-twentieth century, the semiconductor industry has grown steadily, paving the way for the rapid digitization of society thanks to the high-speed information and communication technologies it enabled. Modern semiconductor processes have already reached the nanometer scale, and the design of novel high-performance materials now involves the structural analysis of semiconductor nanofilms. Reflection high-energy electron diffraction (RHEED) is a widely used analytical method for this purpose.
Unfortunately, to make sense of the massive amounts of data that RHEED can create in the form of diffraction patterns, a highly trained experimenter is almost always required. But what if we could delegate the majority of the RHEED data processing to machine learning?
Surface superstructures that emerge on the initial atomic layers of pure single-crystal silicon were the focus of the researchers. They are one of the most versatile semiconductor materials. To begin, the researchers used a variety of hierarchical clustering approaches, which try to divide samples into different clusters based on a variety of similarity metrics. This method is used to determine the number of various surface superstructures present. The scientists next set out to find the best conditions for synthesising each of the surface superstructures they had discovered.
Dr. Naoka Nagamura, a visiting associate professor at Tokyo University of Science (TUS) and a senior researcher of National Institute for Materials Science (NIMS), remarks, “Our efforts will help automate the work that typically requires time-consuming manual analysis by specialists. We believe our study has the potential to change the way materials research is done and allow scientists to spend more time on creative pursuits.”
Overall, the findings of this research should lead to new and more successful ways of applying machine learning techniques to materials science, which is a hot topic in the field of materials informatics. As a result, as existing equipment and technology are upgraded with better materials, this will have an impact on our daily life.
“Our approach can be used to analyze the superstructures grown not only on thin-film silicon single-crystal surfaces, but also metal crystal surfaces, sapphire, silicon carbide, gallium nitride, and various other important substrates. Thus, we expect our work to accelerate the research and development of next-generation semiconductors and high-speed communication devices,” concludes Dr. Nagamura.
