ANTIC: Adaptive Neural Temporal In-situ Compressor
2026-04-10 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed ANTIC, a smart method to shrink huge amounts of data from complex simulations that change over time, like weather or space models. It picks out the most important moments during the simulation and uses neural networks to compress the details between those moments. This approach helps save a ton of storage space without losing much important information. Their tests show it works well in keeping accuracy while drastically reducing storage needs.
partial differential equationsNavier-Stokes equationsin situ compressionneural networksspatiotemporal datahigh-performance computingdata compressionneural fieldsadaptive samplingsimulation data
Authors
Sandeep S. Cranganore, Andrei Bodnar, Gianluca Galleti, Fabian Paischer, Johannes Brandstetter
Abstract
The persistent storage requirements for high-resolution, spatiotemporally evolving fields governed by large-scale and high-dimensional partial differential equations (PDEs) have reached the petabyte-to-exabyte scale. Transient simulations modeling Navier-Stokes equations, magnetohydrodynamics, plasma physics, or binary black hole mergers generate data volumes that are prohibitive for modern high-performance computing (HPC) infrastructures. To address this bottleneck, we introduce ANTIC (Adaptive Neural Temporal in situ Compressor), an end-to-end in situ compression pipeline. ANTIC consists of an adaptive temporal selector tailored to high-dimensional physics that identifies and filters informative snapshots at simulation time, combined with a spatial neural compression module based on continual fine-tuning that learns residual updates between adjacent snapshots using neural fields. By operating in a single streaming pass, ANTIC enables a combined compression of temporal and spatial components and effectively alleviates the need for explicit on-disk storage of entire time-evolved trajectories. Experimental results demonstrate how storage reductions of several orders of magnitude relate to physics accuracy.