Transfer Learning Application of Self-supervised Learning in ARPES
arXiv:2208.10893 · doi:10.1088/2632-2153/aced7d
Abstract
Recent development in angle-resolved photoemission spectroscopy (ARPES) technique involves spatially resolving samples while maintaining the high-resolution feature of momentum space. This development easily expands the data size and its complexity for data analysis, where one of it is to label similar dispersion cuts and map them spatially. In this work, we demonstrate that the recent development in representational learning (self-supervised learning) model combined with k-means clustering can help automate that part of data analysis and save precious time, albeit with low performance. Finally, we introduce a few-shot learning (k-nearest neighbour or kNN) 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 the self-supervised learning to automate the image analysis in ARPES in particular and can be generalized into any science data analysis that heavily involves image data.
References in corpus (20)
- A Simple Framework for Contrastive Learning of Visual Representations
- Bootstrap your own latent: A new approach to self-supervised Learning
- Discovery of a Three-dimensional Topological Dirac Semimetal, Na3Bi
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Angle-resolved photoemission spectroscopy and its application to topological materials
- Fermi Surface, Surface States, and Surface Reconstruction in Sr2RuO4
- Coupling Of The B1g Phonon To The Anti-Nodal Electronic States of Bi2Sr2Ca0.92Y0.08Cu2O(8+delta)
- Self-supervised representation learning from 12-lead ECG data
- Dirac Line-nodes and Effect of Spin-orbit Coupling in Non-symmorphic Critical Semimetal MSiS (M=Hf, Zr)
- Noise2Inverse: Self-supervised deep convolutional denoising for tomography
- Angle-resolved photoemission spectroscopy
- Time- and angle-resolved photoemission spectroscopy of solids in the extreme ultraviolet at 500 kHz repetition rate
- Microfocus laser-ARPES on encapsulated mono-, bi-, and few-layer 1T'-WTe
- Very Efficient Spin Polarization Analysis (VESPA): New Exchange Scattering-based Setup for Spin-resolved ARPES at APE-NFFA Beamline at Elettra
- Persistent gapless surface states in MnBi2Te4/Bi2Te3 superlattice antiferromagnetic topological insulator
- High resolution time- and angle-resolved photoemission spectroscopy with 11 eV laser pulses
- Deep learning-based statistical noise reduction for multidimensional spectral data
- Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data
- Revealing the chemical bonding in adatoms arrays via machine learning of 3D scanning tunneling spectroscopy data
- Fermi surface tomography