Scientific Machine Learning (SciML) is an emerging area in computational science that investigates the synergistic integration of scientific computing and machine learning, with the goal of combining the strengths and compensating the weaknesses of both. In particular, SciML aims to (i) use numerical models for the improvement of established machine learning techniques, (ii) use data-driven machine learning techniques to assist numerical simulations, and (iii) create new efficient, reliable, and robust methodologies by employing aspects from both approaches. The SciML research in the MIA group focuses on:
- Data-driven discovery of reduced-state dynamics through manifold learning;
- Data-driven modeling using Gaussian processes and Bayesian neural networks;
- Uncertainty quantification for physics-informed deep learning;
- Physics-informed geometric deep learning;
- Computational foundation of digital twin technologies; and
- ……
People working on this subject within SACS are:
Staff:
PhD
