We are hiring a postdoctoral researcher at TU Delft to help us investigate how probabilistic programming can help us do better decision-making with coupled systems of digital twins.
Problem overview Arguably the most valuable tool one can create from Big Data is a digital twin that supports policymakers in understanding and interacting with various systems, ranging from industrial products to natural systems. Distilling twins of large-scale systems that consist of many interacting subsystems is, however, a major challenge. For example, a digital twin of a river estuary needs to combine different interacting subsystems (e.g., atmosphere, soil, groundwater, waterways, barriers, and coastal waters) and its overall success depends on the ability to couple the subsystems with each other and data. Unfortunately, naively coupling the existing subsystems into a ‘monster twin’ is computationally infeasible. Probabilistic programming may offer a way to avoid this by reducing the coupled system to its essence. Position overview The postdoctoral researcher will investigate the use of probabilistic programming to couple digital twins and simulators. Probabilistic programming has witnessed significant success in modelling and inverting scientific simulators. Your project will investigate how those techniques can be applied to problems when multiple simulators (digital twins) are present. More information: https://sebdumancic.github.io/team/
_______________________________________________ uai mailing list uai@engr.orst.edu https://it.engineering.oregonstate.edu/mailman/listinfo/uai
