Conference: Scientific Machine Learning: Theory, Algorithms, and Applications

The project supports the 2026 Scientific Machine Learning: Theory, Algorithms, and Applications Workshop at the University of Notre Dame. Scientific machine learning is an emerging area that brings together artificial intelligence, mathematics, scientific computing, and domain science to develop reliable data driven methods for modeling, simulation, prediction, and decision making in science and engineering. Progress in this area can accelerate scientific discovery, improve computational efficiency, and strengthen national capabilities in areas such as advanced manufacturing, energy systems, health technologies, and digital twin modeling. The workshop provides an accessible regional forum for researchers, students, postdoctoral scholars, and early career faculty to exchange ideas, build collaborations, and learn about recent advances in scientific machine learning. Particular emphasis is placed on broadening participation by supporting trainees, researchers from institutions with limited travel resources, and participants from groups historically underrepresented in mathematics and computational science. Through technical exchange, mentoring opportunities, and professional networking, the workshop contributes to the development of a diverse and highly skilled workforce at the intersection of artificial intelligence, mathematics, and scientific computing. The workshop takes place on September 26 and 27, 2026, at the University of Notre Dame and brings together researchers working on theoretical, computational, and application driven aspects of scientific machine learning. The program includes eighteen research presentations, two lightning talk sessions designed especially for students and early career researchers, and a panel discussion on undergraduate and graduate education in the age of artificial intelligence. Technical topics include operator learning and neural operators, learning augmented numerical methods, scientific foundation models, multiscale modeling, uncertainty quantification, inverse problems, physics informed learning, and mathematical analysis of approximation, stability, agentic AI working flow, and generalization. The workshop is designed to foster interaction among researchers from applied mathematics, statistics, computer science, engineering, and related scientific fields while promoting exchange between theory, algorithms, and real world applications. Support primarily enables participant travel and attendance, helping broaden access to scientific machine learning research and strengthening the regional research community in the Midwest and beyond. The conference website is: https://sciml26nd.github.io/index.html. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.