MS-31 Data-Driven Modelling and Machine Learning for Engineering Applications
N M Anoop Krishnan, Indian Institute of Technology Delhi
Mathieu Bauchy, University of California, Los Angeles
Machine learning has been attracting a lot of attention in recent years to solve complex engineering problems in various fields such as materials science, earthquake engineering, fracture, composites, to name a few. The goal of this symposium is to discuss recent advances in data-driven modeling and machine learning methodologies applied to research areas in civil, mechanical, materials science, and chemical engineering. Areas of interest include but are not limited to: materials by design, composite materials, granular materials, cementitious and glassy materials, energy materials, fracture and friction, earthquake engineering.
Topics of Interest Include:
- Machine learning based materials screening and selection
- Informatics approaches for micro-/meso-structure characterization
- Physics-driven machine learning
- Decoding mechanics from data-based models
- Developing constitutive and structure-property models from machine learning