Self-supervised learning for denoising quasiparticle interference data
Physical review. B./Physical review. B, vol. 111
Abstract
Tunneling spectroscopy is an important tool for the study of both real- and momentum-space electronic structure of correlated electron systems. However, such measurements often yield noisy data. Machine learning provides techniques to reduce the noise in postprocessing, but traditionally requires noiseless examples which are unavailable for scientific experiments. In this work we adapt the unsupervised Noise2Noise and self-supervised Noise2Self algorithms, which allow for denoising without clean examples, to denoise quasiparticle interference data. We first apply the techniques on simulated data, and demonstrate that we are able to reduce the noise while preserving finer details, all while outperforming more traditional denoising techniques. We then apply the Noise2Self technique to experimental data from an overdoped cuprate [(Pb,${\mathrm{Bi})}_{2}{\mathrm{Sr}}_{2}{\mathrm{CuO}}_{6+\ensuremath{\delta}}]$ sample. Denoising enhances the clarity of quasiparticle interference patterns, and helps to obtain a precise extraction of electronic structure parameters. Self-supervised denoising is a promising tool for denoising quasiparticle interference data, facilitating deeper insights into the physics of complex materials.
Authors 7
-
Affiliation as printed
Leiden University
-
Willem O. Tromp Aachen
Affiliation as printed
Leiden University
-
Tjerk Benschop Aachen
Affiliation as printed
Leiden University
-
University of the Philippines Diliman
Affiliation as printed
University of the Philippines Diliman
-
University of the Philippines Diliman
Affiliation as printed
University of the Philippines Diliman
-
Evert van Nieuwenburg Aachen
Affiliation as printed
Leiden University
-
Milan P. Allan Aachen
Leiden University · Munich Center for Quantum Science and Technology · Ludwig-Maximilians-Universität München
Affiliation as printed
Leiden University
Ludwig-Maximilians-University Munich
Munich Center for Quantum Science and Technology
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-11).