Data-Driven Seminar: Oriol Lehmkuhl
Title: Towards high-performance strategies for the integration of traditional CFD and ML strategies
Abstract: The integration of machine learning (ML) with traditional computational fluid dynamics (CFD) is opening new directions for scalable, physics-aware simulation and control on modern high-performance computing platforms. Over the last three years, Dr. Lehmkuhl group efforts at BSC has focused on developing hybrid strategies that couple data-driven models with high-order CFD solvers to address challenges of accuracy, efficiency, and robustness in turbulent flow applications.
A central thread of this research is the design of hybrid reduced-order modeling approaches that combine classical POD-based representations with deep learning architectures. By embedding POD coordinates into nonlinear latent spaces and augmenting them with neural closures, we extend reduced models beyond linear dynamics while preserving physical interpretability. This effort is closely linked to a Koopman-inspired framework, where…
Event interval: Single day event. Campus room: Online Only. Accessibility Contact: llederer@uw.edu. Event Types: Academics. Lectures/Seminars.
Thursday, January 29, 2026, 9:00 AM – 10:00 AM.
For more info visit cassyni.com. Data-Driven Seminar: Johannes Brandstetter
Title: Large Engineering Models for instant design validation
Abstract: The multi-trillion high-tech industry heavily relies on simulations throughout their development cycles to model complex systems, optimize performance, and validate designs before costly and time intensive prototype fabrication. We are pioneering Large Engineering Model, which represent foundation models for specific engineering verticals (aerodynamics, crash testing, semiconductor design, injection moulding), capable of replacing the full numerical pipeline, and effectively consolidating the traditional, fragmented pipeline into a single interface that provides near-instantaneous feedback to the engineer. Picture a scenario where heat distribution and mechanical stresses are instantly visualized throughout a new semiconductor design!
Our main hypothesis is that fully data-driven approaches can parallelize across engineering verticals, with minimal structural intervention, because operational patterns such as geometry representation, mesh…
Event interval: Single day event. Campus room: Online Only. Accessibility Contact: llederer@uw.edu. Event Types: Academics. Lectures/Seminars.
Thursday, February 5, 2026, 11:30 AM – 12:30 PM.
For more info visit cassyni.com. Institute-wide Meeting
See internal calendar for Zoom link.
Event interval: Single day event. Accessibility Contact: llederer@uw.edu. Event Types: Meetings.
Monday, February 9, 2026, 12:00 PM – 1:00 PM.
Data-Driven Seminar: Chris Rackauckas
Title and abstract to be posted.
Event interval: Single day event. Campus location: Electrical and Computer Engineering Building (ECE). Campus room: ECE 125. Accessibility Contact: llederer@uw.edu. Event Types: Academics. Lectures/Seminars.
Thursday, February 12, 2026, 11:30 AM – 12:30 PM.
For more info visit cassyni.com. HOLIDAY | UW CLOSED
Event interval: Single day event. Accessibility Contact: N/A. Event Types: Not Specified.
Monday, February 16, 2026.
Data-Driven Seminar: Olga Fink
Title: Momentum-Conserving Physics-Informed Graph Neural Networks for Dynamical Systems
Abstract: Accurate and interpretable modeling of multi-body dynamical systems is a fundamental
challenge in domains ranging from robotics and aerospace to biophysics and materials science.
Traditional physics-based approaches are often computationally expensive and difficult to scale, while
purely data-driven methods like graph neural networks (GNNs) may lack physical consistency and
generalization. This talk presents Dynami-CAL GraphNet, a new physics-informed GNN framework
that explicitly integrates conservation laws, specifically, the pairwise conservation of linear and angular
momentum, into its architecture. By leveraging edge-local reference frames that are equivariant to
rotations and translations, our model produces physically consistent predictions and offers
interpretable insights into the forces and moments governing each interaction.
We demonstrate the effectiveness of Dynami-CAL GraphNet across a wide spectru…
Event interval: Single day event. Campus room: N/A. Accessibility Contact: llederer@uw.edu. Event Types: Academics. Lectures/Seminars.
Thursday, February 19, 2026, 9:00 AM – 10:00 AM.
For more info visit cassyni.com. Data-Driven Seminar: Bing Brunton
Title and abstract to be posted.
Event interval: Single day event. Campus location: Electrical and Computer Engineering Building (ECE). Campus room: 125. Accessibility Contact: llederer@uw.edu. Event Types: Academics. Lectures/Seminars.
Thursday, February 26, 2026, 11:30 AM – 12:30 PM.
For more info visit cassyni.com. Data-Driven Seminar | Oliver Schmidt
Title & abstract to be posted when available.
Event interval: Single day event. Accessibility Contact: llederer@uw.edu. Event Types: Lectures/Seminars. Academics.
Monday, March 2, 2026, 11:30 AM – 12:30 PM.
For more info visit cassyni.com. Thrust Lead Meeting
Calendar invites with a Zoom link will be sent to participants.
Event interval: Single day event. Campus room: N/A. Accessibility Contact: llederer@uw.edu. Event Types: Meetings.
Tuesday, March 10, 2026, 12:00 PM – 1:00 PM.
Data-Driven Seminar: Ricardo Vinuesa
Title: Explainable deep learning for control and foundation models for discovery and optimization
Abstract: In this seminar we discuss a unified framework that combines explainable deep learning, deep reinforcement learning (DRL) and foundation models to advance both understanding and control of turbulence, with direct implications for accelerated design and discovery. First, we will show how explainable deep learning techniques can be used to identify the flow features that are truly responsible for key turbulent processes in wall-bounded flows. By systematically interrogating trained neural networks, we uncover the most influential coherent structures driving momentum transport and drag. Our results reveal that classically studied structures (while important) provide only a partial and sometimes misleading perspective, motivating a more data-driven and physics-aware view of turbulence organization. Building on these insights, we will demonstrate how deep reinforcement learning can be used to actively contr…
Event interval: Single day event. Campus location: Electrical and Computer Engineering Building (ECE). Campus room: 125. Accessibility Contact: llederer@uw.edu. Event Types: Academics. Lectures/Seminars.
Thursday, March 19, 2026, 11:30 AM – 12:30 PM.
For more info visit cassyni.com. Institute-wide Meeting
See internal calendar for Zoom link.
Event interval: Single day event. Campus room: N/A. Accessibility Contact: llederer@uw.edu. Event Types: Meetings.
Tuesday, April 14, 2026, 12:00 PM – 1:00 PM.