Storing and sharing increasingly large datasets is a challenge across scientific research and industry. In this paper, we document the development and applications of Baler - a Machine Learning based data compression tool for use across scientific disciplines and industry. Here, we present Baler's performance for the compression of High Energy Physics (HEP) data, as well as its application to Computational Fluid Dynamics (CFD) toy data as a proof-of-principle. We also present suggestions for cross-disciplinary guidelines to enable feasibility studies for machine learning based compression for scientific data.
@article{arxiv.2305.02283,
title = {Baler -- Machine Learning Based Compression of Scientific Data},
author = {Fritjof Bengtsson and Caterina Doglioni and Per Alexander Ekman and Axel Gallén and Pratik Jawahar and Alma Orucevic-Alagic and Marta Camps Santasmasas and Nicola Skidmore and Oliver Woolland},
journal= {arXiv preprint arXiv:2305.02283},
year = {2024}
}