ATHENA - Python library for Advanced Techniques for High dimensional parameter spaces to Enhance Numerical Analysis
ATHENA is a Python package for reduction of high dimensional parameter spaces in the context of numerical analysis.
ATHENA allows the use of several dimensionality reduction techniques in the parameter space such as Active Subspaces (AS), Kernel-based Active Subspaces (KAS), and Nonlinear Level-set Learning (NLL). It is particularly suited for the study of parametric PDEs, for sensitivity analysis and uncertainty quantification, and for the approximation of engineering quantities of interest with the design of response surfaces. It can handle both scalar and vectorial high dimensional functions, making it useful as a tool to reduce the burden of computational intensive optimization tasks and as a preprocessing step before heavy parametric dependent CFD simulations.
The research in the field is growing towards nonlinear dimension reduction techniques in the context of scientific machine learning and also towards inverse problems and statistical inference in the context of uncertainty quantification and probabilistic modeling.
ATHENA is freely available under the MIT License.
- Download the source code at github.com
- Explore the tutorials
- Check the GitHub page to see how to cite it and the last works made possible by the package
ATHENA is currently developed and maintained at SISSA mathLab by
under the supervision of Prof. Gianluigi Rozza.
Contact us by email for further information or questions about ATHENA, or suggest pull requests.
