This is the authors' abstract. We don't add key points for this paper.
Accurately forecasting axial pile capacity remains a cornerstone challenge in geotechnical design because the empirical and semi-empirical equations that dominate practice often deviate widely from full scale load tests. To address this gap, we compiled a database of 546 instrumented load tests and adopted the Davisson Capacity as ground truth. Four mechanics-based traditional procedures ( FHWA, USACE, API, Revised Lambda ) were first applied to establish a realistic baseline, after which three machine learning (ML) models were trained on identical folds: support vector regression ( SVR ) as a base learner, extreme gradient boosting ( XGBoost ) as a boosted tree ensemble, and a multilayer perceptron ( MLP ). The MLP ’s depth, width, activation family, optimizer, learning rate schedule, batch size, dropout, L 1 /L 2 regularization, normalization strategy, kernel initializer, loss function, and gradient clipping threshold were exhaustively tuned with Optuna ’s Bayesian sampler under five-fold cross validation. Despite this intensive search, the optimized MLP could not produce a tangible improvement over XGBoost , while both MLP and XGBoost outperforming SVR and all four traditional methods.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Öztürk et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: