On September 26-27, 2026, the University of Notre Dame hosted SciML@ND26, a two-day workshop on Scientific Machine Learning: heory, Algorithms, Applications, and Agentic AI Workflows, held in Jordan Hall of Science. This was the second workshop in the series, following the inaugural edition at Purdue University in 2025. The full program is available at sciml26nd.github.io.
The workshop drew more than 170 registered participants. The program featured 36 invited talks, organized into twelve thematic sessions across two parallel tracks, delivered by speakers from more than twenty universities, three national laboratories (Pacific Northwest, Sandia, and Los Alamos), research institutes, and industry. Topics spanned the mathematical foundations of machine learning; operator learning and learning-enhanced numerical methods for partial differential equations; digital twins and data-driven modeling of dynamical systems; uncertainty quantification and multi-fidelity methods; stochastic analysis and optimal transport; and the emerging use of AI agents and foundation models in scientific discovery.
Students and early-career researchers contributed 11 lightning talks and 34 posters, presented at a Saturday evening poster session and speakers' banquet. Many of the attendees and poster presenters were Notre Dame students and trainees, and their participation highlighted both the strong interest in machine learning and AI across campus and the breadth of research programs in these areas at Notre Dame.
The workshop was organized by Zecheng Zhang, Guosheng Fu, Daniele Schiavazzi, and Zhiliang Xu (University of Notre Dame), together with Guang Lin and Di Qi (Purdue University), and was supported by the National Science Foundation (Grant No. 2615564, Computational Mathematics Program). Additional support was generously provided by several units at the University of Notre Dame: the Scientific AI Initiative, the Data, AI, and Computing Initiative, the Colleges of Science and Engineering, Notre Dame Research, the Department of Applied and Computational Mathematics and Statistics, and the Graduate School.