Transfer learning application of self-supervised learning in ARPES

• Published in: Machine learning: science and technology Vol. 4; no. 3; pp. 35021 - 35030
• Main Authors: Ekahana, Sandy Adhitia, Winata, Genta Indra, Soh, Y, Tamai, Anna, Milan, Radovic, Aeppli, Gabriel, Shi, Ming
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.09.2023
• Subjects: ARPES; Automation; Cluster analysis; Clustering; Free electron lasers; Image analysis; Labels; Material properties; Photoelectric emission; representation learning; self-supervised; Self-supervised learning; Spatial resolution; Spectrometers; transfer learning; Vector quantization
• ISSN: 2632-2153; 2632-2153
• DOI: 10.1088/2632-2153/aced7d

Abstract There is a growing recognition that electronic band structure is a local property of materials and devices, and there is steep growth in capabilities to collect the relevant data. New photon sources, from small-laboratory-based lasers to free electron lasers, together with focusing beam optics and advanced electron spectrometers, are beginning to enable angle-resolved photoemission spectroscopy (ARPES) in scanning mode with a spatial resolution of near to and below microns, two- to three orders of magnitude smaller than what has been typical for ARPES hitherto. The results are vast data sets inhabiting a five-dimensional subspace of the ten-dimensional space spanned by two scanning dimensions of real space, three of reciprocal space, three of spin-space, time, and energy. In this work, we demonstrate that recent developments in representational learning (self-supervised learning) combined with k -means clustering can help automate the labeling and spatial mapping of dispersion cuts, thus saving precious time relative to manual analysis, albeit with low performance. Finally, we introduce a few-shot learning ( k -nearest neighbor) in representational space where we selectively choose one ( k = 1) image reference for each known label and subsequently label the rest of the data with respect to the nearest reference image. This last approach demonstrates the strength of self-supervised learning to automate image analysis in ARPES in particular and can be generalized to any scientific image analysis.