Machine learning-accelerated small-angle X-ray scattering analysis of disordered two- and three-phase materials
Artikel i vetenskaplig tidskrift, 2022

Small-angle X-ray scattering (SAXS) is a useful technique for nanoscale structural characterization of materials. In SAXS, structural and spatial information is indirectly obtained from the scattering intensity in the spectral domain, known as the reciprocal space. Therefore, characterizing the structure requires solving the inverse problem of finding a plausible structure model that corresponds to the measured scattering intensity. Both the choice of structure model and the computational workload of parameter estimation are bottlenecks in this process. In this work, we develop a framework for analysis of SAXS data from disordered materials. The materials are modeled using Gaussian Random Fields (GRFs). We study the case of two phases, pore and solid, and three phases, where a third phase is added at the interface between the two other phases. Further, we develop very fast GPU-accelerated, Fourier transform-based numerical methods for both structure generation and SAXS simulation. We demonstrate that length scales and volume fractions can be predicted with good accuracy using our machine learning-based framework. The parameter prediction executes virtually instantaneously and hence the computational burden of conventional model fitting can be avoided.

machine learning

Gaussian random field

regression

disordered material

small angle X-ray scattering

boosted trees

porous material

Författare

Magnus Röding

Henan University of Chinese Medicine

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Piotr Tomaszewski

RISE Research Institutes of Sweden

Shun Yu

RISE Research Institutes of Sweden

M. Borg

RISE Research Institutes of Sweden

Jerk Rönnols

RISE Research Institutes of Sweden

Frontiers in Materials

22968016 (eISSN)

Vol. 9 956839

Ämneskategorier

Beräkningsmatematik

Annan fysik

Sannolikhetsteori och statistik

DOI

10.3389/fmats.2022.956839

Mer information

Senast uppdaterat

2022-10-25