Accelerating Neutron Scattering Data Collection and Experiments Using AI Deep Super-Resolution Learning

TL;DR

This paper introduces a deep learning-based super-resolution method to enhance neutron scattering data, significantly reducing data collection time and enabling the study of dynamic material processes.

Contribution

It presents a novel AI-driven super-resolution approach to reconstruct high-resolution scattering data from lower-resolution measurements, improving experimental efficiency.

Findings

Reduced data collection time by increasing detector pixel binning.

Achieved high-resolution data reconstruction using deep super-resolution learning.

Enabled observation of transient phenomena previously inaccessible.

Abstract

We present a novel methodology of augmenting the scattering data measured by small angle neutron scattering via an emerging deep convolutional neural network (CNN) that is widely used in artificial intelligence (AI). Data collection time is reduced by increasing the size of binning of the detector pixels at the sacrifice of resolution. High-resolution scattering data is then reconstructed by using AI deep super-resolution learning method. This technique can not only improve the productivity of neutron scattering instruments by speeding up the experimental workflow but also enable capturing kinetic changes and transient phenomenon of materials that are currently inaccessible by existing neutron scattering techniques.