SRN-SZ: Deep Leaning-Based Scientific Error-bounded Lossy Compression with Super-resolution Neural Networks

TL;DR

SRN-SZ is a deep learning-based scientific data compressor that leverages super-resolution neural networks to significantly improve compression ratios while maintaining error bounds, addressing limitations of existing methods.

Contribution

The paper introduces SRN-SZ, a novel error-bounded lossy compressor using super-resolution neural networks, achieving higher compression ratios without per-data training.

Findings

Up to 75% higher compression ratios compared to state-of-the-art.

Achieves up to 80% better compression under the same PSNR.

No additional per-data training required for the super-resolution network.

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 SRN-SZ, which is a deep learning-based scientific error-bounded lossy compressor leveraging the hierarchical data grid expansion paradigm implemented by super-resolution neural networks. SRN-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, SRN-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.