Developing Machine Learning Models to Generate the Load-Settlement Curves of Piles from Cone Penetration Test Data
Document Type
Conference Proceeding
Publication Date
1-1-2025
Abstract
This paper explores the potential application of machine learning (ML) algorithms to evaluate the load-settlement curve of piles from cone penetration test (CPT) data. Several ML models, such as artificial neural network (ANN), random forest (RF), and gradient boosted tree (GBT), were developed using a database of 64 static pile load tests (PLTs) and corresponding CPT data. The load-settlement curves predicted using the developed ML models were compared with the measured curves from PLTs and those predicted using conventional load-transfer methods on the same test data. The results show that the ML models have great potential in predicting the load-settlement behavior of axially loaded single piles from CPT data that outperform the conventional load-transfer methods.
Publication Source (Journal or Book title)
Geotechnical Special Publication
First Page
104
Last Page
113
Recommended Citation
Abu-Farsakh, M., & Shoaib, M. (2025). Developing Machine Learning Models to Generate the Load-Settlement Curves of Piles from Cone Penetration Test Data. Geotechnical Special Publication, 2025-March (GSP 364), 104-113. https://doi.org/10.1061/9780784485972.011