利用跨场信息提升科学数据压缩率，不损失质量
Enhancing Lossy Compression Through Cross-Field Information for Scientific Applications
- 用CNN捕捉多场数据间的关联信息，融合局部预测
- 在三个数据集上实现最高25%的压缩率提升
- 适合需要高压缩比的科学数据存储与传输场景
有损压缩是减少包含多个数据场的科学数据规模的有效方法，通过预测或变换技术降低信息密度以实现压缩。以往方法在预测目标数据点时仅使用单个目标场的局部信息，限制了压缩比的进一步提升。本文发现科学数据集中存在显著的跨场相关性，提出一种新型混合预测模型，利用卷积神经网络（CNN）提取跨场信息，并与现有局部场信息结合。该方法提升了有损压缩器的预测精度，从而在不损害数据质量的前提下提高压缩比。我们在三个科学数据集上进行了评估，结果表明，在特定误差约束下，压缩比最高可提升25%。此外，相比基线方法，本方案保留了更多数据细节并减少了伪影。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。