MADS

MADS is an integrated high-performance/cloud-computing framework for data/model/decision analyses.
MADS can be coupled with any existing numerical model or simulator, including machine learning algorithms and models.
MADS can be applied to perform:
- Parameter Estimation
- Model Inversion and Calibration
- Model Selection and Averaging
- Model Reduction and Surrogate Modeling
- Sensitivity Analysis
- Uncertainty Quantification
- Risk Assessment
- Decision Analysis and Support
MADS analyses utilize adaptive rules and techniques which allow the analyses to be performed efficiently with minimum user input.
Start here
- Stable docs (recommended for most users)
- Development docs
- Getting Started
- Example Problems
- Notebooks
Getting help
- GitHub Discussions (questions, support)
- GitHub Issues (bugs, feature requests)
- Support email: <a class="js-obfuscated-email" data-u="support" data-d="envitrace.com" href="#" rel="nofollow">support [at] envitrace [dot] com</a>
Developers
Primary developer:
- Velimir ("monty") Vesselinov
- Emails: velimir.vesselinov@gmail.com, monty@envitrace.com
- GitHub: github.com/montyvesselinov
- LinkedIn: linkedin.com/in/montyvesselinov
- ORCID: 0000-0002-6222-0530
- Google Scholar: Profile
- YouTube: Channel