A clean two-way dissociation is found: the physics residual is a reliable, backbone-robust trust signal, but a poor correction objective (it does not tell you how to fix it), and a split-conformal layer, which depends only on predictions and σ attains target coverage.
Plasolver, a physics-informed neural operator framework that combines the efficiency of operator learning with the accuracy and robustness of classical numerical solvers, provides an efficient, accurate, and discretization-invariant computational framework for nonlinear, path-dependent elastoplastic problems.
Yi-Zheng Wang, M. Eshaghi, Hua-Dong Zhang et al.· 0 citations
This work presents NeuralFlowNet, a data-free, physics-informed proof-of-concept framework designed to solve steady Navier-Stokes problems across low- to high-Reynolds-number conditions, and establishes NeuralFlowNet as a reliable framework for future testing of unsteady and more complex simulations.
Jayanga T. Samarasinghe, Luis A. de la Fuente, Laura V. Alvarez· 0 citations
In many computational science and engineering problems, repeatedly solving fully resolved physics-based models to design for a quantity of interest (QoI) can quickly become intractable, requiring the use of low-fidelity models to predict the same QoI but introduce errors where some features are neglected or are otherwi...
Wesley Lao, Thomas Scott, T. Bui-Thanh et al.· 0 citations
It is concluded that aligning data-driven methods with physical constraints—and the training objective with deployment—is the path toward reliable, generalizable, and computationally efficient turbulence models for engineering applications.
Jia-Hao Hu, Jun-Ya Yang· The Physics of Fluids· 0 citations
Neural surrogate models for Partial Differential Equations (PDEs) on unstructured 3D geometries are often limited by poor generalization and the high cost of generating large-scale training datasets. Consequently, pre-training on massive datasets of related PDE dynamics has emerged as a critical alternative to enhance...
Luis Medrano-Navarro, G. Baldan, Qiang Liu et al.· 0 citations
Neural operators are typically trained in a supervised fashion, which requires a dataset to be generated with a classical solver. Training them physics-informed, i.e., purely from the governing equations, removes this large offline cost and allows fresh samples to be drawn at every optimization step, but has so far bee...
Shi-Zheng Wen, Siddhartha Mishra, Marius Zeinhofer· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
