Sonny Astani Civil and Environmental Engineering Seminar
Thu, Mar 05, 2020
4:00 PM - 5:00 PM
Location: MCB 102
Speaker: Dr. Francesca Boso, Stanford University
Talk Title: Data and probabilistic forecasting in environmental applications
Abstract: Mathematical models expressing conservation of certain quantities (e.g. mass) are ubiquitous in the environmental sciences. A common challenge is often the lack of enough observations to inform these models, either because data collection is costly or impractical/impossible at the required level of spatial and temporal refinement. We propose a computational tool to treat the parametric uncertainty of these models, leveraging the inherent physical constraints, and combining them with data. Specifically, we quantify the impact of parametric uncertainty by deriving model-dependent deterministic equations for the probability distribution (Probability Density Function, PDF, or Cumulative Distribution Function, CDF) of the model solution. These equations can be derived in exact form for a class of nonlinear hyperbolic governing laws (e.g. advection-dominated transport in heterogeneous flows), whereas in general they require the development of ad-hoc closures. I will be presenting an overview of strategies to obtain workable PDF-CDF equations for specific conservation problems, and some recent work on how to combine them with available data to eventually reduce uncertainty.
Biography: Francesca is a senior research scientist in the Energy Resources Engineering Department at Stanford University, following her postdoc at the University of California, San Diego. She received her PhD in Environmental Engineering from the University of Trento, Italy, specializing in hydrology. She has been investigating uncertainty quantification for environmental applications.
Host: Dr. Felipe de Barros