Hybrid deep learning and isogeometric analysis for bearing capacity assessment of sand over clay

In this paper, Isogeometric analysis (IGA) is effectively integrated with machine learning (ML) to investigate the bearing capacity of strip footings in layered soil profiles, with a focus on a sand-over-clay configuration. The study begins with the generation of a comprehensive dataset of 10,000 samples from IGA upper bound (UB) limit analyses, facilitating an in-depth examination of various material and geometric conditions. A hybrid deep neural network, specifically the Whale Optimization Algorithm-Deep Neural Network (WOA-DNN), is then employed to utilize these 10,000 outputs for precise bearing capacity predictions. Notably, the WOA-DNN model outperforms conventional ML techniques, offering a robust and accurate prediction tool. This innovative approach explores a broad range of design parameters, including sand layer depth, load-to-soil unit weight ratio, internal friction angle, cohesion, and footing roughness. A detailed analysis of the dataset reveals the significant influence of these parameters on bearing capacity, providing valuable insights for practical foundation design. This research demonstrates the usefulness of data-driven techniques in optimizing the design of shallow foundations within layered soil profiles, marking a significant stride in geotechnical engineering advancements.