Paris Perdikaris, Massachusetts Institute of Technology
Host: Handy Zhang
Learning and optimization under uncertainty via probabilistic multi-fidelity modeling
The analysis of complex physical and biological systems necessitates the accurate resolution of interactions across multiple spatio-temporal scales, the consistent propagation of information between concurrently coupled multi-physics processes, and the effective quantification of model error and parametric uncertainty. Addressing these grand challenges is a multi-faceted problem that poses the need for a highly sophisticated arsenal of tools in stochastic modeling, high-performance scientific computing, and probabilistic machine learning. Through the lens of two realistic large-scale applications, this talk aims to demonstrate how the compositional synthesis of such tools is introducing a new paradigm in scientific discovery. We will demonstrate how the introduction of probabilistic machine learning techniques, and the key concept of multi-fidelity modeling, provide a scalable platform for information fusion and lead to significant computational expediency gains. The first application involves an environmental study that illustrates how machine learning tools enable the synergistic combination of simulations, noisy measurements and satellite images with the goal of quantifying the anthropogenic effect in the increasing acidification of coastal waters, and developing a cost-effective monitoring and prediction mechanism. The second application considers the shape optimization of super-cavitating hydrofoils of an ultrafast marine vessel for special naval operations. Specifically, we show how the combination of turbulent multi-phase flow simulations and the concept of multi-fidelity Bayesian optimization allows us to tackle complex engineering design problems in which a rigorous assessment of uncertainty and risk becomes critical in policy and decision making.