Join the Notre Dame Environmental Change Initiative for an in-person seminar by Toros Arikan, assistant professor in Electrical Engineering at the University of Notre Dame, as he presents on, "Proposed Deep Learning-Based Sensing of Dynamic Ocean Parameters."

Abstract: Underwater communication and localization are very challenging tasks due to attenuation and excessive reverberation, and also due to a time- and spatially-varying sound-speed profile that is controlled by temperature, salinity, and pressure (TSP). Accurate localization and mapping requires taking TSP into account, especially for defense applications where surreptitious, silent underwater targets are to be tracked. Additional challenges in underwater acoustics applications are spatiotemporally-varying reflective boundaries, such as layered seafloors or a choppy sea surface, that introduce errors due to domain mismatch in standard matched field processing (MFP) methods. Due to the difficulty of directly measuring these parameters over wide swaths of the ocean, tomographic methods are currently employed in a remote sensing framework; but these are subject to the same UWAC issues of poor performance under difficult environmental conditions. We have previously introduced a deep learning-based single-snapshot method for mapping out reflective features in the underwater acoustic environment; and since it outperforms the literature in this particular application, we propose to extend it for improved inference of ocean parameters. Beyond their immediate applications, these new methods point to a general strategy of solving a broad class of joint parameter estimation problems via deep learning.

Biography: Toros Arikan obtained his B.S. and M.S. degrees from the University of Illinois at Urbana-Champaign, with a focus on digital communications and signal processing; and his Ph.D. degree from the Massachusetts Institute of Technology in 2023, specializing in localization, tracking, and remote sensing. In 2023-25 he was a postdoctoral researcher at Rice University, where he researched deep learning methods for environment estimation, and robotic path planning algorithms for cluttered environments. He is currently a new assistant professor in EE at the University of Notre Dame, where he introduced Array Signal Processing as a graduate class, and is actively recruiting graduate students and postdoctoral candidates.

Lunch will be provided. Please RSVP if you plan to attend to help limit food waste.