Inverse Methodologies and Machine Learning

SEM Inverse Methodologies and Machine Learning Technical Division

The Inverse Methodologies and Machine Learning Technical Division is soliciting papers on inverse methods in experimental mechanics, including using full-field measurements, and on machine-learning approaches applied to solid mechanics. This includes research in novel methods that include experimental and/or computational demonstration and new applications of existing approaches. Topics of particular interest include:

• Bayesian inference
• Material Testing 2.0 for calibration
• Machine-learned material modeling
• Virtual Fields Method
• Inverse Methods for Plasticity
• Inverse Methods for High Strain Rate Testing
• Physics-Informed Neural Networks for materials mechanics
• Data driven approaches