Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge

Dohyun Bu; Chanho Kim; Seokun Choi; Jong-Seok Lee

cs.LGMar 20, 2026

Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge

Authors: Dohyun Bu, Chanho Kim, Seokun Choi, Jong-Seok Lee

Organizations: Department of Industrial & Systems Engineering, KAIST, Daejeon, Repulic of Korea · Department of Mathematical Sciences, KAIST, Daejeon, Repulic of Korea

Abstract

Data assimilation (DA) for systems governed by partial differential equations (PDE) aims to reconstruct full spatiotemporal fields from sparse high-fidelity (HF) observations while respecting physical constraints. While full-grid low-fidelity (LF) simulations provide informative priors in multi-fidelity settings, recovering an HF field consistent with both sparse observations and the governing PDE typically requires per-instance test-time optimization, which becomes a major bottleneck in time-critical applications. To alleviate this, amortized reconstruction using generative models has recently been proposed; however, such approaches rely on full-field HF supervision during training, which is often impractical in real-world settings. From a more realistic perspective, we propose the Physics-Informed Conditional Schrödinger Bridge (PICSB), which transports an informative LF prior toward an observation-conditioned HF posterior without any additional inference-time guidance. To enable learning without HF endpoints, PICSB employs an iterative surrogate-endpoint refresh scheme, and directly incorporates PDE residuals into the training objective while enforcing observations via hard conditioning throughout sampling. Experiments on fluid PDE benchmarks demonstrate that PICSB enables extremely fast spatiotemporal field reconstruction while maintaining competitive accuracy under sparse HF supervision.

Figures & tables

Method	Zero-shot	DA	Label-Efficient	Guidance-free
PINNs ( Raissi et al., 2019 )	✗	✓	✓	✓
MMGN ( Luo et al., 2024 )	✗	✓	✓	✗
FNO, NOICL ( Li et al., 2021 ; Chen et al., 2024 )	✓	✗	✗	✗
P 2 INN ( Cho et al., 2024 )	✓	✗	✓	✓
DiffusionPDE, ECI, PCFM	✓	✓	✗	✗
( Huang et al., 2024 ; Cheng et al., 2025 ; Utkarsh et al., 2025 )	✓	✓	✗	✗

Table 1: Comparison of learning-based field reconstruction methods for PDE-governed systems. Zero-shot indicates amortized reconstruction without test-time re-optimization. DA indicates the capability to solve an observation-conditioned inverse problem using sparse HF observations. Label-Efficient indicates training under sparse HF supervision, where HF targets are available only at partial spatiotemporal locations. Guidance-free indicates that PDE residuals are incorporated directly into training, avoiding inference-time correction.

Figure 1: Overview of PICSB training with sparse supervision. The static model (parameters $\tilde{\theta}$ ) provides surrogate endpoints to construct the bridge reference, while the trainable sampler (parameters $\theta$ ) is updated by minimizing the physics residual under hard observation projection at every sampling step. Here, with refresh period $C\!=\!20$ , iteration $73$ uses a static model last refreshed at iteration $60$ .

Figure 2: Qualitative comparison of reconstructed fields under ( R3 ). For Burgers and Darcy flow, a single test sample is shown. For Kolmogorov, a snapshot at $\gamma=0.64$ from the time horizon $\gamma\in(0,1.25]$ is visualized. LF, sparse HF observations (obs.), PINNs, Guidance, and PICSB are compared against the HF reference (ref.). Zoomed-in regions highlight local reconstruction quality.

PDE	Task	PINNs	Guidance	PICSB
Burgers	R1	8.29	0.99	2.59
	R2	13.48	19.04	14.05
	R3	11.79	10.66	14.25
Darcy	R1	5.69	12.02	0.29
Darcy	R3	5.64	27.39	0.28
Kolmogorov	R1	64.47	8.99	7.32

Table 2: Relative reconstruction error (in %) on the test set, reported as

\mathrm{RelError}

in Eq. ( 15 ) under each observation regime ( R1 – R3 ). All values are averaged over the four test instances per PDE benchmark. For each task, the best-performing method is underlined , and the overall best result within each PDE benchmark is highlighted in bold .

PDE	PINNs	Guidance	PICSB
Burgers	1733	174	0.023
Darcy	2682	173	0.023
Kolmogorov	10680	801	0.134

Table 3: Average wall-time (seconds) for inference under ( R3 ).

Appendix figures & tables28 assets

Supplementary material from the paper’s appendix.

Appendix

PDE	Enc. ch.	Dec. ch.	#Enc.	#Dec.	Kernel	$d_{\mathrm{cond}}$	Bridge-time steps	$\epsilon$	LR	Train iters.
Burgers	$128,256$	$256,128$	2	2	$3\times 3$	8	10	$10^{-2}$	$10^{-3}$	100k
Darcy	$128,256$	$256,128$	2	2	$3\times 3$	8	10	$10^{-2}$	$10^{-6}$	100k
Kolmogorov	$128,256$	$256,128$	2	2	$3\times 3$	8	10	$10^{-2}$	$10^{-3}$	100k

Appendix

Table 4: PICSB architectural and training hyperparameters used for each PDE benchmark. All benchmarks share the same network architecture and training schedule, except for the input/output channel dimensionality and learning rate. The table summarizes the key structural and optimization-related hyperparameters that define the PICSB model.

PDE	Hidden dim	Depth	$N_{\mathrm{colloc}}$	$\lambda_{\mathrm{obs}}$	$\lambda_{\mathrm{phys}}$	LR	Epochs	Extra settings
Burgers	512	6	8192	1.0	1.0	$10^{-3}$	100k	–
Darcy	512	6	8192	1.0	1.0	$10^{-3}$	100k	$\lambda_{\mathrm{bc}}{=}1,\;N_{\mathrm{bc}}{=}2048$ , grad clip (1e-5)
Kolmogorov	256	4	8192	1.0	1.0	$10^{-3}$	100k	–

Appendix

Table 5: PINNs architectural and optimization hyperparameters used for each PDE benchmark. The table summarizes the key structural and optimization-related hyperparameters that define the PINNs baseline, with Darcy-specific stabilization settings reported in the last column.

PDE	Sampling steps	$\sigma_{\min}$	$\sigma_{\max}$	$\rho$	$\lambda_{\mathrm{obs}}$	$\lambda_{\mathrm{phys}}$	$\lambda_{\mathrm{bc}}$
Burgers	2000	0.002	80	7	320	100	–
Darcy	2000	0.002	80	7	$10^{-3}$	$10^{-1}$	$10^{-1}$
Kolmogorov	2000	0.002	80	7	$3.2\times 10^{6}$	1000	–

Appendix

Table 6: Guidance-based sampling hyperparameters used for each PDE benchmark. All benchmarks use the same noise schedule parameters

(\sigma_{\min},\sigma_{\max},\rho)

and the same number of sampling iterations. Observation and PDE guidance are applied in a stage-wise manner, while Darcy additionally employs boundary guidance with separate step sizes.

Figure 3: Additional visualization illustrating reconstruction performance for Burgers’ equation. Each row corresponds to a different test sample. Columns show the sparse HF observations used for conditioning (obs.), the LF input, reconstructions obtained under different reconstruction regimes (R1–R3), and the HF reference solution (ref.). Relative reconstruction errors are reported below each reconstructed field.

Figure 4: Additional visualization illustrating reconstruction performance for Darcy flow. Each row corresponds to a different test sample. Columns show the sparse HF observations used for conditioning (obs.), the LF input, reconstructions obtained under different reconstruction regimes (R1–R3), and the HF reference solution (ref.). Relative reconstruction errors are reported below each reconstructed field.

Figure 5: Additional visualization illustrating reconstruction performance for Kolmogorov flow at frame 1. Each row corresponds to a different test sample. Columns show the sparse HF observations used for conditioning (obs.), the LF input, reconstructions obtained under different reconstruction regimes (R1–R3), and the HF reference solution (ref.). Relative reconstruction errors are reported below each reconstructed field.

Figure 6: Additional visualization illustrating reconstruction performance for Kolmogorov flow at frame 20. Each row corresponds to a different test sample. Columns show the sparse HF observations used for conditioning (obs.), the LF input constructed from sparse observations via interpolation, reconstructions obtained under different reconstruction regimes (R1–R3), and the HF reference solution (ref.). Relative reconstruction errors are reported below each reconstructed field.

Figure 7: Additional visualization illustrating reconstruction performance for Kolmogorov flow at frame 38. Each row corresponds to a different test sample. Columns show the sparse HF observations used for conditioning (obs.), the LF input constructed from sparse observations via interpolation, reconstructions obtained under different reconstruction regimes (R1–R3), and the HF reference solution (ref.). Relative reconstruction errors are reported below each reconstructed field.

Figure 8: Inference dynamics comparison between PICSB and guidance-based sampling for Burgers’ equation.

Figure 9: Inference dynamics comparison between PICSB and guidance-based sampling for Darcy flow.

Figure 10: Inference dynamics comparison between PICSB and guidance-based sampling for Kolmogorov flow at frame 20.

Figure 11: Reconstruction results under $5\%$ sparse observations for the Burgers’ equation.

Figure 12: Reconstruction results under $1\%$ sparse observations for the Burgers’ equation.

Figure 13: Inference under noisy observations for Burgers’ equation with randomly resampled sensors (R1). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 14: Inference under noisy observations for Burgers’ equation with per-sample fixed sensors (R2). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 15: Inference under noisy observations for Burgers’ equation with a fixed sensor set (R3). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 16: Inference under noisy observations for Darcy flow with randomly resampled sensors (R1). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 17: Inference under noisy observations for Darcy flow with a fixed sensor set (R3). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 18: Inference under noisy sparse observations for Kolmogorov flow with randomly resampled sensors (R1). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 19: Inference under noisy observations for Kolmogorov flow with per-sample fixed sensors (R2). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 20: Inference under noisy observations for Kolmogorov flow with a fixed sensor set (R3). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 21: Inference under noisy observations for Kolmogorov flow with a fixed sensor set (R3). Each row corresponds to a different test sample, and each column corresponds to a noise level, with the HF reference solution shown in the rightmost column. Relative reconstruction errors are reported below each predicted field.

Figure 22: Finetuning and inference results under $1\%$ sparse observations for the Burgers’ equation with integrated finetuning.

Figure 23: Finetuning and inference results under $1\%$ sparse observations for Darcy flow with integrated finetuning.

Figure 24: Finetuning and inference results under $1\%$ sparse observations for the Kolmogorov flow with integrated finetuning.

Figure 25: Finetuning and inference results under $5\%$ sparse observations for the Burgers’ equation with integrated finetuning.

Figure 26: Finetuning and inference results under $5\%$ sparse observations for Darcy flow with integrated finetuning.

Figure 27: Finetuning and inference results under $5\%$ sparse observations for the Kolmogorov flow with integrated finetuning.

Explore similar work

SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
Oct 9, 2026Jaehyeon Park, Inhyeok Jeong, Noseong ParkPDE Operator Learning PDE Surrogate Modeling
SolverX · KAIST
PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements
Oct 1, 2026Zhenyu Liang, Yining Huang, Yubo Zhao +1Physics-Informed Diffusion Models Physics-Informed Generative Modeling
HKUST · UT Austin
SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference
Sep 29, 2026Ruichen Xu, Siyao Wang, Fang Wan +8PDE Surrogate Modeling PDE Inverse Problems
Stony Brook University · University of California, Davis · Independent Research +3

Oct 9, 2026J/K move · Enter open · S save

SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information

Jaehyeon Park, Inhyeok Jeong, Noseong Park

SolverX · KAIST

PDE Operator Learning PDE Surrogate Modeling PDE Inverse Problems Learning with Missing Data Schrödinger Bridges

Open paper AskPDF arXiv

Partial differential equation (PDE) surrogate modeling often relies on either dense observations or access to governing equations/physics constraints. In practice, observations can be sparse and partial, and the underlying physics may be partially specified or unavailable. We introduce SBNO, an equation-free paired-data diffusion bridge matching framework that learns conditional operators for both forward and inverse PDE problems under partial observations. SBNO uses diffusion Schrödinger bridge matching to learn a pair of time-dependent drifts from a mask-aware endpoint coupling that preserves empirical input-solution pairing during training and supports both PDE-task directions within a single framework. At inference time, SBNO produces a deterministic point reconstruction by integrating the probability-flow ODE constructed from the learned drift pair, without inference-time observation or PDE guidance-weight tuning. On five PDE benchmarks with 5% observations, SBNO achieves superior or comparable accuracy to baselines while demonstrating lower test-instance error dispersion. Furthermore, SBNO is at least

9.7 \times

faster and reduces GPU memory by at least

4.3 \times

compared to guided-diffusion baselines.

Abstract

Explore similar work

SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information

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

SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference