Saved in:
Bibliographic Details
Main Authors: Si, Chenhao, Yan, Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.03172
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917685216935936
author Si, Chenhao
Yan, Ming
author_facet Si, Chenhao
Yan, Ming
contents We propose a new physics-informed neural network framework, IDPINN, based on the enhancement of initialization and domain decomposition to improve prediction accuracy. We train a PINN using a small dataset to obtain an initial network structure, including the weighted matrix and bias, which initializes the PINN for each subdomain. Moreover, we leverage the smoothness condition on the interface to enhance the prediction performance. We numerically evaluated it on several forward problems and demonstrated the benefits of IDPINN in terms of accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03172
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Initialization-enhanced Physics-Informed Neural Network with Domain Decomposition (IDPINN)
Si, Chenhao
Yan, Ming
Machine Learning
We propose a new physics-informed neural network framework, IDPINN, based on the enhancement of initialization and domain decomposition to improve prediction accuracy. We train a PINN using a small dataset to obtain an initial network structure, including the weighted matrix and bias, which initializes the PINN for each subdomain. Moreover, we leverage the smoothness condition on the interface to enhance the prediction performance. We numerically evaluated it on several forward problems and demonstrated the benefits of IDPINN in terms of accuracy.
title Initialization-enhanced Physics-Informed Neural Network with Domain Decomposition (IDPINN)
topic Machine Learning
url https://arxiv.org/abs/2406.03172