Salvato in:
Dettagli Bibliografici
Autori principali: Wei, Zhao, Ooi, Chin Chun, Wong, Jian Cheng, Gupta, Abhishek, Chiu, Pao-Hsiung, Ong, Yew-Soon
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.19091
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908790781116416
author Wei, Zhao
Ooi, Chin Chun
Wong, Jian Cheng
Gupta, Abhishek
Chiu, Pao-Hsiung
Ong, Yew-Soon
author_facet Wei, Zhao
Ooi, Chin Chun
Wong, Jian Cheng
Gupta, Abhishek
Chiu, Pao-Hsiung
Ong, Yew-Soon
contents 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 generalization beyond their training support limits exploration of novel designs and long-time horizon predictions. We introduce NOVA, a route to generalizable neural physics solvers that can provide rapid, accurate solutions to scenarios even under distributional shifts in partial differential equation parameters, geometries and initial conditions. By learning physics-aligned representations from an initial sparse set of scenarios, NOVA consistently achieves 1-2 orders of magnitude lower out-of-distribution errors than data-driven baselines across complex, nonlinear problems including heat transfer, diffusion-reaction and fluid flow. We further showcase NOVA's dual impact on stabilizing long-time dynamical rollouts and improving generative design through application to the simulation of nonlinear Turing systems and fluidic chip optimization. Unlike neural physics solvers that are constrained to retrieval and/or emulation within an a priori space, NOVA enables reliable extrapolation beyond known regimes, a key capability given the need for exploration of novel hypothesis spaces in scientific discovery
format Preprint
id arxiv_https___arxiv_org_abs_2601_19091
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Out-of-Distribution Generalization for Neural Physics Solvers
Wei, Zhao
Ooi, Chin Chun
Wong, Jian Cheng
Gupta, Abhishek
Chiu, Pao-Hsiung
Ong, Yew-Soon
Machine Learning
Artificial Intelligence
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 generalization beyond their training support limits exploration of novel designs and long-time horizon predictions. We introduce NOVA, a route to generalizable neural physics solvers that can provide rapid, accurate solutions to scenarios even under distributional shifts in partial differential equation parameters, geometries and initial conditions. By learning physics-aligned representations from an initial sparse set of scenarios, NOVA consistently achieves 1-2 orders of magnitude lower out-of-distribution errors than data-driven baselines across complex, nonlinear problems including heat transfer, diffusion-reaction and fluid flow. We further showcase NOVA's dual impact on stabilizing long-time dynamical rollouts and improving generative design through application to the simulation of nonlinear Turing systems and fluidic chip optimization. Unlike neural physics solvers that are constrained to retrieval and/or emulation within an a priori space, NOVA enables reliable extrapolation beyond known regimes, a key capability given the need for exploration of novel hypothesis spaces in scientific discovery
title Out-of-Distribution Generalization for Neural Physics Solvers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.19091