IS014 - Machine Learning For Computational Mechanics Across Scales
Organized by: F. Aldakheel , E. Cueto , S. Sun , M. Bessa , Y. Heider , O. Weeger and D. Kochmann
Keywords: Scientific machine learning
This mini-symposium brings together researchers from mechanics, applied mathematics, and related engineering disciplines to explore the integration of machine learning into computational mechanics. The focus is on leveraging data-driven methods to enhance modeling, simulation, and design across a wide range of scales and physical phenomena.
Particular emphasis is placed on physics-based machine learning approaches that incorporate physical principles and constraints to improve consistency, interpretability, and generalization.
We welcome theoretical developments, algorithmic innovations, and application-oriented studies that utilize machine learning to advance understanding and computation in mechanics.
The goal is to foster interdisciplinary exchange and highlight cutting-edge advances that push the boundaries of computational mechanics through intelligent, physically grounded learning strategies.