Pseudo-Physics-Informed Neural Operators: Enhancing Operator Learning from Limited Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Keyan, Li, Yile, Long, Da, Xu, Zhitong, Xing, Wei, Hochhalter, Jacob, Zhe, Shandian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910010691289088
author Chen, Keyan
Li, Yile
Long, Da
Xu, Zhitong
Xing, Wei
Hochhalter, Jacob
Zhe, Shandian
author_facet Chen, Keyan
Li, Yile
Long, Da
Xu, Zhitong
Xing, Wei
Hochhalter, Jacob
Zhe, Shandian
contents Neural operators have shown great potential in surrogate modeling. However, training a well-performing neural operator typically requires a substantial amount of data, which can pose a major challenge in complex applications. In such scenarios, detailed physical knowledge can be unavailable or difficult to obtain, and collecting extensive data is often prohibitively expensive. To mitigate this challenge, we propose the Pseudo Physics-Informed Neural Operator (PPI-NO) framework. PPI-NO constructs a surrogate physics system for the target system using partial differential equations (PDEs) derived from simple, rudimentary physics principles, such as basic differential operators. This surrogate system is coupled with a neural operator model, using an alternating update and learning process to iteratively enhance the model's predictive power. While the physics derived via PPI-NO may not mirror the ground-truth underlying physical laws -- hence the term ``pseudo physics'' -- this approach significantly improves the accuracy of standard operator learning models in data-scarce scenarios, which is evidenced by extensive evaluations across five benchmark tasks and a fatigue modeling application.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02682
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pseudo-Physics-Informed Neural Operators: Enhancing Operator Learning from Limited Data
Chen, Keyan
Li, Yile
Long, Da
Xu, Zhitong
Xing, Wei
Hochhalter, Jacob
Zhe, Shandian
Machine Learning
Computational Physics
Neural operators have shown great potential in surrogate modeling. However, training a well-performing neural operator typically requires a substantial amount of data, which can pose a major challenge in complex applications. In such scenarios, detailed physical knowledge can be unavailable or difficult to obtain, and collecting extensive data is often prohibitively expensive. To mitigate this challenge, we propose the Pseudo Physics-Informed Neural Operator (PPI-NO) framework. PPI-NO constructs a surrogate physics system for the target system using partial differential equations (PDEs) derived from simple, rudimentary physics principles, such as basic differential operators. This surrogate system is coupled with a neural operator model, using an alternating update and learning process to iteratively enhance the model's predictive power. While the physics derived via PPI-NO may not mirror the ground-truth underlying physical laws -- hence the term ``pseudo physics'' -- this approach significantly improves the accuracy of standard operator learning models in data-scarce scenarios, which is evidenced by extensive evaluations across five benchmark tasks and a fatigue modeling application.
title Pseudo-Physics-Informed Neural Operators: Enhancing Operator Learning from Limited Data
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2502.02682