cs.AINov 4, 2026

DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation

Authors: Yizhou Zhang, Panqi Chen, Lei Cheng, Ting Zhang, Jianlong Li, Jianfeng Shi, Shikai Fang

Organizations: School of Mathematical Sciences, Ocean University of China · College of Information Science and Electronic Engineering, Zhejiang University · College of Energy Engineering, Zhejiang University

Abstract

Physics sensing in evolving environments requires reconstructing dense spatiotemporal fields from sparse observations while adapting where future observations should be collected. Existing reconstruction and sensor-placement methods have made substantial progress, but they typically rely on static sensing assumptions: they either use a single layout across all frames or optimize placements independently at each frame, which limits their ability to produce temporally coherent sensing trajectories. We introduce DyPSI, a dynamic physics sensing framework that formulates this problem as the joint generation of future fields and sensor trajectories conditioned on historical observations. DyPSI lifts discrete sensor coordinates into continuous Sensor Position Fields, encodes fields and sensing configurations with a shared Functional Tucker representation, and trains a joint diffusion model to generate future fields and sensing trajectories simultaneously in the resulting latent space. A Gaussian-process temporal kernel correlates the perturbation injected during diffusion training, biasing the denoiser toward temporally smooth recoveries, and we further provide an analysis linking the EDM training objective to a sequence-aggregated A-optimality criterion and a kernel-induced bound on discrete trajectory variation. Experiments on turbulent flow, GLORYS12 sea-surface temperature, and 3D car aerodynamics show that DyPSI consistently outperforms static and frame-wise placement strategies, with substantial error reduction under tight sensor budgets. The code is available at https://github.com/mengqi132/DyPSI.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Flow Field Reconstruction via Voronoi-Enhanced Physics-Informed Neural Networks with End-to-End Sensor Placement Optimization

    Mar 10, 2026Renjie Xiao, Bingteng Sun, Yiling Chen +3Computational Fluid DynamicsPhysics-Informed ML

  2. TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured Sensing

    Aug 26, 2026Xinyu Zhang, Lihao Chen, Panqi Chen +4Conditional Generative ModelingBayesian Inverse Problems