Spectroscopic data de-noising via training-set-free deep learning method

TL;DR

This paper introduces a training-set-free deep learning approach for de-noising spectra, particularly in ARPES, by leveraging self-correlation within the data, enabling intrinsic feature extraction without high-quality training data.

Contribution

The method uniquely removes the need for training sets by utilizing self-correlation, making it adaptable to various fields with limited training data.

Findings

Effectively preserves intrinsic spectral features.

Applicable to ARPES and potentially other spectral data.

Does not require high-quality training datasets.

Abstract

De-noising plays a crucial role in the post-processing of spectra. Machine learning-based methods show good performance in extracting intrinsic information from noisy data, but often require a high-quality training set that is typically inaccessible in real experimental measurements. Here, using spectra in angle-resolved photoemission spectroscopy (ARPES) as an example, we develop a de-noising method for extracting intrinsic spectral information without the need for a training set. This is possible as our method leverages the self-correlation information of the spectra themselves. It preserves the intrinsic energy band features and thus facilitates further analysis and processing. Moreover, since our method is not limited by specific properties of the training set compared to previous ones, it may well be extended to other fields and application scenarios where obtaining high-quality multidimensional training data is challenging.