Sensitivity-driven adaptive construction of reduced-space surrogates
From MaRDI portal
Abstract: We develop a systematic approach for surrogate model construction in reduced input parameter spaces. A sparse set of model evaluations in the original input space is used to approximate derivative based global sensitivity measures (DGSMs) for individual uncertain inputs of the model. An iterative screening procedure is developed that exploits DGSM estimates in order to identify the unimportant inputs. The screening procedure forms an integral part of an overall framework for adaptive construction of a surrogate in the reduced space. The framework is tested for computational efficiency through an initial implementation in simple test cases such as the classic Borehole function, and a semilinear elliptic PDE with a random source term. The framework is then deployed for a realistic application from chemical kinetics, where we study the ignition delay in an H2/O2 reaction mechanism with 19 uncertain rate constants. It is observed that significant computational gains can be attained by constructing accurate low-dimensional surrogates using the proposed framework.
Recommendations
- Global sensitivity analysis based on high-dimensional sparse surrogate construction
- Surrogate-based modeling and dimension reduction techniques for multi-scale mechanics problems
- Dimensionality reduction for complex models via Bayesian compressive sensing
- Kriging-sparse polynomial dimensional decomposition surrogate model with adaptive refinement
- Structure exploiting methods for fast uncertainty quantification in multiphase flow through heterogeneous media
Cites work
- Advanced Lectures on Machine Learning
- Aerodynamic design via control theory
- Bayesian Design and Analysis of Computer Experiments: Use of Derivatives in Surface Prediction
- Computational optimization of systems governed by partial differential equations
- Derivative based global sensitivity measures and their link with global sensitivity indices
- Derivative-based global sensitivity measures: general links with Sobol' indices and numerical tests
- Evaluating Derivatives
- Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates
- scientific article; zbMATH DE number 49187 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 1425054 (Why is no real title available?)
- Least angle regression. (With discussion)
- Mean-variance risk-averse optimal control of systems governed by PDEs with random parameter fields using quadratic approximations
- Perspectives in Flow Control and Optimization
- Probabilistic modeling and global sensitivity analysis for CO\(_2\) storage in geological formations: a spectral approach
- Quantifying initial and wind forcing uncertainties in the gulf of Mexico
- Sparse polynomial chaos expansions and adaptive stochastic finite elements using a regression approach
- Spectral Methods for Uncertainty Quantification
- The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
Cited in
(9)- Goal-oriented adaptive surrogate construction for stochastic inversion
- On the merits of sparse surrogates for global sensitivity analysis of multi-scale nonlinear problems: application to turbulence and fire-spotting model in wildland fire simulators
- A distributed active subspace method for scalable surrogate modeling of function valued outputs
- Kriging-sparse polynomial dimensional decomposition surrogate model with adaptive refinement
- Dimensionality reduction for complex models via Bayesian compressive sensing
- Efficient localization of discontinuities in complex computational simulations
- Derivative-Based Global Sensitivity Analysis for Models with High-Dimensional Inputs and Functional Outputs
- An integrated surrogate model constructing method: annealing combinable Gaussian process
- Sensitivity-driven adaptive surrogate modeling for simulation and optimization of dynamical systems
This page was built for publication: Sensitivity-driven adaptive construction of reduced-space surrogates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2312009)
