Compositional neural networks improve multimodal X-ray and neutron data analysis

Compositional neural networks for multimodal X-ray and neutron scattering inversion

Machine Learning

Summary

X-ray and neutron scattering techniques help scientists understand the tiny structures inside materials, but interpreting their data is tricky because different structures can look similar. The authors created a way to combine different types of these measurements using specialized neural networks that can be trained separately and then joined together for analysis. This approach helps reduce confusion and gives better estimates of structures by using multiple kinds of scattering data without needing to retrain all models together. They tested the method on examples involving reflectometry, which looks at thin layers inside materials, showing it works well for combining different measurement types.

What this means in practice

Authors

Valentin Munteanu, Alexander Hinderhofer, Dmitry Lapkin, Vladimir Starostin, Frank Schreiber

Abstract

X-ray and neutron scattering are indispensable for structural characterization across condensed-matter physics and materials science. Yet, because scattering experiments generally record intensities without phase information, distinct structures can yield similar scattering patterns, rendering the corresponding inverse problems non-unique. This ambiguity can be reduced by combining complementary measurements, but their integration into machine-learning frameworks remains challenging. Here we introduce a modular framework for probabilistic multi-measurement analysis based on prior-amortized flow matching. Single-observation posterior estimators are trained separately for individual observation types or physical probes and combined only at inference time through a compositional sampler. This late fusion approach allows pretrained single-observation models to be reused without dedicated joint retraining. As a case in point, we consider reflectometry, which provides depth-resolved, nanometer-scale information about thin films and interfaces. Our single-observation demonstrations span X-ray, time-of-flight neutron and polarized neutron reflectometry. In separate co-refinement studies, task-matched estimators enable homogeneous composition across multiple neutron contrasts and heterogeneous multimodal composition of X-ray and neutron measurements. Together, these results establish compositional flow matching as a modular approach to uncertainty-aware inversion and co-refinement, with potential applicability to other scattering problems in which multiple observations constrain a common physical structure while retaining measurement-specific parameters.
View PDFOpen arXiv