AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Physics-Informed Functional Tucker Method with RKHS Factors for Sparse Spatiotemporal Reconstruction

Zhengyang Liu, Jianguo Huang, Junxi Hu, Yucheng Mi, Haojie Cai, Wenxuan Shen, zhikun zhang, Renfeng Peng, Guangtao Zhang, Zhiqiang Liu

NeurIPS 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Data assimilation from sparse observations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a physics-informed functional Tucker method with RKHS factors for reconstructing physical fields from sparse, irregular spatiotemporal observations.

Problem

Reconstructing physical dynamics from sparse and irregular spatiotemporal observations is ill-posed: models can fit sensors while producing nonphysical off-sensor structures or unreliable predictions between support times.

Approach

Combines a functional Tucker decomposition with reproducing kernel Hilbert space (RKHS) factor functions and physics-informed constraints to regularize the reconstruction away from sensors (based on the title and abstract; details not available).

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add PDE residual loss at collocation points (ablation)PhysFTM · NS2Doff-sensor RMSE: 0.086781 -> 0.061196Improved
add PDE residual loss (ablation)PhysFTM · AC2Doff-sensor RMSE: 0.092520 -> 0.089395Improved
add RKHS norm regularization (ablation)PhysFTM · NS2Doff-sensor RMSE: 0.115421 -> 0.061196Improved
alternate core solve with gradient factor learning vs solve-only (ablation)PhysFTM · AC2Doff-sensor RMSE: 0.173653 -> 0.089395Improved
alternate core solve with gradient factor learning vs gradient-only (ablation)PhysFTM · AC2Doff-sensor RMSE: 0.352132 -> 0.089395Improved
replace MLP mode factors with RKHS factors (ablation)FTM · AC2Doff-sensor RMSE support frames: 0.1026 -> 0.0925Improved
impose PDE residual at off-sensor collocation points rather than sensor or full-domain points (ablation)PhysFTM · AC2DRMSE: 0.0898 -> 0.0884Improved
add learned ODE-RNN correction to cubic Hermite interpolation of cores (ablation)PhysFTM · NS2D (s=0.03)non-grid-aligned RMSE: 0.063790 -> 0.055546Improved
PhysFTM instead of RecFNO on sensor locations in missing framesPhysFTM · AC2Dsensor RMSE missing frames: 0.02178 vs 0.05035Hurt
PhysFTM instead of LRTFR on Ocean3D interval-missingPhysFTM · Ocean3Doff-sensor RMSE missing frames: 0.18377 vs 0.18565Hurt
PhysFTM vs other methods on divergencePhysFTM · NS2Ddivergence error: 0.134170 vs PINNs 0.120243Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy