Current Focus of Our Research:
- Machine learning (ML) and artificial intelligence (AI)-empowered surrogate modeling for complex systems
- Probabilistic reduced order modeling for solid materials and extreme events
- Quantum algorithms for topology optimization and linear systems
- Data-driven coarse-grained modeling of soft matter
- Data-driven non-intrusive reduced order modeling for fluids, fluid-solid interactions, and multiphase flows
- High-fidelity simulations (enabled by high-order accurate numerical methods) for fluid-solid interactions
- Multiphysics modeling and simulations in manufacturing, energy storage, and thermal sciences
Computational tools developed by our group:
(https://github.com/Pan-Group-UW-Madison)
- Parallel, scalable code for graph neural network-based modeling of complex fluids (HIGNN)
- Codes for (quantum-accelerated) topology optimization with discrete variables
- Parallel, scalable code for high-fidelity simulations of fluid-solid interactions based on adaptive generalized moving least square (GMLS)