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

TL;DR

This paper presents a deep neural network approach for denoising X-ray diffraction data, enabling accurate visualization of weak signals like charge ordering that are obscured by noise.

Contribution

The study introduces a supervised deep learning method for quantitative denoising of diffraction data, outperforming artificial noise models and aiding scientific analysis.

Findings

Weak signals become visible after denoising.

Supervised training with real data pairs is crucial.

Artificial noise training does not achieve the same accuracy.

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.