Machine learning for prediction of undrained shear strength from cone penetration test data

Research output: Contribution to conferencePaperpeer-review

31 Downloads (Pure)

Abstract

This research focuses on investigating the relative performance of a range of machine learning algorithms, namely the artificial neural network, support vector machine, Gaussian process regression, random forest, and XGBoost, for predicting the undrained shear strength from cone penetration test data. This is to assess how machine learning could help us lower the need for laboratory test data. The training dataset compiles 526 data from 12 regions and the testing dataset consists of 20 data from a polder located close to Leiden in the Netherlands. In addition, k-fold and group k-fold cross-validation strategies are both applied to validate the models. The poor performance of the models during group k-fold cross-validation suggests that, while machine learning techniques can perform well when site-specific data are included during training, they struggle to generalize without site-specific data. This highlights the difficulty of capturing soil heterogeneity and suggests that either machine learning methods should be trained on specific sites for which some data are already available, or much larger training datasets are needed.
Original languageEnglish
Number of pages8
Publication statusPublished - 2023
Event14th International Conference on Applications of Statistics and Probability in Civil Engineering 2023 - Trinity College Dublin, Dublin, Ireland
Duration: 9 Jul 202313 Jul 2023
https://icasp14.com/

Conference

Conference14th International Conference on Applications of Statistics and Probability in Civil Engineering 2023
Abbreviated titleICASP14
Country/TerritoryIreland
CityDublin
Period9/07/2313/07/23
Internet address

Fingerprint

Dive into the research topics of 'Machine learning for prediction of undrained shear strength from cone penetration test data'. Together they form a unique fingerprint.

Cite this