Location
Innovation Lab Atrium
Start Date
4-3-2025 10:00 AM
End Date
4-3-2025 11:30 AM
Presentation Date
3 April 2025, 10:00am - 11:30am
Biography
Kolawole Arowoogun holds a master’s degree in geoscience with a concentration in geology from Georgia State University, Atlanta. He is currently a Ph.D. candidate in geological engineering at Missouri S&T. His research is focused on using geophysics, UAV remote sensing and machine learning techniques to enhance the understanding of levee failure along the Mississippi River.
Meeting Name
2025 - Miners Solving for Tomorrow Research Conference
Department(s)
Geosciences and Geological and Petroleum Engineering
Document Type
Poster
Document Version
Final Version
File Type
event
Language(s)
English
Rights
© 2025 The Authors, All rights reserved
Prediction of Undrained Shear Strength from Towed-TEM Resistivity Attributes using Machine Learning Techniques
Innovation Lab Atrium
Comments
Advisor: Katherine R. Grote
Abstract:
Undrained shear strength (Su) is an essential geotechnical parameter for levee foundation stability evaluation. However, traditional methods of estimating Su is invasive, and expensive. In this study, we present a machine learning (ML) based workflow for prediction of undrained shear strength from cost-effective resistivity data. We used three ML algorithms (support vector regression, random forest, and extreme gradient boosting) to predict Su from depth and resistivity attributes. To augment the training data, we generated 20,000 synthetic data using generative adversarial networks models. The results show that both depth and resistivity can be used to predict Su, with depth having more weight in the prediction but resistivity adding important information. Leveraging generative models to increase the number of training samples improved the overall prediction accuracy of the models. Improved predictions can better inform levee foundation models.