Aggregate piers represent an economical ground improvement technique used to increase bearing capacity and reduce settlements of weak soils. Several approaches have been developed to estimate the bearing capacity of aggregate pier–reinforced clay, but these models exhibit large prediction bias and uncertainty. This study uses newly developed footing loading test data to investigate the relationship between the bearing capacity and the area replacement and slenderness ratios. The bearing capacity of a single aggregate pier, whether isolated or in groups, below a loaded footing increases as the area replacement ratio decreases due to increase in extent of confined soil surrounding the pier. The length and diameter of an aggregate pier is also shown to result in significantly increased bearing capacity, an effect that diminishes with increasing slenderness. New modifications are proposed to existing simplified and cavity expansion models to account for the effect of confinement, area replacement ratio, and slenderness ratio using a leave-one-out cross-validation technique. The cross-validation analysis resulted in robust bearing capacity models that are more accurate than existing analytical models. Additionally, the stress concentration ratio for shallow foundations supported by aggregate pier–reinforced plastic soils at failure was estimated and compared with the available data, indicating its sensitivity to design variables and showing that this critical design parameter may be predicted using the updated models.

Aggregate piers have been widely used to increase bearing pressure and reduce settlement under structural footings. The ultimate bearing capacity of aggregate pier-reinforced ground is affected by the soil strength, replacement ratio of piles, and construction conditions. Various prediction models have been proposed to predict the ultimate bearing capacity. However, existing models have shown a broad range of bias, variation, and error, and they are at times unsuitable for practical design. In this study, multiple regression analysis was performed using field loading test results to predict the ultimate bearing capacity of ground reinforced by aggregate piers, and the number and type of the most efficient input variables were evaluated to build a robust predictive model. Accordingly, a multiple regression equation for predicting the ultimate bearing capacity was proposed, and a sensitivity analysis was conducted to identify the effect of input variables. In addition, a deep neural network was applied to estimate the ultimate bearing capacity. The optimal structure was selected on the basis of cross-validation results to prevent overtraining. Prediction errors for two approaches were evaluated and then compared with those of existing models.

No abstract

No abstract

No abstract