Identification of partial differential equations from noisy data with integrated knowledge discovery and embedding using evolutionary neural networks
Open Access
- 12 March 2024
- journal article
- research article
- Published by Elsevier in Theoretical and Applied Mechanics Letters
- Vol. 14 (2)
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (92152102)
- National Natural Science Foundation of China (92152202)
- National Natural Science Foundation of China (HKCX2022-01-010)
This publication has 20 references indexed in Scilit:
- Machine learning of partial differential equations from noise dataTheoretical and Applied Mechanics Letters, 2023
- Data-driven discovery of the governing equations of dynamical systems via moving horizon optimizationScientific Reports, 2022
- Data-driven and physical-based identification of partial differential equations for multivariable systemTheoretical and Applied Mechanics Letters, 2022
- Deep-learning based discovery of partial differential equations in integral form from sparse and noisy dataJournal of Computational Physics, 2021
- Physics-informed learning of governing equations from scarce dataNature Communications, 2021
- DeepMoD: Deep learning for model discovery in noisy dataJournal of Computational Physics, 2021
- DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithmJournal of Computational Physics, 2020
- PDE-Net 2.0: Learning PDEs from data with a numeric-symbolic hybrid deep networkJournal of Computational Physics, 2019
- Hidden physics models: Machine learning of nonlinear partial differential equationsJournal of Computational Physics, 2018
- A novel evolutionary algorithm applied to algebraic modifications of the RANS stress–strain relationshipJournal of Computational Physics, 2016