Search NASA⌕ Search
Home/Archive/NASA NTRS

NASA NTRS · 20140012999

Bayesian Statistics and Uncertainty Quantification for Safety Boundary Analysis in Complex Systems

He, Yuning·Davies, Misty Dawn
View original source ↗Export metadata ↓

Abstract

The analysis of a safety-critical system often requires detailed knowledge of safe regions and their highdimensional non-linear boundaries. We present a statistical approach to iteratively detect and characterize the boundaries, which are provided as parameterized shape candidates. Using methods from uncertainty quantification and active learning, we incrementally construct a statistical model from only few simulation runs and obtain statistically sound estimates of the shape parameters for safety boundaries.

Explore related subjects

Active LearningBayesian StatisticsSafety Boundary

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

He, Yuning, Davies, Misty Dawn. 2014-08-29. Bayesian Statistics and Uncertainty Quantification for Safety Boundary Analysis in Complex Systems. https://ntrs.nasa.gov/citations/20140012999

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2025

Atomic Energy Accuracy of Neural Network Potentials: Harnessing Pretraining and Transfer Learning

Machine learning-based interatomic potentials (MLIPs) have transformed the prediction of potential energy surfaces (PESs), achieving accuracy comparable to ab initio calculations. However, atomic energy predictions, often assumed to lack physical meaning, remain underexplored. In this study, we demonstrate that inaccuracies in atomic energy predictions reduce the robustness and transferability of Neural Network Potentials (NNPs) and atomic energy error can be masked in total energy predictions due to error cancellation. Here, we validate this finding using challenging configurations involving deformation and failure under tensile loading. By pretraining atomic energy predictions using empirical potentials and applying transfer learning with density functional theory (DFT) data, we achieve notable improvements in the accuracy of total energy, forces, and stress predictions. Furthermore, this approach enhances the robustness and transferability of NNPs, emphasizing the importance of atomic energy predictions in developing high-quality and reliable MLIPs.

Active Learning↗