TL;DR
The results confirm the accuracy, interpretability, and computational efficiency of the integrated FEA-ML approach as an alternative to traditional bearing capacity analysis.
The proposed AFELA–machine learning framework provides a computationally efficient, reliable, and interpretable approach for tunnel stability assessment in sloping rock mass conditions.
This study investigates the pseudo-static bearing capacity of skirted strip footings on cohesionless slopes using finite-element limit analysis and data-driven prediction models. A total of 216 numerical simulations were performed by varying soil strength, slope angle, seismic coefficient, footing location and skirt depth. The results showed that the inclusion of vertical skirts significantly enhances footing performance under seismic loading. However, increasing the horizontal seismic coefficient from 0 to 0.4 caused a considerable reduction in bearing capacity. Artificial neural network (ANN) and random forest regression (RFR) models were developed using 70% of the data set for training and 30% for testing. Both models achieved high prediction accuracy with coefficient of determination (R2) values greater than 0.90. The ANN model outperformed the RFR model, achieving a maximum R2 value of 0.97. Sensitivity analysis indicated that skirt depth and width of the footing are the most influential parameter, contributing approximately 50.49% to the overall footing response. The proposed models provide a rapid and reliable approach for estimating the seismic bearing capacity of skirted foundations on sandy slopes.
This study presents a data-driven framework for predicting the shaft resistance ( β ) and end bearing capacity ( N t ) factors of piles using cone penetration test (CPT) data. Traditional design methods often rely on empirical values that oversimplify soil–pile interaction by neglecting the influence of pile geometry. To address this, this research employs an evolutionary polynomial regression with a multiobjective genetic algorithm (EPR-MOGA) to develop design equations. A two-step methodology was used: first, robust models for shaft capacity ( Q s ) and end-bearing capacity ( Q t ) of drilled piles were developed from databases of 54 and 31 load tests, respectively. Validated using fivefold cross-validation, these base models demonstrated high predictive accuracy, achieving an average coefficient of determination of 0.92 for Q s and 0.97 for Q t . Explicit equations for the β and N t factors were then derived from these validated models. These equations inherently account for complex soil–pile interactions, showing increases with soil friction angle and reductions with pile slenderness ratio ( L / D ) at a diminishing rate. This eliminates the need for the additional caps on effective vertical stress required by conventional methods. Finally, the models were extended to driven piles by calibrating modification factors on an independent 36-test database, yielding values of 1.46 for Q s and 2.38 for Q t .
