Center for Computing Research (CCR)

Center for Computing Research

Optimization & Uncertainty Quantification, 01463

The Optimization and Uncertainty Quantification (UQ) Department's mission is to provide leadership in the research, development, and application of scientific optimization and UQ algorithms and software, in support of Sandia's many mission areas. The department produces several open-source, scientific software packages including Dakota and ROL (Rapid Optimization Library).

People

Daniel Z. Turner
Manager, Optimization & Uncertainty Quantification
Email: dzturne@sandia.gov
Phone: 505/845-7446
Fax: 505/845-7442

Mailing address:
Sandia National Laboratories
P.O. Box 5800, MS 1323
Albuquerque, NM
87185-1320
Celia Montoya, Office Administrative Assistant
Staff
Brian M. Adams
Robert John Baraldi
Kelsey DiPietro
Michael S. Eldred
Gianluca Geraci
Joseph Lee Hart
Russell Hooper
John Davis Jakeman
Aurya Serafini Javeed
Drew Philip Kouri
Kathryn Anne Maupin
Shane Alexander McQuarrie
Diana Marcela Morales
Zachary Benjamin Morrow
Teresa Portone
William Mcneil Reese
Bryan William Reuter
Denis Ridzal
Ahmad Rushdi
Daniel Thomas Seidl (Tom)
John Adam Stephens
Isaac Paul Sunseri
Laura Painton Swiler
Anh Tran
Bart G van Bloemen Waanders (Bart G.)
Gregory John von Winckel
Rebekah Dale White
Timothy Michael Wildey
Nickolas Winovich
Tian Yu Yen

News

  • Credibility in Scientific Machine Learning: Data Verification and Model Qualification

    The Advanced Simulation and Computing (ASC) initiative on Advanced Machine Learning (AML) aims to maximize near and long-term impact of Artificial Intelligence (AI) and Machine Learning (ML) technologies on Sandia’s Nuclear Deterrence (ND) program....

    Credibility in Scientific Machine Learning: Data Verification and Model Qualification

    The Advanced Simulation and Computing (ASC) initiative on Advanced Machine Learning (AML) aims to maximize near and long-term impact of Artificial Intelligence (AI) and Machine Learning (ML) technologies on Sandia’s Nuclear Deterrence (ND) program. In this ASC-AML funded project, the team is developing new approaches for assessing the quality of machine learning predictions based on expensive/limited experimental data, with focus on problems in the nuclear deterrence (ND) mission domain. Guided by the classical Predictive Capability Maturity Model (PCMM) workflow for Verification, Validation, and Uncertainty Quantification (V&V/UQ), the project aims to rigorously assess the statistical properties of the input features when training a Scientific Machine Learning (SciML) model and examine the associated sources of noise, e.g., measurement noise. This will, in turn, enable the decomposition of output uncertainty into unavoidable aleatory part versus reducible model-form uncertainty. To improve Sandia’s stockpile surveillance analysis capabilities, the team uses signature waveforms collected using non-destructive functioning and identify the most-discriminative input features, in order to assess the quality of a training dataset. By further decomposing uncertainty into its aleatoric and epistemic components, the team will guide computational/sampling resources towards reducing the treatable parts of uncertainty. This workflow will enhance the overall credibility of the resulting predictions and open new doors for SciML models to be credibly deployed to costly or high stakes ND problems.

    Workflow illustration of a machine learning classifier, trained on labeled time- or frequency-domain signals in order to classify new measurements, with uncertainty metrics.

    Contact: Rushdi, Ahmad
    June 2021
    2021-7207 S

UNCLASSIFIED UNLIMITED RELEASE DOCUMENTS ONLY