A principled distance-aware uncertainty quantification approach for enhancing the reliability of physics-informed neural network
Lists
Only you see this
Abstract
Highlights•Develop a principled approach to estimate model uncertainty of physics-informed neural network (PINN).•Define performance measures tailored to PINN when evaluating the quality of estimated uncertainty.•The proposed method outperforms Monte Carlo dropout in detecting PINN's prediction failure.
BibTeX
@article{li2024principled,
author = {Jinwu Li and Xiangyun Long and Xinyang Deng and Wen Jiang and Kai Zhou and Chao Jiang and Xiaoge Zhang},
title = {{A principled distance-aware uncertainty quantification approach for enhancing the reliability of physics-informed neural network}},
journal = {Reliab. Eng. Syst. Saf.},
year = {2024},
doi = {10.1016/j.ress.2024.109963},
}Loading related content...