Transfer learning based multi-fidelity physics informed deep neural network

2020/05/31 by Souvik Chakraborty · 233 citations
Computer Science · Decision Sciences · Engineering · Mathematics · Physics and Astronomy · #Algorithm #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Computer science #Deep learning #Fidelity #Field (mathematics) #High fidelity #Machine learning #Mathematics #Model Reduction and Neural Networks #Non-Destructive Testing Techniques #Physics #Probabilistic and Robust Engineering Design #Theoretical computer science #Transfer of learning #cs.LG #physics.comp-ph #stat.ML

paper · pdf · doi:10.1016/j.jcp.2020.109942

published in Journal of Computational Physics 426, 109942 (Elsevier BV)

arxiv created 2020/06/14 · openalex publication_date 2020/10/22 · arxiv updated 2021/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

For many systems in science and engineering, the governing differential equation is either not known or known in an approximate sense. Analyses and design of such systems are governed by data collected from the field and/or laboratory experiments. This challenging scenario is further worsened when data-collection is expensive and time-consuming. To address this issue, this paper presents a novel multi-fidelity physics informed deep neural network (MF-PIDNN). The framework proposed is particularly suitable when the physics of the problem is known in an approximate sense (low-fidelity physics) and only a few high-fidelity data are available. MF-PIDNN blends physics informed and data-driven deep learning techniques by using the concept of transfer learning. The approximate governing equation is first used to train a low-fidelity physics informed deep neural network. This is followed by transfer learning where the low-fidelity model is updated by using the available high-fidelity data. MF-PIDNN is able to encode useful information on the physics of the problem from the \it approximate governing differential equation and hence, provides accurate prediction even in zones with no data. Additionally, no low-fidelity data is required for training this model. Applicability and utility of MF-PIDNN are illustrated in solving four benchmark reliability analysis problems. Case studies to illustrate interesting features of the proposed approach are also presented.

Citations

• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems

Cited by

• Multifidelity deep operator networks for data-driven and physics-informed problems
• Convolutional-neural-operator-based transfer learning for solving PDEs
• Bridging quantum and classical computing for partial differential equations through multifidelity machine learning
• Enforcing hidden physics in physics-informed neural networks
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks
• A transfer learning metamodel using artificial neural networks applied to natural convection flows in enclosures
• Multi-level datasets training method in Physics-Informed Neural Networks
• Benchmarking Multi-fidelity Neural Operators on Complex PDE Problems with Non-trivial Fidelity Differences
• Constructing Physics-Informed Neural Networks with Architecture Based on Analytical Modification of Numerical Methods by Solving the Problem of Modelling Processes in a Chemical Reactor. [europepmc]
• Graph Laplacian-based spectral multi-fidelity modeling. [europepmc]
• Machine learning (ML)-assisted surface tension and oscillation-induced elastic modulus studies of oxide-coated liquid metal (LM) alloys. [europepmc]
• SANS-CNN: An automated machine learning technique for spaceflight associated neuro-ocular syndrome with astronaut imaging data. [europepmc]
• Fast adaptation of physics-informed hybrid models for pneumatic artificial muscles. [europepmc]