Building & investing in technology & healthcare businesses

My basket (no items)

You are not signed in.

Sign-in

- DESCRIPTION
- FILES (0)
- REFERENCES (0)
- SUPPORT

- Page 1
- Page 2

**Academic users can download SobolGSA free of charge via the following link: www.imperial.ac.uk/process-systems-engineering/research/free-software/sobolgsa-software/**

**Commercial users can licence the latest version of SobolGSA by emailing quicktech@imperialinnovations.co.uk. Price is on application. **

** **

**Description **

High complexity models are commonly used in physics, chemistry, bioengineering, environmental studies, finance, statistics and other fields. Models with a large number of variables require significant time and computational power to produce outputs. However, in practice, some of these variables will have little impact on the model outputs. A metamodel treats these variables as constants, which reduces the amount of time and computing effort to produce outputs that are very similar to the full model. Global sensitivity analysis (GSA) is a method of analysing the effect of a variable on the outputs of a model in order to construct a metamodel.

SobolGSA is a user-friendly software application that can conduct global sensitivy analyses and construct metamodels. It can:

- Be applied to both static and time-dependent problems
- Handle several outputs for analysis - these can be time-dependent
- Construct metamodels either from explicitly known models or directly from data produced by "black-box" models
- Output metamodels as C# or MATLAB files (SobolGSA can be linked to MATLAB)
- Deploy three different metamodeling techniques, including Quasi Random Sampling-High dimensional model representation (QRS-HDMR) and Radial Basis Function (RBF)
- Deploy several GSA measures including Sobol indices, FAST, Morris and derivative-based measures
- Allow users to save both settings as well as results

SobolGSA has over 300 users worldwide

**Screenshots**

SobolGSA can run a number of different analyses and models

SobolGSA can model multiple outputs

Sensitivity analysis can return the first order effect of multiple inputs

Metamodels can be easily compared to original models

Next page ►

High complexity of models in physics, chemistry, bioengineering, environmental studies, finance, statistics and other fields results in the increased uncertainty in model parameters and model structures. Uncertainty in the model parameters is introduced because parameters are not perfectly known, they are originated from noisy measurements or expert judgement, or because they have an intrinsic variability. Uncertainty in input parameters is reflected in uncertainty of model outputs and predictions. Uncertainty analysis has been recognized as an essential part of model applications. Sensitivity analysis (SA) aims at quantifying the relative importance of each input parameter in determining the value of model output. Global SA (GSA) estimates the effect of varying a given input (or set of inputs) while all other inputs are varied as well, thus providing a measure of interactions among them. GSA is used to identify key inputs whose uncertainty most affects the output and the results are used to rank inputs, fix unessential inputs and decrease problem dimensionality. Over the last decade GSA has gained acceptance among practitioners in the process of model development, calibration and validation, reliability and robustness analysis, decision-making under uncertainty, quality-assurance, and complexity reduction.

For computationally expensive models and models which need to be run repeatedly on-line the replacement of complex models by equivalent operational metamodels (also known as surrogate models) is a practical way of making computations tractable. Such an approach is also invaluable in cases when the model is not given explicitly but it exists only in a form of input- output maps or is given as a “black box”. Another advantage of using metamodeling methods is that they can provide the values of GSA measures for “free” that is without the need of extra model runs. One of the important applications of metamodels is optimization of complex processes. Optimization can be very demanding from a computational point of view, while metamodels can provide an accurate representation of the detailed and costly objective functions and/or set of constraints. Metamodel based optimization results in a significant reduction of the computational time.

SobolGSA is general purpose GUI driven global sensitivity analysis and metamodeling software. It can be used to compute various sensitivity measures and to develop metamodels. SobolGSA can be applied to both static and time-dependent problems. It can handle several outputs for analysis; each output can be time-dependent. SobolGSA can be used to construct metamodels either from explicitly known models or directly from data produced by "black-box" models. Developed metamodels are produced in a form of self-contained MATLAB or C# files which can be used as accurate, reliable and very fast surrogates of the computationally expensive full scale models. A set of available global sensitivity analysis techniques includes various screening and SA methods. All techniques implemented in SobolGSA make use of the very efficient sampling methods based pn Sobol’ sequences. The software has a user friendly interface for inputs and presenting results. SobolGSA can be linked to MATLAB and other packages. Software includes detailed manuals, case studies and a set of test problems with descriptions for benchmarking and training.

Since its introduction a few years ago SobolGSA became very popular among practitioners with the number of users reaching 300 worldwide.

- Kucherenko S. SobolHDMR: a general-purpose modeling software Methods Mol Biol. (2013) 1073:191-224. doi: 10.1007/978-1-62703-625-2_16
- Feil B., Kucherenko S., Shah N. Comparison of Monte Carlo and Quasi Monte Carlo Sampling Methods in High Dimensional Model Representation, SIMUL 2009, Porto, Portugal.
- Zuniga M., Kucherenko S., Shah N. Metamodelling with independent and dependent inputs, Computer Physics Communications, 184, 6 (2013) 1570-1580.
- Sobol’ I., Kucherenko S. Global Sensitivity Indices for Nonlinear Mathematical Models. Review, Wilmott, 1 (2005) 56-61.
- Kucherenko S., Feil B., Shah N., Mauntz W. The identification of model effective dimensions using global sensitivity analysis Reliability Engineering and System Safety 96 (2011) 440–449.
- Kucherenko S., Tarantola S., Annoni P. Estimation of global sensitivity indices for models with dependent variables, Computer Physics Communications, 183 (2012) 937–946.
- Kucherenko S., Rodriguez-Fernandez M., Pantelides C., Shah N. Monte Carlo evaluation of derivative based global sensitivity measures. Reliability Engineering and System Safety 94, 7 (2009) 1135-1148.
- Sobol’ I.M., Kucherenko S. Derivative based Global Sensitivity Measures and their link with global sensitivity indices, Mathematics and Computers in Simulation, 79, 10 (2009) 3009-3017.
- Sobol’ I.M., Asotsky D., Kreinin A., Kucherenko S. Construction and Comparison of High-Dimensional Sobol’ Generators, 2011, Wilmott Journal (2012) 64-79.
- Kucherenko S., Albrecht D., Saltelli A. Exploring multi-dimensional spaces: a Comparison of Latin Hypercube and Quasi Monte Carlo Sampling Techniques, to be published in Reliability Engineering and System Safety, 2016 arXiv:1505.02350.

There are no files uploaded for this item.

There are no references for this product.

There are no support topics defined for this product.

CONTACT SUPPORT

Close X

E-lucid has transformed into two separate sites.

UCLB’s platform for licensing technology from across UCL has become XIP (the site you’re on).

E-lucid has become the home for the platform that powers XIP and similar sites for other universities.

CONTINUE BROWSING XIP

FIND OUT MORE ABOUT E-LUCID
Contact us · F.A.Q. · Standard Terms of Use · Privacy Policy · Cookies Policy

2017 © Imperial Innovations · All Rights Reserved

Imperial Innovations

Registered Office: 52 Princes Gate, London, SW7 2PG, United Kingdom

Registered in England and Wales No. 5796766 VAT Registration Number: 100190776