Dakota 6.10

Released: May 15, 2019
Release Highlights:

  • Evaluation data (variables and responses) may now be output to disk in HDF5 format. HDF5 support has been added to all of our downloads. See the Dakota HDF5 Output section of the Reference Manual for full details.
  • Capabilities for multilevel polynomial chaos expansion (ML PCE) and stochastic collocation (MC SC) have been expanded and hardened to improve their efficiency, completeness, and accuracy.

Dakota 6.9

Released: November 15, 2018
Release Highlights:

  • Dakota can now output method results to HDF5
  • Dakota's graphical user interface (GUI) was updated with several new features including the Dakota Study Wizard.
  • Bayesian calibration capabilities received several enhancments, including model evidence calculation with Monte Carlo sampling and 2nd-order local Laplace approximation

Dakota 6.8

Released: May 15, 2018
Release Highlights:

  • dprepro was completely re-written and has many new features, including the ability to execute arbitrary Python scripting in templates
  • Dakota's graphical user interface (GUI) was updated with many new features and bugfixes
  • Dakota now includes a suite of gradient-based optimization algorithms from the SNL-developed Rapid Optimization Library (ROL).
  • Bayesian calibration capabilities received several enhancements, including improved concurrency in evaluating optimal experimental designs

Dakota 6.7

Released: November 15, 2017
Release Highlights:

  • Graphical user interface improvements including support for a number of additional visualization types, and more...
  • Substantial improvements to multi-level and multi-fidelity methods, including greater flexbility in model hierarchies, and more...
  • Dakota now requires a C++11-compliant compiler, together with CMake 3.1 or newer (recommend 3.6 or greater).

Dakota in SIAM News

The following Dakota article appeared in SIAM News in April 2017:

Dakota 6.6

Released: May 12, 2017
Release Highlights:

  • Plotly Plotting Integration.
  • Generalize multifidelity surrogate-based local optimization to recur across multiple model fidelities, instead of just two.

Sandia Research Magazine

A "Looking Back" article in the February 2016 Sandia Research Magazine (see last page) refle

Dakota 6.5

Released: November 15, 2016
Release Highlights:

More Training Videos Available

New videos for Sensitivity Analysis, Optimization, Calibration, Uncertainty Quantification, Surrogate Models, and Parallelism have been added!

Training Videos Available

The Dakota team is excited to announce the release of introductory Dakota training via streaming video.

Dakota team members contribute UQ expertise to predictions of sea-level rise

Dakota 6.3

Released: November 16, 2015
Release Highlights:

Dakota 6.2

Released: May 15, 2015
Release Highlights:

Dakota 6.1

Released: November 15, 2014
Release Highlights:

Dakota's New Website

Thank you for visiting Dakota's new website! Features of the new website include: