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

TL;DR

This paper demonstrates the use of a shallow variational auto-encoder neural network to simultaneously denoise and extract features from ARPES energy-momentum dispersion maps, streamlining analysis of photoemission spectra.

Contribution

It introduces a novel application of a shallow VAE for combined denoising and feature extraction in ARPES data, unifying two separate ML tasks.

Findings

VAE effectively denoises ARPES spectra.

VAE extracts meaningful features from raw data.

Method shows potential for improved spectral analysis.

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.