MetaNO: how to transfer your knowledge on learning hidden physics

DOI10.1016/J.CMA.2023.116280arXiv2301.12095OpenAlexW4385335847WikidataQ130547266 ScholiaQ130547266MaRDI QIDQ6187622FDOQ6187622

Authors: Lu Zhang, Huaiqian You, Tian Gao, Mo Yu, Chung-Hao Lee, Yue Yu 

Publication date: 15 January 2024

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Abstract: Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification. Recently, PDE-solving deep learning methods, such as neural operators, are starting to make an important impact on learning and predicting the response of a complex physical system directly from observational data. Since the data acquisition in this context is commonly challenging and costly, the call of utilization and transfer of existing knowledge to new and unseen physical systems is even more acute. Herein, we propose a novel meta-learning approach for neural operators, which can be seen as transferring the knowledge of solution operators between governing (unknown) PDEs with varying parameter fields. Our approach is a provably universal solution operator for multiple PDE solving tasks, with a key theoretical observation that underlying parameter fields can be captured in the first layer of neural operator models, in contrast to typical final-layer transfer in existing meta-learning methods. As applications, we demonstrate the efficacy of our proposed approach on PDE-based datasets and a real-world material modeling problem, illustrating that our method can handle complex and nonlinear physical response learning tasks while greatly improving the sampling efficiency in unseen tasks.

Full work available at URL: https://arxiv.org/abs/2301.12095

zbMATH Keywords

transfer learningmeta-learningscientific machine learningneural operatorsoperator-regression neural networksdata-driven physics modeling

Mathematics Subject Classification ID

Partial differential equations (35-XX) Computer science (68-XX)

Cites Work

• Fast simulation of Gaussian random fields
• A new constitutive framework for arterial wall mechanics and a comparative study of material models
• Title not available (Why is that?)
• Interfacing finite elements with deep neural operators for fast multiscale modeling of mechanics problems
• Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling
• Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network
• Isogeometric analysis-based physics-informed graph neural network for studying traffic jam in neurons

This page was built for publication: MetaNO: how to transfer your knowledge on learning hidden physics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6187622)