An interpretable AI framework using XGB-POA for micropile compressive stiffness prediction

Accurate calculation of the compressive stiffness of micropiles ([Formula: see text]) is essential for forecasting load-displacement behavior and maintaining foundation serviceability in geotechnical structures. Conventional analytical and numerical methods frequently oversimplify soil-structure interaction and require substantial calibration, thereby limiting their applicability across diverse ground conditions. This paper presents a data-driven predictive approach that combines supervised machine learning techniques with a field-based micropile ([Formula: see text]) test database to address these limitations. A comprehensive dataset of 393 in-situ MP compression experiments was compiled after statistical preprocessing, including normalization, randomization, and outlier elimination based on the interquartile range criterion. Nine geotechnical and geometric characteristics were utilized as predictors of [Formula: see text]. Five ensemble learning models-Gradient Boosting ([Formula: see text]), Light Gradient Boosting ([Formula: see text]), Histogram-based Gradient Boosting ([Formula: see text]), Extreme Gradient Boosting ([Formula: see text]), and Categorical Boosting ([Formula: see text])-were created and refined with the Parrot Optimization Algorithm ([Formula: see text]) for hyperparameter optimization. The [Formula: see text] algorithm demonstrated the greatest prediction reliability. Comparative analyses demonstrated that [Formula: see text] decreased prediction error by 10-22% compared to other boosting models while ensuring enhanced convergence stability. The proposed [Formula: see text]-optimized boosting framework offers a precise, interpretable, and computationally efficient method for calculating [Formula: see text] directly from field data. This hybrid modeling methodology reconciles empirical testing with predictive analytics, providing a pragmatic solution for performance-oriented [Formula: see text] design and foundation system optimization in geotechnical engineering.