Augmenting Physics-based Models in ICME with Machine Learning & Uncertainty Quant.
Access all papers from this issue
here.
This topic is no longer accepting submissions.
Manuscript Submission Deadline:
August 01, 2020
Co-Guest Editors: David McDowell
Sponsored By: Other-Invited
Publication Date: January 2021
Keywords: Computational Materials Science & Engineering, Machine Learning, Uncertainty Quantification
Scope: This topic will include papers on modeling complex material behavior and failure characteristics at multiple scales, using ICME and physics-based simulation tools augmented by machine learning and uncertainty quantification. Machine learning, using datasets from experiments and validated simulation tools, can unravel novel material models and physical phenomena. It is necessary to couple these predictions with uncertainty quantification to understand levels of error and ways to mitigate uncertainty.