• Alessandro Fascetti, University of Pittsburgh
• John Brigham, University of Pittsburgh
• Caglar Oskay, Vanderbilt University

Recent advancements in Machine Learning and Artificial Intelligence can be leveraged in the simulation of complex, large-scale Engineering Mechanics problems. In this context, particular interest lies in the development of new algorithms and methodologies that can efficiently couple the physical understanding of the mechanics of the problems and the computational efficiency granted by data-based approaches. In this mini-symposium, we will bring together experts in data-based computational approaches for the solution of engineering mechanics problems. Presentations will discuss the most recent advancements in Machine Learning-based approaches, and the links between them and traditional numerical and experimental investigations. Presentations are anticipated from academia, industry and governmental agencies, where big data approaches are gaining increasing popularity in the context of science-based decision making.
We are particularly interested in the following topics:
- data collection and manipulation
- data-based computational models for large-scale Engineering applications
- Interpretable Machine Learning for the solution of large-scale real-life problems
- physics-informed probabilistic methods
- probabilistic methods and uncertainty quantification
- experimental approaches at multiple scales for large databases acquisition
- real-time simulation and digital twin approaches
- field data measurements, cyber-physical infrastructure and IoT