Enhancing Lossy Compression Through Cross-Field Information for Scientific Applications

TL;DR

This paper introduces a hybrid prediction model leveraging cross-field correlations with CNNs to significantly improve lossy compression ratios for scientific data, preserving data quality and reducing artifacts.

Contribution

It presents a novel hybrid CNN-based prediction model that utilizes cross-field information, enhancing lossy compression performance for scientific datasets.

Findings

Up to 25% improvement in compression ratios.

Better data detail preservation and fewer artifacts.

Effective across multiple scientific datasets.

Abstract

Lossy compression is one of the most effective methods for reducing the size of scientific data containing multiple data fields. It reduces information density through prediction or transformation techniques to compress the data. Previous approaches use local information from a single target field when predicting target data points, limiting their potential to achieve higher compression ratios. In this paper, we identified significant cross-field correlations within scientific datasets. We propose a novel hybrid prediction model that utilizes CNN to extract cross-field information and combine it with existing local field information. Our solution enhances the prediction accuracy of lossy compressors, leading to improved compression ratios without compromising data quality. We evaluate our solution on three scientific datasets, demonstrating its ability to improve compression ratios by up to 25% under specific error bounds. Additionally, our solution preserves more data details and reduces artifacts compared to baseline approaches.