Active learning for adaptive surrogate model improvement in high-dimensional problems
Open Access
- 10 July 2024
- journal article
- research article
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 67 (7) , 1-26
Abstract
This paper investigates a novel approach to efficiently construct and improve surrogate models in problems with high-dimensional input and output. In this approach, the principal components and corresponding features of the high-dimensional output are first identified. For each feature, the active subspace technique is used to identify a corresponding low-dimensional subspace of the input domain; then a surrogate model is built for each feature in its corresponding active subspace. A low-dimensional adaptive learning strategy is proposed to identify training samples to improve the surrogate model. In contrast to existing adaptive learning methods that focus on a scalar output or a small number of outputs, this paper addresses adaptive learning with high-dimensional input and output, with a novel learning function that balances exploration and exploitation, i.e., considering unexplored regions and high-error regions, respectively. The adaptive learning is in terms of the active variables in the low-dimensional space, and the newly added training samples can be easily mapped back to the original space for running the expensive physics model. The proposed method is demonstrated for the numerical simulation of an additive manufacturing part, with a high-dimensional field output quantity of interest (residual stress) in the component that has spatial variability due to the stochastic nature of multiple input variables (including process variables and material properties). Various factors in the adaptive learning process are investigated, including the number of training samples, range and distribution of the adaptive training samples, contributions of various errors, and the importance of exploration versus exploitation in the learning function.Keywords
Funding Information
- National Institute of Standards and Technology (70NANB22H181)
This publication has 73 references indexed in Scilit:
- Adaptive surrogate modeling for high-dimensional spatio-temporal outputStructural and Multidisciplinary Optimization, 2022
- A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering designStructural and Multidisciplinary Optimization, 2017
- Global sensitivity analysis-enhanced surrogate (GSAS) modeling for reliability analysisStructural and Multidisciplinary Optimization, 2015
- A priori testing of sparse adaptive polynomial chaos expansions using an ocean general circulation model databaseComputational Geosciences, 2013
- Active learning for spectroscopic data regressionJournal of Chemometrics, 2012
- Investigation of an adaptive sampling method for data interpolation using radial basis functionsInternational Journal for Numerical Methods in Engineering, 2010
- An accumulative error based adaptive design of experiments for offline metamodelingStructural and Multidisciplinary Optimization, 2009
- Gaussian Process Regression: Active Data Selection and Test Point Rejection2000
- Support-vector networksMachine Learning, 1995
- Estimation using spatially distributed multivariate data: An example with coal qualityMathematical Geology, 1983