Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data

Abstract

Two dimensional (2D) peak finding is a common practice in data analysis for physics experiments, which is typically achieved by computing the local derivatives. However, this method is inherently unstable when the local landscape is complicated, or the signal-to-noise ratio of the data is low. In this work, we propose a new method in which the peak tracking task is formalized as an inverse problem, thus can be solved with a convolutional neural network (CNN). In addition, we show that the underlying physics principle of the experiments can be used to generate the training data. By generalizing the trained neural network on real experimental data, we show that the CNN method can achieve comparable or better results than traditional derivative based methods. This approach can be further generalized in different physics experiments when the physical process is known.

13pages, 6 figures

References in corpus (6)

• Angle-resolved photoemission spectroscopy of the cuprate superconductors
• A precise method for visualizing dispersive features in image plots
• Phase competition in trisected superconducting dome
• Rapid change of superconductivity and electron-phonon coupling through 19% doping in Bi2212
• The hierarchy of multiple many-body interaction scales in high-temperature superconductors
• Visualizing dispersive features in 2D image via minimum gradient method

Cited by in corpus (9)

• Electronic structure of quantum materials studied by angle-resolved photoemission spectroscopy
• Machine Learning on Neutron and X-Ray Scattering
• A machine learning route between band mapping and band structure
• Removing grid structure in angle-resolved photoemission spectra via deep learning method
• Transfer Learning Application of Self-supervised Learning in ARPES
• Denoising and feature extraction in photoemission spectra with variational auto-encoder neural networks
• Spectroscopic data de-noising via training-set-free deep learning method
• About two-dimensional fits for the analysis of the scattering rates and renormalization functions from angle-resolved photoelectron spectroscopy data
• Neural networks for a quick access to a digital twin of scanning physical properties measurements