Transfer learning based multi-fidelity physics informed deep neural network

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.

References in corpus (6)

• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• A Gaussian process latent force model for joint input-state estimation in linear structural systems
• Simulation free reliability analysis: A physics-informed deep learning based approach
• On transfer learning of neural networks using bi-fidelity data for uncertainty propagation
• Adaptive Multilevel Monte Carlo Approximation of Distribution Functions
• A Generalized Probabilistic Learning Approach for Multi-Fidelity Uncertainty Propagation in Complex Physical Simulations

Cited by in corpus (19)

• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• A novel meta-learning initialization method for physics-informed neural networks
• Multifidelity Deep Operator Networks For Data-Driven and Physics-Informed Problems
• In-Context Operator Learning with Data Prompts for Differential Equation Problems
• Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow
• Active Learning with Multifidelity Modeling for Efficient Rare Event Simulation
• Surrogate assisted active subspace and active subspace assisted surrogate -- A new paradigm for high dimensional structural reliability analysis
• Predicting drag on rough surfaces by transfer learning of empirical correlations
• Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
• A Latent Variable Approach for Non-Hierarchical Multi-Fidelity Adaptive Sampling
• Transfer Learning as a Method to Reproduce High-Fidelity NLTE Opacities in Simulations
• Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
• Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study
• A transfer learning metamodel using artificial neural networks applied to natural convection flows in enclosures
• Graph Laplacian-based Bayesian Multi-fidelity Modeling
• Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks
• Transfer Learning Approaches for Knowledge Discovery in Grid-based Geo-Spatiotemporal Data
• Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks