FLUID: A Neural Operator-Based Framework for Learning Multi-Fidelity of Unstructured Data
- 19 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (6) , 4731-4741
Abstract
With increasing computational power, scientists often employ high-fidelity simulations to study complex scientific phenomena. However, these simulations remain slow and costly in terms of computation and storage, prompting the use of faster low-fidelity alternatives. Yet, the distribution gap between low- and high-fidelity data, due to missing fine-scale details and simplified physics, hampers accurate scientific understanding. To overcome these challenges, we propose a neural operator-based framework for multi-fidelity prediction on unstructured data. Our framework leverages a graph neural operator to effectively map low-fidelity data to the high-fidelity counterparts. It further incorporates a spectral-based module that captures fine-scale details, enhancing the reconstruction of high-fidelity fields. Extensive experiments across diverse datasets demonstrate that our method consistently surpasses strong baselines, including state-of-the-art neural operators and learning methods for unstructured data, highlighting its robustness and effectiveness in bridging fidelity gaps.Keywords
Funding Information
- US Department of Energy SciDAC (DE-SC0021360)
- US Department of Energy SciDAC (DE-SC0023193)
- National Science Foundation Division of Information and Intelligent Systems (IIS-1955764)
- Los Alamos National Laboratory Contract (C3435)
- Brookhaven National Laboratory
- Office of Science (DE-SC0012704)
- Office of Science (FWP No. CC122)
This publication has 34 references indexed in Scilit:
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud2020
- Dedalus: A flexible framework for numerical simulations with spectral methodsPhysical Review Research, 2020
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks2016
- A multi-resolution approach to global ocean modelingOcean Modelling, 2013
- Computing non-equilibrium turbulent flows with time-dependent rans and vles2007
- Super-resolution through neighbor embedding2004
- Turbulent FlowsMeasurement Science and Technology, 2001
- Enlargement or reduction of digital images with minimum loss of informationIEEE Transactions on Image Processing, 1995
- Adaptive mesh refinement for hyperbolic partial differential equationsJournal of Computational Physics, 1984