Deep learning denoising unlocks quantitative insights in operando materials microscopy

TL;DR

This paper introduces a deep learning-based denoising framework that enhances the resolution and quantitative analysis of operando microscopy across various modalities, revealing nanoscale details and reducing noise-related variability.

Contribution

It presents a general, unsupervised deep denoising approach that preserves physical fidelity and improves quantitative microscopy in multiple experimental settings.

Findings

Preserves physical fidelity with minimal bias in simulated data.

Reveals nanoscale heterogeneity in X-ray microscopy of LFP.

Reduces noise variability by nearly 80% in neutron radiography.

Abstract

Operando microscopy provides direct insight into the dynamic chemical and physical processes that govern functional materials, yet measurement noise limits the effective resolution and undermines quantitative analysis. Here, we present a general framework for integrating unsupervised deep learning-based denoising into quantitative microscopy workflows across modalities and length scales. Using simulated data, we demonstrate that deep denoising preserves physical fidelity, introduces minimal bias, and reduces uncertainty in model learning with partial differential equation (PDE)-constrained optimization. Applied to experiments, denoising reveals nanoscale chemical and structural heterogeneity in scanning transmission X-ray microscopy (STXM) of lithium iron phosphate (LFP), enables automated particle segmentation and phase classification in optical microscopy of graphite electrodes, and reduces noise-induced variability by nearly 80% in neutron radiography to resolve heterogeneous lithium transport. Collectively, these results establish deep denoising as a powerful, modality-agnostic enhancement that advances quantitative operando imaging and extends the reach of previously noise-limited techniques.