Skip to content
Preprint

Physical-Field Reconstruction from Sparse Observations: When Are Diffusion Models Preferable to Deterministic Regression?

Sep 2026 · 0 citations · 44 references
Physics

Abstract

Reconstructing physical fields from sparse observations is central to system identification, forecasting, and control, yet sparse measurements generally underdetermine the full field. This makes reconstruction an ill-posed inverse problem rather than simple interpolation. Although many deterministic and generative methods have been developed, there is still no clear consensus on when a single point estimate is sufficient and when a distribution of plausible reconstructions is more useful. We conduct a fair comparison of a deterministic U-Net, conditional diffusion, and prior-guided diffusion under matched experimental settings, including 2D Poisson equation, 2D Navier-Stokes flow, and 1D Kuramoto-Sivashinsky dynamics. Through this comparison, we make three observations. First, accuracy is field- and regime-dependent, with no systematic advantage for diffusion under higher complexity or sparser observations. Second, ensemble means improve phase-aligned accuracy, whereas individual samples better preserve variability and can retain high-wavenumber power in selected regimes. Third, conditional diffusion provides more reliable uncertainty estimates at lower cost, while prior-guided diffusion is more robust to mask-distribution shifts but requires substantially higher inference cost and guidance tuning. These results clarify when generative reconstruction is useful and provide guidance for improving uncertainty estimation, fine-scale sample fidelity, robustness, and computational efficiency in sparse field reconstruction.

View source

Similar papers

Sep 2026

Full-Field Reconstruction from Sparse Observations Using Multiscale Gaussian Kernel and Factorized Fourier Neural Operators

Reconstructing high-dimensional physical fields from sparse observations is a central challenge in subsurface monitoring, where dense measurements are often impractical or unavailable. Existing approaches typically require dense full-state supervision, limiting their applicability when only sparse measurements are av...

R. Wibawa, B. Jha · 0 citations
Preprint Oct 2026

PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements

PhysDEM is the first physics-defined diffusion model enabling amortized spatiotemporal field inference without preassembled full-field datasets, and is described as the first physics-defined diffusion model enabling amortized spatiotemporal field inference without preassembled full-field datasets.

Zhen-Yu Liang, Ying Huang, Yu-Bo Zhao et al. · 0 citations

Physical-State-Guided Diffusion Sampling for Full-Waveform Inversion

Full waveform inversion (FWI) reconstructs subsurface velocity models from seismic mea surements but faces the challenges of ill-posedness and nonlinearity, making accurate inversion dependent on suitable initialization and effective prior constraints. Classical methods stabi lize the inversion and improve convergence...

Chen Min, Hao-Wen Jiang, Zheng Ma et al. · 0 citations
Preprint Aug 2026

Learning dynamically consistent flow reconstructions from limited observations

Trajectory-Consistent Network Training (TraCTra), a label-free framework that trains reconstruction networks using only partial observation sequences and a differentiable forward model, establishes trajectory consistency as a general supervision principle for reconstructing hidden dynamical states without full state tr...

Lu Zhu, Jacob Page · 1 citation
Aug 2026

A Physics-Informed Multi-Scale Diffusion Model Framework for Physical Field Imputation from Randomly Missing Data

Non-intrusive optical measurement techniques are widely used to obtain high-resolution pressure, temperature, and velocity fields, but they often suffer from random data loss caused by geometric obstruction, surface reflection, or illumination non-uniformity. Conventional reconstruction methods usually depend on high...

Bo Yu, Pingting Chen, JunKui Mao · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.