Prediction of Bearing Capacity of Skirted Strip Footing Along Unsupported Slope Using Back Propagation Neural Network Approach

Abstract In the past two decades, advancements in artificial intelligence have significantly benefited geotechnical research. Design engineers are primarily concerned with the bearing capacity of shallow foundations, which depends on factors like b/B, embedment depth (de), and ds/B. A back propagation artificial neural network was used to create a reliable model for predicting bearing capacity values under specific conditions. The model was validated with a mean absolute error (MAE) of 0.002697 mm/y. demonstrating its accuracy and reliability.