Weak-signal extraction enabled by deep-neural-network denoising of diffraction data

Abstract

Removal or cancellation of noise has wide-spread applications for imaging and acoustics. In every-day-life applications, denoising may even include generative aspects, which are unfaithful to the ground truth. For scientific use, however, denoising must reproduce the ground truth accurately. Here, we show how data can be denoised via a deep convolutional neural network such that weak signals appear with quantitative accuracy. In particular, we study X-ray diffraction 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 demonstrate 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.

14 pages, 10 figures; extended study, additional supplementary information, results unchanged

References in corpus (9)

• Charge density wave fluctuations in La2-xSrxCuO4 and their competition with superconductivity
• Competing charge, spin, and superconducting orders in underdoped YBa2Cu3Oy
• Tuning competing orders in La2-xSrxCuO4 cuprate superconductors by the application of an external magnetic field
• Rotated stripe order and its competition with superconductivity in La${}_{1.88}$Sr${}_{0.12}$CuO${}_4$
• Deep learning-based statistical noise reduction for multidimensional spectral data
• Field-induced spin-density wave beyond hidden order in URu2Si2
• Susceptibility anisotropy in an iron arsenide superconductor revealed by x-ray diffraction in pulsed magnetic fields
• Bulk charge stripe order competing with superconductivity in La2-xSrxCuO4 (x=0.12)
• Crystal Symmetry of Stripe Ordered La1.88Sr0.12CuO4

Cited by in corpus (3)

• Deep-learning real-time phase retrieval of imperfect diffraction patterns from X-ray free-electron lasers
• Identifying Crystal Structures Beyond Known Prototypes from X-ray Powder Diffraction Spectra
• Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising