Denoising and feature extraction in photoemission spectra with variational auto-encoder neural networks

Abstract

In recent years, distinct machine learning (ML) models have been separately used for feature extraction and noise reduction from energy-momentum dispersion intensity maps obtained from raw angle-resolved photoemission spectroscopy (ARPES) data. In this work, we employ a shallow variational auto-encoder (VAE) neural network to demonstrate the prospect of using ML for both denoising of as well as feature extraction from ARPES dispersion maps.

arXiv commentSubmitted to Review of Scientific Instruments

References in corpus (9)

• A precise method for visualizing dispersive features in image plots
• Collective Modes and the Superconducting State Spectral Function of Bi2212
• Linear Response Theory and the Universal Nature of the Magnetic Excitation Spectrum of the Cuprates
• Condensation Energy and Spectral Functions in High Temperature Superconductors
• Deep learning-based statistical noise reduction for multidimensional spectral data
• Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data
• Visualizing dispersive features in 2D image via minimum gradient method
• Deconstruction of Resolution Effects in Angle-Resolved Photoemission
• Spectral deconvolution with deep learning: removing the effects of spectral PSF broadening