paper-with-me

홈 › Papers

Ambient Physics: Training Neural PDE Solvers with Partial Observations

2026-02-14 · Harris Abdul Majid, Giannis Daras, Francesco Tudisco, Steven McDonagh arxiv

In many scientific settings, acquiring complete observations of PDE coefficients and solutions can be expensive, hazardous, or impossible. Recent diffusion-based methods can reconstruct fields given partial observations, but require complete observations for training. We introduce Ambient Physics, a framework for learning the joint distribution of coefficient-solution pairs directly from partial observations, without requiring a single complete observation. The key idea is to randomly mask a subset of already-observed measurements and supervise on them, so the model cannot distinguish "truly unobserved" from "artificially unobserved", and must produce plausible predictions everywhere. Ambient Physics achieves state-of-the-art reconstruction performance. Compared with prior diffusion-based methods, it achieves a 62.51$\%$ reduction in average overall error while using 125$\times$ fewer function evaluations. We also identify a "one-point transition": masking a single already-observed point enables learning from partial observations across architectures and measurement patterns. Ambient Physics thus enables scientific progress in settings where complete observations are unavailable.

📄 PDF Abstract BibTeX arXiv:2602.13873

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Physics-informed diffusion models in spectral space

2026-02-10 · Davide Gallon, Philippe von Wurstemberger, Patrick Cheridito, Arnulf Jentzen arxiv

We propose physics-informed spectral diffusion (PISD), a methodology that combines generative latent diffusion models with physics-informed machine learning to generate solutions of partial differential equations (PDEs) …

Dimensionality ReductionComputational Efficiency

Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers

2025-05-20 · Nima Hosseini Dashtbayaz, Hesam Salehipour, Adrian Butscher, Nigel Morris

Reduced-order modeling (ROM) of time-dependent and parameterized differential equations aims to accelerate the simulation of complex high-dimensional systems by learning a compact latent manifold representation that capt…

Robust Parameter and State Estimation in Multiscale Neuronal Systems Using Physics-Informed Neural Networks

2026-02-27 · Changliang Wei, Yangyang Wang, Xueyu Zhu arxiv

Inferring biophysical parameters and hidden state variables from partial and noisy observations is a fundamental challenge in computational neuroscience. This problem is particularly difficult for fast - slow spiking and…

Out-of-Distribution Generalization for Neural Physics Solvers

2026-01-27 · Zhao Wei, Chin Chun Ooi, Jian Cheng Wong, Abhishek Gupta 외 arxiv

Neural physics solvers are increasingly used in scientific discovery, given their potential for rapid in silico insights into physical, materials, or biological systems and their long-time evolution. However, poor genera…

Text2PDE: Latent Diffusion Models for Accessible Physics Simulation

2024-10-02 · Anthony Zhou, Zijie Li, Michael Schneier, John R Buchanan Jr 외

Recent advances in deep learning have inspired numerous works on data-driven solutions to partial differential equation (PDE) problems. These neural PDE solvers can often be much faster than their numerical counterparts;…