Modeling, AI, and Optimization for Engineering Design
We develop methods for simulation-based design optimization, dimensionality reduction, surrogate modeling, and machine learning for complex engineering systems, with applications in marine, aerospace, and multidisciplinary vehicle design.
About¶
The MAO Research Group works on advanced computational methods for engineering design, with a focus on:
- simulation-based design optimization
- dimensionality reduction for shape optimization
- physics-informed and multi-fidelity surrogate models
- machine learning for marine and aerospace applications
- reproducible computational workflows and open scientific software
Research Areas¶
Dimensionality Reduction
Reduced-order representations of high-dimensional design spaces, including PME and its physics-informed variants.
Simulation-Based Design Optimization
Optimization frameworks for expensive engineering simulations, including multi-objective and many-fidelity settings.
Scientific Machine Learning
Integration of machine learning with physical models for design exploration, prediction, and interpretability.
Marine and Aerospace Applications
Applications to ships, propellers, underwater vehicles, airfoils, and advanced transportation systems.
Featured Resources¶
Projects
Ongoing and past research projects, collaborations, and funded activities.
Software
Open and in-development research software supporting reproducible computational design workflows.
Datasets
Research datasets for dimensionality reduction, optimization, and computational benchmarking. Available via our Zenodo collection.
Publications
Selected journal articles, conference papers, and software-related outputs.
Highlights¶
Note
This website is documentation-oriented by design: lightweight, maintainable, and directly connected to the group’s research outputs, software, and datasets.
News¶
You can use this section for brief updates such as:
- new papers
- released software
- open positions
- conference sessions
- funded projects