Towards Reflectivity profile inversion through Artificial Neural Networks

Carmona-Loaiza, Juan Manuel

Preprint

FZJ-2020-05304

Towards Reflectivity profile inversion through Artificial Neural Networks

Carmona-Loaiza, J. M. (Corresponding author)FZJ*

2020

This record in other databases:

Please use a persistent id in citations: http://hdl.handle.net/2128/26611

Abstract: The goal of Specular Neutron and X-ray Reflectometry is to infer materials Scattering Length Density (SLD) profiles from experimental reflectivity curves. This paper focuses on investigating an original approach to the ill-posed non-invertible problem which involves the use of Artificial Neural Networks (ANN). In particular, the numerical experiments described here deal with large data sets of simulated reflectivity curves and SLD profiles, and aim to assess the applicability of Data Science and Machine Learning technology to the analysis of data generated at large scale facilities. It is demonstrated that, under certain circumstances, properly trained Deep Neural Networks are capable of correctly recovering plausible SLD profiles when presented with never-seen-before simulated reflectivity curves. When the necessary conditions are met, a proper implementation of the described approach would offer two main advantages over traditional fitting methods when dealing with real experiments, namely, 1. no prior assumptions about the sample physical model are required and 2. the times-to-solution are shrank by orders of magnitude, enabling faster batch analyses for large datasets.

Keyword(s): Others (1st) ; Instrument and Method Development (2nd)

Note: Submitted to MLST (Machine Learning: Science and Technology) - 10 pages, 8 figures

Contributing Institute(s):

Research Program(s):

Experiment(s):