Researchers have shown that machine learning techniques can automate some of the harder parts of analyzing RHEED data. Image: Naoka Nagamura from National Institute for Materials Science and Tokyo University of Science.The semiconductor industry has been growing steadily ever since its first steps in the mid-20th century, leading to the rapid digitalization of society. Today, in line with a tight global energy demand, there is a growing need for faster, more integrated and more energy-efficient semiconductor devices.
But 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. RHEED can be used to determine the structures that form on the surface of thin films at the atomic level and can even capture structural changes in real time as a thin film is synthesized.
Unfortunately, for all its benefits, RHEED is sometimes hindered by the fact that its output patterns are complex and difficult to interpret. In virtually all cases, a highly skilled experimenter is needed to make sense of the huge amounts of data that RHEED can produce in the form of diffraction patterns. But what if machine learning could do most of the work when processing RHEED data?
A team of researchers led by Naoka Nagamura, a visiting associate professor at Tokyo University of Science (TUS) and a senior researcher at the National Institute for Materials Science (NIMS), both in Japan, has been working on just that. In a paper in Science and Technology of Advanced Materials: Methods, Nagamura and his colleagues explore the possibility of using machine learning to automatically analyze RHEED data.
The researchers focused on the surface superstructures that form when indium is deposited on the atomic layers of clean single-crystal silicon (one of the most versatile semiconductor materials), which depends on the number of indium atoms adsorbed and slight differences in temperature. Surface superstructures are atomic arrangements unique to crystal surfaces, where atoms stabilize in different periodic patterns to those inside the bulk of the crystal, depending on differences in the surrounding environment. Because they often exhibit unique physical properties, surface superstructures are the focus of much interest in materials science.
To analyze the data produced by studying superstructures with RHEED, the team tried out various hierarchical clustering methods, which divide samples into different clusters based on various measures of similarity. This approach serves to detect how many different surface superstructures are present. The researchers found that a technique known as Ward’s method could best track the actual phase transitions in surface superstructures.
They then sought to determine the optimal process conditions for synthesizing each of the identified surface superstructures, focusing on how the indium deposition time influences what superstructures are most extensively formed. While principal component analysis and other typical methods for dimensionality reduction did not perform well, they found that non-negative matrix factorization, a different clustering and dimensionality reduction technique, could accurately and automatically obtain the optimal deposition times for each superstructure.
“Our efforts will help automate the work that typically requires time-consuming manual analysis by specialists,” said Nagamura. “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 reported in this study will hopefully lead to new and effective ways of using machine-learning techniques for materials science – a central topic in the field of materials informatics. In turn, this could have implications in our everyday lives, as existing devices and technologies are upgraded with better materials.
“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 Nagamura.
This story is adapted from material from Tokyo University of Science, with editorial changes made by Materials Today. The views expressed in this article do not necessarily represent those of Elsevier. Link to original source.