The goal of the interdisciplinary seminar series Computation & Data at HSU is to bring together researchers and foster exchange on the development of algorithms, methods and software. The seminar series is typically scheduled for the last Wednesday every month, 16:00-17:00, with 1 presentation per hybrid session (digital and at HSU). Immediately after the seminar series, the HPC Café take place.
Feel free to subscribe the seminar newsletter by sending an e-mail to info-hpc-bw@hsu-hh.de with the subject line „Subscription Seminar Computation & Data”.
Intrinsic multiscale features in various physical systems stem from hierarchical structures that span a broad spectrum of temporal and spatial scales beyond the reach of any single simulation method, which have been recognized as significant challenges in multiscale engineering, especially for complex fluids and multifunctional materials. Recent advancements in deep learning, particularly in deep neural networks, have shown remarkable success in different scientific research fields.
In this talk, I will introduce two deep-learning-enabled strategies for addressing such challenges. First, I will introduce a deep neural operator learning approach for predicting multirate bubble growth dynamics across scales, bridging nanoscale mechanisms to macroscopic continuum behavior. Subsequently, I will describe a combined neural operator learning and physics-informed symbolic regression to discover interpretable mathematical models directly from computational data, demonstrated on the spreading dynamics of highly viscous liquids. Also, I will briefly introduce some of our ongoing efforts that extend neural operator learning to accelerate the design of composite materials and to optimize their manufacturing process.
