Usage of coot optimization-based random forests analysis for determining the shallow foundation settlement

Settlement estimation in cohesion materials is a crucial topic to tackle because of the complexity of the cohesion soil texture, which could be solved roughly by substituted solutions. The goal of this research was to implement recently developed machine learning features as effective methods to predict settlement (𝑆m) of shallow foundations over cohesion soil properties. These models include hybridized support vector regression (𝑆𝑉𝑅), random forests (𝑅𝐹), and coot optimization algorithm (𝐶𝑂𝑀), and black widow optimization algorithm (𝐵𝑊𝑂𝐴). The results indicate that all created systems accurately simulated the 𝑆𝑚, with an 𝑅2 of better than 0.979 and 0.9765 for the train and test data phases, respectively. This indicates extraordinary efficiency and a good correlation between the experimental and simulated 𝑆𝑚. The model's results outperformed those of 𝐴𝑁𝐹𝐼𝑆−𝑃𝑆𝑂, and 𝐶𝑂𝑀−𝑅𝐹 findings were much outstanding to those of the literature. By analyzing established designs utilizing different analysis aspects, such as various error criteria, Taylor diagrams, uncertainty analyses, and error distribution, it was feasible to arrive at the final result that the recommended 𝐶𝑂𝑀−𝑅𝐹 was the outperformed approach in the forecasting process of 𝑆m of shallow foundation, while other techniques were also reliable.