Deep learning-based statistical noise reduction for multidimensional spectral data

TL;DR

This paper presents a deep learning-based denoising method that significantly reduces noise in multidimensional spectral data, enabling high-quality analysis with much shorter data acquisition times.

Contribution

The authors develop a neural network denoising approach that effectively removes noise from multidimensional spectral data, demonstrated on ARPES, without overfitting, and applicable to various spectral datasets.

Findings

Neural network denoising preserves intrinsic data features.

Achieves similar analysis quality with 100x less acquisition time.

Applicable to any multidimensional spectral data.

Abstract

In spectroscopic experiments, data acquisition in multi-dimensional phase space may require long acquisition time, owing to the large phase space volume to be covered. In such case, the limited time available for data acquisition can be a serious constraint for experiments in which multidimensional spectral data are acquired. Here, taking angle-resolved photoemission spectroscopy (ARPES) as an example, we demonstrate a denoising method that utilizes deep learning as an intelligent way to overcome the constraint. With readily available ARPES data and random generation of training data set, we successfully trained the denoising neural network without overfitting. The denoising neural network can remove the noise in the data while preserving its intrinsic information. We show that the denoising neural network allows us to perform similar level of second-derivative and line shape analysis on data taken with two orders of magnitude less acquisition time. The importance of our method lies in its applicability to any multidimensional spectral data that are susceptible to statistical noise.