"Make uncertainty quantification available for anybody,
in any field of applied science and engineering"
The general uncertainty quantification framework underlying UQLab
Easily plug-in your computational models via an intuitive API
The HPC dispatcher provides a user-friendly interface between users' personal computer to common HPC resources to conveniently offload and retrieve the results of expensive UQLab computations
The general uncertainty quantification framework underlying UQLab
-
MATLAB®-based Uncertainty Quantification framework
-
State-of-the art, highly optimized open source algorithms
-
Fast learning curve for beginners
-
Modular structure, easy to extend
-
Exhaustive documentation
In a nutshell
UQLab is a general purpose Uncertainty Quantification framework developed at ETH Zurich (Switzerland). It is made of open-source scientific modules which are smoothly connected to perform uncertainty quantification through Monte Carlo simulation, sensitivity analysis, reliability analysis (computation of rare event probabilities), surrogate models (polynomial chaos expansions, Kriging, etc.), Bayesian inversion/calibration and many more.
Since version 2.0, UQLab is released open source under the BSD-3 clause license ➜
News
-
23rd February 2026: UQLab 2.2 is now available! This release introduces a dedicated Benchmarking ➜ module to rigorously test and compare different surrogate modeling techniques. It also ships with numerous performance improvements and bug fixes (Release Notes ➜)
Log in ➜ to download the latest version!
-
13th May 2024: After a long incubation, UQLab Version 2.1.0 is released! This major update comprises a long list of new features, as well as performance improvements and bugfixes. Check out the Release Notes ➜ for more information!
UQLab is developed at the Chair of Risk, Safety and Uncertainty Quantification of ETH Zurich under the supervision of Prof. B. Sudret and Dr. S. Marelli.
MATLAB® is a registered trademark of The MathWorks, Inc.