Skip to main content

Neutron Reflectivity Dataset for Noise-Robust SLD Profile Prediction Using Structured Dropout - Five Layers Material

    Yuqing Qiao | Northeastern University
    Shanshou Li | Northeastern University
    Jong Keum | Oak Ridge National Laboratory
    Rajeev Kumar | Oak Ridge National Laboratory
    Miguel Fuentes-Cabrera | Northeastern University
Download Dataset on Globus

Description

This dataset contains 150,000 simulated five-layer neutron reflectivity (NR) curves and corresponding scattering length density (SLD) profiles generated using the pyreflect-nr library. The paired data were shuffled and divided into training and test sets. The dataset also includes seven experimental NR datasets and corresponding SLD fits prepared by Dr. Jong Keum.

Funding Information

DOE Contract Number

AC05-00OR22725

Originating Research Organization

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Other Contributing Organizations

Northeastern University

Sponsoring Organization

Office of Science (SC)

Details

DOI

https://doi.org/10.13139/ORNLNCCS/3363420

Release Date

October 19, 2026

Subject

MATERIALS SCIENCE

Keywords

Machine Learning, Materials Science

Dataset

Dataset Type

ND Numeric Data

Software

Python (≥ 3.10); CUDA

Cite This Dataset:

Qiao, Y., Li, S., Keum, J., Kumar, R., Fuentes-Cabrera, M. (2026). Neutron Reflectivity Dataset for Noise-Robust SLD Profile Prediction Using Structured Dropout - Five Layers Material. Oak Ridge National Laboratory. https://doi.org/10.13139/ORNLNCCS/3363420.

Acknowledgements

This work was carried out [in part] at Oak Ridge National Laboratory, managed by UT-Battelle, LLC for the U.S. Department of Energy under contract DE-AC05-00OR22725.