Solving the inverse problem of X-ray absorption spectroscopy via physics-informed deep learning

TL;DR

This paper introduces SPT, a physics-informed deep learning method that accurately inverts X-ray absorption spectra to determine atomic structures, enabling rapid, noise-resilient analysis for materials discovery.

Contribution

The authors develop a novel deep learning framework leveraging Fourier duality to improve the inversion of XAS spectra, bridging the gap between theory and experiment.

Findings

Achieves state-of-the-art accuracy in structural determination from XAS data.

Operates with millisecond-scale latency, suitable for autonomous experiments.

Effectively isolates structural signals from experimental noise.

Abstract

Resolving transient atomic configurations in non-crystalline or dynamic environments remains a fundamental bottleneck in the physical sciences. While X-ray absorption spectroscopy (XAS) is a premier probe of local structure, inverting spectra into structural descriptors is a notoriously ill-posed problem due to inherent many-to-one mapping. Here, we present the Spectral Pattern Translator (SPT), a physics-informed deep learning framework that establishes a robust bridge between large-scale theoretical datasets and experimental reality. Our strategy exploits the Fourier duality between spectral energy oscillations and spatial scattering paths to overcome the "simulation-to-experiment" gap. By decomposing spectra into frequency domains, SPT effectively isolates robust structural coordination signals from the destabilizing noise inherent in experimental data. Trained on a massive library of diverse atomic environments, this approach achieves state-of-the-art accuracy in resolving continuous phase transitions in battery cathodes and deciphering local order in amorphous materials. With millisecond-scale latency, SPT removes the primary computational barrier to autonomous materials discovery, establishing a robust, noise-resilient engine for closed-loop robotic chemistry.