In recent years, researchers have been trying to implement machine learning (ML) based approaches in a wide range of scientific fields, and it has attracted considerable attention. ML has demonstrated its capability to implement semantic segmentation, which classifies objects in an image pixel by pixel, and has been applied to practical applications for example, automated driving technology and the medical field.
An emerging application of ML is analytical methods for extracting characteristic information about the structure, composition, and properties of various materials, especially nanoscale materials. Many reported cases of extracting specific features from a dataset by ML have shown that ML can be further advanced toward a major unbiased data-driven analysis method to gain new insights from the extracted features.
In this study, we developed a ML-based framework for quantitative analysis of nanoscale objects’ dynamic behavior based on the information obtained by detecting the objects in a video using machine learning and tracking the detected objects with particle filters. We confirmed that if a video presents a single experiment, the number of data is sufficient for machine learning to detect dislocations in that video. We then applied the developed ML-based framework to a video in which the dislocation gliding under applied external tensile stresses in a metal was observed using TEM. By detecting and tracking dislocations in the TEM video singly and as a whole using the framework, we were able to calculate the time history of dislocation velocity and quantitatively analyzed its behavior. In particular, we employed the particle filter to the quantitative analysis part of the framework. Thanks to the probabilistic prediction of the particle filter, we successfully captured the unexpected behaviors of individual dislocations.
This is a result of research collaboration with Prof. Mayu Muramatsu, Department of Science for Open and Environmental Systems, Graduate School of Keio University, and has been published in Scientific Reports (June 22, 2022).
