Scientific Machine Learning
Research Interests
- Scientific Machine learning
- Data driven models, System identification, Neural and deep learning for physics-informed applications.
- Numerical methods for forward and inverse problems
- Ensemble learning, Bayesian inference, and Numerical optimization methods with applied for model order reduction, PDE-Constrained optimization and inverse problems
- Quantitative Social science research
- Exploratory and explanatory data analysis for chronic disease prevention intervention
- Quantitative social research at the intersection of online learning and Gerontology
- Time-stepping methods for PDEs
- High-order time discretizations for multi-physics systems. Implicit-Explicit, variable time-stepping and error control strategies. Parallel and Jacobian-free methods Advanced methods for fluid simulations, DAEs and stiff problems
