Efficient learning of accurate surrogates for simulations of complex systems
Publication Date
5-1-2024
Document Type
Article
Publication Title
Nature Machine Intelligence
Volume
6
Issue
5
DOI
10.1038/s42256-024-00839-1
First Page
568
Last Page
577
Abstract
Machine learning methods are increasingly deployed to construct surrogate models for complex physical systems at a reduced computational cost. However, the predictive capability of these surrogates degrades in the presence of noisy, sparse or dynamic data. We introduce an online learning method empowered by optimizer-driven sampling that has two advantages over current approaches: it ensures that all local extrema (including endpoints) of the model response surface are included in the training data, and it employs a continuous validation and update process in which surrogates undergo retraining when their performance falls below a validity threshold. We find, using benchmark functions, that optimizer-directed sampling generally outperforms traditional sampling methods in terms of accuracy around local extrema even when the scoring metric is biased towards assessing overall accuracy. Finally, the application to dense nuclear matter demonstrates that highly accurate surrogates for a nuclear equation-of-state model can be reliably autogenerated from expensive calculations using few model evaluations.
Funding Number
20190005DR
Funding Sponsor
Los Alamos National Laboratory
Department
Mathematics and Statistics
Recommended Citation
A. Diaw, M. McKerns, I. Sagert, L. G. Stanton, and M. S. Murillo. "Efficient learning of accurate surrogates for simulations of complex systems" Nature Machine Intelligence (2024): 568-577. https://doi.org/10.1038/s42256-024-00839-1
