# Foundation Model for Lossy Compression of Spatiotemporal Scientific Data

arXiv: https://arxiv.org/abs/2412.17184 · HTML: https://mlsanity.com/paper/2412.17184/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors](https://mlsanity.com/paper/2111.02925/) (2021)
- [Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets](https://mlsanity.com/paper/2003.13549/) (2020)
- [Exploring Autoencoder-based Error-bounded Compression for Scientific Data](https://mlsanity.com/paper/2105.11730/) (2021)
- [SRN-SZ: Deep Leaning-Based Scientific Error-bounded Lossy Compression with Super-resolution Neural Networks](https://mlsanity.com/paper/2309.04037/) (2023)
- [Attention Based Machine Learning Methods for Data Reduction with Guaranteed Error Bounds](https://mlsanity.com/paper/2409.05357/) (2024)
- [A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps](https://mlsanity.com/paper/2212.06717/) (2022)
- [Machine Learning Techniques for Data Reduction of Climate Applications](https://mlsanity.com/paper/2405.00879/) (2024)

## Built on by (most cited first, 2 of 2)

- [Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction](https://mlsanity.com/paper/2507.02129/) (2025)
- [Residual Modeling for High-Fidelity Learned Compression of Scientific Data](https://mlsanity.com/paper/2606.05389/) (2026)

## Abstract (arXiv)

We present a foundation model (FM) for lossy scientific data compression, combining a variational autoencoder (VAE) with a hyper-prior structure and a super-resolution (SR) module. The VAE framework uses hyper-priors to model latent space dependencies, enhancing compression efficiency. The SR module refines low-resolution representations into high-resolution outputs, improving reconstruction quality. By alternating between 2D and 3D convolutions, the model efficiently captures spatiotemporal correlations in scientific data while maintaining low computational cost. Experimental results demonstrate that the FM generalizes well to unseen domains and varying data shapes, achieving up to 4 times higher compression ratios than state-of-the-art methods after domain-specific fine-tuning. The SR module improves compression ratio by 30 percent compared to simple upsampling techniques. This approach significantly reduces storage and transmission costs for large-scale scientific simulations while preserving data integrity and fidelity.