Determining Atomic Structure from Spectroscopy via an Active Learning Framework

TL;DR

ActiveStructOpt is an active learning framework that uses graph neural networks to efficiently determine atomic structures from spectroscopic data, outperforming existing methods across various materials.

Contribution

It introduces a novel active learning approach combining GNN surrogate models for rapid and accurate atomic structure determination from spectroscopy.

Findings

Reliable structure determination matching spectra across materials

Outperforms existing methods within same computational budgets

Effective with diverse spectroscopic techniques

Abstract

Determining atomic structure from spectroscopic data is central to materials science but remains restricted to a limited set of techniques and material classes, largely due to the computational cost and complexity of structural refinement. Here we introduce ActiveStructOpt, a general framework that integrates graph neural network surrogate models with active learning to efficiently determine candidate structures that reproduce target spectra with minimal computational expenditure. Benchmarking with X-ray pair distribution function data, and with the more computationally demanding simulations of X-ray absorption near-edge spectra (XANES) and extended X-ray absorption fine structure (EXAFS), demonstrate that ActiveStructOpt reliably determines structures that match closely in spectra across diverse materials classes. Under equivalent computational budgets, ActiveStructOpt outperforms existing structure determination methods. By enabling data-efficient, multi-objective structural refinement across a broad range of computable spectroscopic techniques, ActiveStructOpt provides a flexible and extensible approach to atomic structure determination in complex materials.