Vladimir Druskin (WPI/SIAM): Network realizations of data-driven reduced order models and remote sen
Vladimir Druskin, Research Professor at Worcester Polytechnic Institute and Society for Industrial and Applied Mathematics Fellow, presents "Network realizations of data-driven reduced order models and remote sensing" at the MIT Earth Resources Laboratory.
"Network synthesis was at the base of modern electronics design and consecutively of model order reduction that tremendously impacted many areas of engineering by enabling efficient compression of the underlying dynamical systems. In his seminal 1950s works Mark Krein realized that in addition to their compressing properties, such networks can be used to embed the data back into the state space. The networks can learn the underlying PDE system from the data (transfer function) via rigorously chosen hyper-parameters. Among many application of this powerful approach we discuss the following two. 1. Our earlier work on construction of efficient 3D anisotropic Maxwell's solvers that recently became important in oil industry for geosteering applications. 2. Recent progress in radar imaging for multiple scattering environment."
Prof. Druskin graduated from Moscow Oil and Gas Academy with degree in geophysics in 1979 and received Ph.D. in applied math from Moscow State University in 1984. He worked at Central Geophysical Expedition of Russian Oil Ministry and then at Schlumberger-Doll Research. Vladimir recently moved to Worcester Polytechnic Institute (WPI) as a Research Professor. His research interests include efficient computational algorithms for forward and inverse problems, in particular, surface and borehole electromagnetic methods, and also for radar applications. Vladimir is SIAM fellow and has h=37 in Google Scholar.