Analysis of Neural Network Combustion Surrogate Models
- Sandia National Lab. (SNL-CA), Livermore, CA (United States)
This report details initial investigations of neural network surrogate models for combustion applications. The models are assessed with respect to averaged predictive fidelity over a test data set as well as with respect to the accuracy of resolving landmark statistics of interest, as a function of increasing training data volume.
- Research Organization:
- Sandia National Laboratories (SNL-CA), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- AC04-94AL85000; NA0003525
- OSTI ID:
- 1569154
- Report Number(s):
- SAND--2019-11283R; 679688
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Bayesian Multi-fidelity Neural Network to Predict Nonlinear Frequency Backbone Curves
A framework for strategic discovery of credible neural network surrogate models under uncertainty
Equipping Neural Network Surrogates with Uncertainty for Propagation in Physical Systems
Journal Article
·
Thu Jun 20 20:00:00 EDT 2024
· Journal of Verification, Validation and Uncertainty Quantification
·
OSTI ID:2317735
A framework for strategic discovery of credible neural network surrogate models under uncertainty
Journal Article
·
Tue May 21 20:00:00 EDT 2024
· Computer Methods in Applied Mechanics and Engineering
·
OSTI ID:2479027
Equipping Neural Network Surrogates with Uncertainty for Propagation in Physical Systems
Conference
·
Mon May 13 00:00:00 EDT 2024
·
OSTI ID:2352231