Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.22338 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913152553189376 |
|---|---|
| author | Zhu, Ziyuan Hu, Keyu Chen, Zhifei Shi, Yuhao Bao, Ming Zhao, Jing Wang, Gang Xu, Haitan Li, Jiadong Zhao, Qijun Li, Xiaodong Lu, Minghui Chen, Yanfeng |
| author_facet | Zhu, Ziyuan Hu, Keyu Chen, Zhifei Shi, Yuhao Bao, Ming Zhao, Jing Wang, Gang Xu, Haitan Li, Jiadong Zhao, Qijun Li, Xiaodong Lu, Minghui Chen, Yanfeng |
| contents | Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states that violate governing dynamics. We introduce a physics-informed generative solver that separates stable prior learning from inference-time enforcement of conservation laws. Martingale-Regularized Score Matching regularizes score pretraining with a Score Fokker-Planck constraint, yielding a dynamically stable prior. Physics-Informed Implicit Score Sampling then guides denoising trajectories by gradients of physical residuals, projecting samples toward admissible manifolds without retraining. In acoustics, the method co-generates pressure and particle velocity from sparse sensors, enabling dense virtual arrays that suppress spatial aliasing. The same framework generalizes to real-world ERA5 meteorological fields under extreme sparsity. Together, this work establishes a rigorous and generalizable paradigm for solving high-dimensional inverse problems, bridging the gap between generative artificial intelligence and first-principles science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22338 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction Zhu, Ziyuan Hu, Keyu Chen, Zhifei Shi, Yuhao Bao, Ming Zhao, Jing Wang, Gang Xu, Haitan Li, Jiadong Zhao, Qijun Li, Xiaodong Lu, Minghui Chen, Yanfeng Machine Learning Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states that violate governing dynamics. We introduce a physics-informed generative solver that separates stable prior learning from inference-time enforcement of conservation laws. Martingale-Regularized Score Matching regularizes score pretraining with a Score Fokker-Planck constraint, yielding a dynamically stable prior. Physics-Informed Implicit Score Sampling then guides denoising trajectories by gradients of physical residuals, projecting samples toward admissible manifolds without retraining. In acoustics, the method co-generates pressure and particle velocity from sparse sensors, enabling dense virtual arrays that suppress spatial aliasing. The same framework generalizes to real-world ERA5 meteorological fields under extreme sparsity. Together, this work establishes a rigorous and generalizable paradigm for solving high-dimensional inverse problems, bridging the gap between generative artificial intelligence and first-principles science. |
| title | Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.22338 |