An Interpretable ML-based Model for Predicting p-y Curves of Monopile Foundations in Sand

TL;DR

This paper presents an interpretable machine learning model using XGBoost and SHAP to accurately predict p-y curves of monopile foundations in sand, aligning with theoretical understanding of pile-soil interactions.

Contribution

It introduces an interpretable ML model for p-y curve prediction, combining XGBoost with SHAP for enhanced accuracy and interpretability in pile foundation analysis.

Findings

The model achieves high predictive accuracy.

SHAP explanations align with theoretical knowledge.

The approach improves understanding of pile-soil interactions.

Abstract

Predicting the lateral pile response is challenging due to the complexity of pile-soil interactions. Machine learning (ML) techniques have gained considerable attention for their effectiveness in non-linear analysis and prediction. This study develops an interpretable ML-based model for predicting p-y curves of monopile foundations. An XGBoost model was trained using a database compiled from existing research. The results demonstrate that the model achieves superior predictive accuracy. Shapley Additive Explanations (SHAP) was employed to enhance interpretability. The SHAP value distributions for each variable demonstrate strong alignment with established theoretical knowledge on factors affecting the lateral response of pile foundations.