Weak signal extraction enabled by deep neural network denoising of diffraction data
Open Access
- 13 February 2024
- journal article
- research article
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 6 (2) , 180-186
Abstract
The removal or cancellation of noise has wide-spread applications in imaging and acoustics. In applications in everyday life, such as image restoration, denoising may even include generative aspects, which are unfaithful to the ground truth. For scientific use, however, denoising must reproduce the ground truth accurately. Denoising scientific data is further challenged by unknown noise profiles. In fact, such data will often include noise from multiple distinct sources, which substantially reduces the applicability of simulation-based approaches. Here we show how scientific data can be denoised by using a deep convolutional neural network such that weak signals appear with quantitative accuracy. In particular, we study X-ray diffraction and resonant X-ray scattering data recorded on crystalline materials. We demonstrate that weak signals stemming from charge ordering, insignificant in the noisy data, become visible and accurate in the denoised data. This success is enabled by supervised training of a deep neural network with pairs of measured low- and high-noise data. We additionally show that using artificial noise does not yield such quantitatively accurate results. Our approach thus illustrates a practical strategy for noise filtering that can be applied to challenging acquisition problems.Keywords
All Related Versions
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (200021 188564, PP00P2 176866, 200021 188564, 200021 188564, 200021 188564, 200021 188564)
- Universität Zürich (K-72334-06-0, FK-22-085)
- ONR
- EC | Horizon 2020 Framework Programme (ERC-StG-Neupert-757867-PARATOP, 730872, ERC-StG-Neupert-757867-PARATOP, 730872)
- Research Grants Council of Hong Kong
- Swiss Government Excellence Scholarship
- Swiss Government Excellence Scholarship
This publication has 33 references indexed in Scilit:
- Crystal symmetry of stripe-orderedPhysical Review B, 2022
- Deep time series models for scarce dataNeurocomputing, 2021
- Deep learning-based statistical noise reduction for multidimensional spectral dataReview of Scientific Instruments, 2021
- Deep learning on image denoising: An overviewNeural Networks, 2020
- Quantitative Analysis of Electron Beam Damage in Organic Thin FilmsThe Journal of Physical Chemistry C, 2017
- Field-induced spin-density wave beyond hidden order in URu2Si2Nature Communications, 2016
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- Competing charge, spin, and superconducting orders in underdopedPhysical Review B, 2014
- Charge density wave fluctuations inand their competition with superconductivityPhysical Review B, 2014
- Tuning competing orders incuprate superconductors by the application of an external magnetic fieldPhysical Review B, 2008