An autoencoder for compressing angle-resolved photoemission spectroscopy data

TL;DR

This paper introduces ARPESNet, an autoencoder that effectively compresses ARPES data, enabling faster analysis without significant loss of information, which is crucial given the increasing data rates and limited access to advanced ARPES instruments.

Contribution

The paper presents a novel autoencoder architecture, ARPESNet, specifically designed for efficient compression and summarization of ARPES datasets, outperforming traditional methods in clustering quality.

Findings

ARPESNet achieves high compression ratios with minimal loss of clustering quality.

ARPESNet outperforms discrete cosine transform in data compression tasks.

The autoencoder maintains robustness across different noise levels.

Abstract

Angle-resolved photoemission spectroscopy (ARPES) is a powerful experimental technique to determine the electronic structure of solids. Advances in light sources for ARPES experiments are currently leading to a vast increase of data acquisition rates and data quantity. On the other hand, access time to the most advanced ARPES instruments remains strictly limited, calling for fast, effective, and on-the-fly data analysis tools to exploit this time. In response to this need, we introduce ARPESNet, a versatile autoencoder network that efficiently summmarises and compresses ARPES datasets. We train ARPESNet on a large and varied dataset of 2-dimensional ARPES data extracted by cutting standard 3-dimensional ARPES datasets along random directions in $\mathbf{k}$. To test the data representation capacity of ARPESNet, we compare $k$-means clustering quality between data compressed by ARPESNet, data compressed by discrete cosine transform, and raw data, at different noise levels. ARPESNet data excels in clustering quality despite its high compression ratio.