@inproceedings{d732dc4b721d438c820827a2abe06e8f,
title = "Scientific Error-bounded Lossy Compression with Super-resolution Neural Networks",
abstract = "The fast growth of computational power and scales of modern super-computing systems have raised great challenges for the management of exascale scientific data. To maintain the usability of scientific data, error-bound lossy compression is proposed and developed as an essential technique for the size reduction of scientific data with constrained data distortion. Among the diverse datasets generated by various scientific simulations, certain datasets cannot be effectively compressed by existing error-bounded lossy compressors with traditional techniques. The recent success of Artificial Intelligence has inspired several researchers to integrate neural networks into error-bounded lossy compressors. However, those works still suffer from limited compression ratios and/or extremely low efficiencies. To address those issues and improve the compression on the hard-to-compress datasets, in this paper, we propose SRNNSZ, which is a deep learning-based scientific error-bounded lossy compressor leveraging the hierarchical data grid expansion paradigm implemented by super-resolution neural networks. SRNN-SZ applies the most advanced super-resolution network HAT for its compression, which is free of time-costing per-data training. In experiments compared with various state-of-the-art compressors, SRNN-SZ achieves up to 75% compression ratio improvements under the same error bound and up to 80% compression ratio improvements under the same PSNR than the second-best compressor.",
keywords = "deep learning, error-bounded lossy compression, super-resolution",
author = "Jinyang Liu and Sheng Di and Sian Jin and Kai Zhao and Xin Liang and Zizhong Chen and Franck Cappello",
note = "ACKNOWLEDGMENTS This research was supported by the Exascale Computing Project (ECP), Project Number: 17-SC-20-SC, a collaborative effort of two DOE organizations – the Office of Science and the National Nuclear Security Administration, responsible for the planning and preparation of a capable exascale ecosystem, including software, applications, hardware, advanced system engineering and early testbed platforms, to support the nation{\textquoteright}s exascale computing imperative. The material was supported by the U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research (ASCR), under contract DE-AC02-06CH11357, and supported by the National Science Foundation under Grant OAC-2003709, OAC-2104023, OAC-2311875, OAC-2311877, and OAC-2153451. We acknowledge the computing resources provided on Bebop (operated by Laboratory Computing Resource Center at Argonne) and on Theta and JLSE (operated by Argonne Leadership Computing Facility).; 2023 IEEE International Conference on Big Data, BigData 2023 ; Conference date: 15-12-2023 Through 18-12-2023",
year = "2023",
doi = "10.1109/BigData59044.2023.10386682",
language = "English (US)",
series = "Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "229--236",
editor = "Jingrui He and Themis Palpanas and Xiaohua Hu and Alfredo Cuzzocrea and Dejing Dou and Dominik Slezak and Wei Wang and Aleksandra Gruca and Lin, {Jerry Chun-Wei} and Rakesh Agrawal",
booktitle = "Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023",
address = "United States",
}