APIK: Active Physics-Informed Kriging Model with Partial Differential Equations
From MaRDI portal
Abstract: Kriging (or Gaussian process regression) is a popular machine learning method for its flexibility and closed-form prediction expressions. However, one of the key challenges in applying kriging to engineering systems is that the available measurement data is scarce due to the measurement limitations and high sensing costs. On the other hand, physical knowledge of the engineering system is often available and represented in the form of partial differential equations (PDEs). We present in this work a PDE Informed Kriging model (PIK), which introduces PDE information via a set of PDE points and conducts posterior prediction similar to the standard kriging method. The proposed PIK model can incorporate physical knowledge from both linear and nonlinear PDEs. To further improve learning performance, we propose an Active PIK framework (APIK) that designs PDE points to leverage the PDE information based on the PIK model and measurement data. The selected PDE points not only explore the whole input space but also exploit the locations where the PDE information is critical in reducing predictive uncertainty. Finally, an expectation-maximization algorithm is developed for parameter estimation. We demonstrate the effectiveness of APIK in two synthetic examples, a shock wave case study, and a laser heating case study.
Recommendations
- Physics information aided kriging using stochastic simulation models
- Physics-informed cokriging: a Gaussian-process-regression-based multifidelity method for data-model convergence
- Physics-Based Kriging Surrogates for a Class of Finite Element Codes
- Active subspace methods in theory and practice: applications to kriging surfaces
- A data-driven kernel method assimilation technique for geophysical modelling
- Stochastic intrinsic Kriging for simulation metamodeling
- Gradient Extrapolated Stochastic Kriging
- Generalized polynomial chaos-informed efficient stochastic kriging
Cites work
- scientific article; zbMATH DE number 5822909 (Why is no real title available?)
- scientific article; zbMATH DE number 2152342 (Why is no real title available?)
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- A unifying view of sparse approximate Gaussian process regression
- An efficient surrogate model for emulation and physics extraction of large eddy simulations
- Approximation of Bayesian Inverse Problems for PDEs
- Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systems
- Computational Methods for Inverse Problems
- Computer Experiments: Prediction Accuracy, Sample Size and Model Complexity Revisited
- Data Assimilation
- Design and analysis of computer experiments. With comments and a rejoinder by the authors
- Ensemble-marginalized Kalman filter for linear time-dependent PDEs with noisy boundary conditions: application to heat transfer in building walls
- Estimating shape constrained functions using Gaussian processes
- Exploratory designs for computational experiments
- Gaussian process modeling with inequality constraints
- Gaussian process regression constrained by boundary value problems
- Gaussian processes for machine learning.
- High dimensional kriging metamodelling utilising gradient information
- High-dimensional ODEs coupled with mixed-effects modeling techniques for dynamic gene regulatory network identification
- Inverse problems for partial differential equations
- Machine Learning of Space-Fractional Differential Equations
- Machine learning of linear differential equations using Gaussian processes
- Maximum projection designs for computer experiments
- Mechanistic hierarchical Gaussian processes
- Minimax and Minimax Projection Designs Using Clustering
- Model-Based Geostatistics
- Numerical Gaussian processes for time-dependent and nonlinear partial differential equations
- On arbitrage and replication in the fractional Black–Scholes pricing model
- On the distribution of points in a cube and the approximate evaluation of integrals
- On the instability issue of gradient-enhanced Gaussian process emulators for computer experiments
- On the limited memory BFGS method for large scale optimization
- Output-Weighted Optimal Sampling for Bayesian Experimental Design and Uncertainty Quantification
- Output-weighted optimal sampling for Bayesian regression and rare event statistics using few samples
- Sequential Monte Carlo methods for high-dimensional inverse problems: a case study for the Navier-Stokes equations
- Sieve estimation of constant and time-varying coefficients in nonlinear ordinary differential equation models by considering both numerical error and measurement error
- Strictly Proper Scoring Rules, Prediction, and Estimation
- The Geometry of Random Fields
- The design and analysis of computer experiments
- The ensemble Kalman filter for combined state and parameter estimation
- Theory of elasticity and thermal stresses. Explanations, problems and solutions
Cited in
(6)- Physics-informed cokriging: a Gaussian-process-regression-based multifidelity method for data-model convergence
- Stochastic PDE representation of random fields for large-scale Gaussian process regression and statistical finite element analysis
- Augmenting a Simulation Campaign for Hybrid Computer Model and Field Data Experiments
- Parameter inference based on Gaussian processes informed by nonlinear partial differential equations
- Physics information aided kriging using stochastic simulation models
- Traffic prediction by combining macroscopic models and Gaussian processes
This page was built for publication: APIK: Active Physics-Informed Kriging Model with Partial Differential Equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5075236)
