Neural network analysis of neutron and X-ray reflectivity data incorporating prior knowledge

J Appl Crystallogr. 2024 Mar 31;57(Pt 2):456-469. doi: 10.1107/S1600576724002115. eCollection 2024 Apr 1.

Abstract

Due to the ambiguity related to the lack of phase information, determining the physical parameters of multilayer thin films from measured neutron and X-ray reflectivity curves is, on a fundamental level, an underdetermined inverse problem. This ambiguity poses limitations on standard neural networks, constraining the range and number of considered parameters in previous machine learning solutions. To overcome this challenge, a novel training procedure has been designed which incorporates dynamic prior boundaries for each physical parameter as additional inputs to the neural network. In this manner, the neural network can be trained simultaneously on all well-posed subintervals of a larger parameter space in which the inverse problem is underdetermined. During inference, users can flexibly input their own prior knowledge about the physical system to constrain the neural network prediction to distinct target subintervals in the parameter space. The effectiveness of the method is demonstrated in various scenarios, including multilayer structures with a box model parameterization and a physics-inspired special parameterization of the scattering length density profile for a multilayer structure. In contrast to previous methods, this approach scales favourably when increasing the complexity of the inverse problem, working properly even for a five-layer multilayer model and a periodic multilayer model with up to 17 open parameters.

Keywords: inverse problems; machine learning; reflectometry; soft matter.

Grants and funding

This research was part of a project (VIPR 05D23VT1 ERUM-DATA) funded by the German Federal Ministry for Science and Education (BMBF). This work was partly supported by the consortium DAPHNE4NFDI in the context of the work of the NFDI e.V., funded by the German Research Foundation (DFG).