LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
2026-04-01 • Machine Learning
Machine LearningArtificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors developed LAPIS-SHRED, a system that can predict how complex things change over space and time even when only limited and brief sensor data is available. Their approach first learns from simulations to understand hidden patterns, then uses this knowledge to fill in missing time information. Finally, by combining these parts, it can reconstruct or predict full spatiotemporal behavior from very sparse, short observations. They tested this method on various complex systems like turbulent flows and environmental data, showing its usefulness when real-world measurements are scarce.
spatio-temporal dynamicslatent spacerecurrent decoderssimulation datadata assimilationturbulent flowstime series forecastingsensor datamultiscale reconstruction
Authors
Yuxuan Bao, Xingyue Zhang, J. Nathan Kutz
Abstract
Reconstructing full spatio-temporal dynamics from sparse observations in both space and time remains a central challenge in complex systems, as measurements can be spatially incomplete and can be also limited to narrow temporal windows. Yet approximating the complete spatio-temporal trajectory is essential for mechanistic insight and understanding, model calibration, and operational decision-making. We introduce LAPIS-SHRED (LAtent Phase Inference from Short time sequence using SHallow REcurrent Decoders), a modular architecture that reconstructs and/or forecasts complete spatiotemporal dynamics from sparse sensor observations confined to short temporal windows. LAPIS-SHRED operates through a three-stage pipeline: (i) a SHRED model is pre-trained entirely on simulation data to map sensor time-histories into a structured latent space, (ii) a temporal sequence model, trained on simulation-derived latent trajectories, learns to propagate latent states forward or backward in time to span unobserved temporal regions from short observational time windows, and (iii) at deployment, only a short observation window of hyper-sparse sensor measurements from the true system is provided, from which the frozen SHRED model and the temporal model jointly reconstruct or forecast the complete spatiotemporal trajectory. The framework supports bidirectional inference, inherits data assimilation and multiscale reconstruction capabilities from its modular structure, and accommodates extreme observational constraints including single-frame terminal inputs. We evaluate LAPIS-SHRED on six experiments spanning complex spatio-temporal physics: turbulent flows, multiscale propulsion physics, volatile combustion transients, and satellite-derived environmental fields, highlighting a lightweight, modular architecture suited for operational settings where observation is constrained by physical or logistical limitations.