Skip to content
Open-source constructor of surrogates and metamodels
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
bin
doc
lib
LICENSE.md
README.md

README.md

Consumet: constructor of surrogates and metamodels

This is a tool for creating surrogate models from a user-provided black box, via penalized regression methods and adaptive sampling. It uses the same sampling algorithm as the proprietary black-box modeling tool Alamo, i.e. error-maximization sampling with derivative-free optimization. However, in constrast to e.g. Alamo, Consumet and all of its dependencies are completely free. In other words, you can use it for any purpose without having to purchase any license.

Please see the user manual for more information; this includes a reference to a scientific paper that contains more details about the algorithms behind our software implementation.

The surrogate modeling tool is available as free and open-source software under the MIT license. This is a permissive license that permits you to use the software for any purpose, as long as you just give credit where appropriate. However, outside of any legal obligations, the authors at SINTEF Energy Research kindly request that any useful modifications you make to the code be contributed back to us, so we can improve the tool over time.

Most of the code was developed by SINTEF Energy Research as part of the ELEGANCY project. The exception is src/sobol.py; this is also covered by an MIT license, and the authors are listed in the source.

You can’t perform that action at this time.