Software Open Access

Removal of bremsstrahlung background from SAXS signals with deep neural networks: sourcecode

Starke, Sebastian; Smid, Michal

This repository contains the sourcecode used to train neural networks for the removal of bremsstrahlung background from SAXS data. Also, it offers a script to apply trained models to new noisy data.

Files (1.1 MB)
Name Size
Helmholtz-AI-Matter/bremsstrahlung_denoising-v0.1.0.zip
md5:6ea745227e4fd29dd03748bf7887e97d 		1.1 MB Download
273
13
views
downloads
All versions This version
Views 273273
Downloads 1313
Data volume 14.7 MB14.7 MB
Unique views 249249
Unique downloads 1313
More info on how stats are collected.
Publication date:
August 25, 2026
DOI:
10.14278/rodare.4976

RODARE DOI Badge

DOI 

10.14278/rodare.4976

Markdown 

[![DOI](https://rodare.hzdr.de/badge/DOI/10.14278/rodare.4976.svg)](https://doi.org/10.14278/rodare.4976)

reStructedText 

.. image:: https://rodare.hzdr.de/badge/DOI/10.14278/rodare.4976.svg
   :target: https://doi.org/10.14278/rodare.4976

HTML 

<a href="https://doi.org/10.14278/rodare.4976"><img src="https://rodare.hzdr.de/badge/DOI/10.14278/rodare.4976.svg" alt="DOI"></a>

Image URL 

https://rodare.hzdr.de/badge/DOI/10.14278/rodare.4976.svg

Target URL 

https://doi.org/10.14278/rodare.4976

Keyword(s):
SAXS XFEL equivariant neural networks noise removal
Related identifiers:
Compiles:
https://www.hzdr.de/publications/Publ-37977, 10.14278/rodare.4956
Has part:
https://github.com/Helmholtz-AI-Matter/bremsstrahlung_denoising/tree/v0.1.0
Identical to:
https://www.hzdr.de/publications/Publ-43791
Communities:
License (for files):
MIT License

Versions

Version v0.1.0 10.14278/rodare.4976 Aug 25, 2026
Cite all versions? You can cite all versions by using the DOI 10.14278/rodare.4975. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export