Enhancing PINN Performance Through Lie Symmetry Group

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shah, Ali Haider, Butt, Naveed R., Ahmad, Asif, Saeed, Muhammad Omer Bin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912617835003904
author Shah, Ali Haider
Butt, Naveed R.
Ahmad, Asif
Saeed, Muhammad Omer Bin
author_facet Shah, Ali Haider
Butt, Naveed R.
Ahmad, Asif
Saeed, Muhammad Omer Bin
contents This paper presents intersection of Physics informed neural networks (PINNs) and Lie symmetry group to enhance the accuracy and efficiency of solving partial differential equation (PDEs). Various methods have been developed to solve these equations. A Lie group is an efficient method that can lead to exact solutions for the PDEs that possessing Lie Symmetry. Leveraging the concept of infinitesimal generators from Lie symmetry group in a novel manner within PINN leads to significant improvements in solution of PDEs. In this study three distinct cases are discussed, each showing progressive improvements achieved through Lie symmetry modifications and adaptive techniques. State-of-the-art numerical methods are adopted for comparing the progressive PINN models. Numerical experiments demonstrate the key role of Lie symmetry in enhancing PINNs performance, emphasizing the importance of integrating abstract mathematical concepts into deep learning for addressing complex scientific problems adequately.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing PINN Performance Through Lie Symmetry Group
Shah, Ali Haider
Butt, Naveed R.
Ahmad, Asif
Saeed, Muhammad Omer Bin
Analysis of PDEs
Artificial Intelligence
This paper presents intersection of Physics informed neural networks (PINNs) and Lie symmetry group to enhance the accuracy and efficiency of solving partial differential equation (PDEs). Various methods have been developed to solve these equations. A Lie group is an efficient method that can lead to exact solutions for the PDEs that possessing Lie Symmetry. Leveraging the concept of infinitesimal generators from Lie symmetry group in a novel manner within PINN leads to significant improvements in solution of PDEs. In this study three distinct cases are discussed, each showing progressive improvements achieved through Lie symmetry modifications and adaptive techniques. State-of-the-art numerical methods are adopted for comparing the progressive PINN models. Numerical experiments demonstrate the key role of Lie symmetry in enhancing PINNs performance, emphasizing the importance of integrating abstract mathematical concepts into deep learning for addressing complex scientific problems adequately.
title Enhancing PINN Performance Through Lie Symmetry Group
topic Analysis of PDEs
Artificial Intelligence
url https://arxiv.org/abs/2509.26113