The Optimal ANN Model for Predicting Bearing Capacity of Shallow Foundations Trained on Scarce Data
This work addresses the challenge of limited experimental data in geotechnical engineering, offering a practical approach for engineers to use small, high-quality datasets instead of large, error-prone ones, though it is incremental in applying existing DNN methods to a specific domain.
This study tackled the problem of predicting the ultimate bearing capacity of shallow foundations using deep neural networks (DNNs) with scarce training data, finding that DNNs outperform shallow networks with small datasets and that optimal performance occurs with 5 to 7 layers, achieving good accuracy even with only 6 samples.
This study is focused on determining the potential of using deep neural networks (DNNs) to predict the ultimate bearing capacity of shallow foundation in situations when the experimental data which may be used to train networks is scarce. Two experiments involving testing over 17000 networks were conducted. The first experiment was aimed at comparing the accuracy of shallow neural networks and DNNs predictions. It shows that when the experimental dataset used for preparing models is small then DNNs have a significant advantage over shallow networks. The second experiment was conducted to compare the performance of DNNs consisting of different number of neurons and layers. Obtained results indicate that the optimal number of layers varies between 5 to 7. Networks with less and - surprisingly - more layers obtain lower accuracy. Moreover, the number of neurons in DNN has a lower impact on the prediction accuracy than the number of DNN's layers. DNNs perform very well, even when trained with only 6 samples. Basing on the results it seems that when predicting the ultimate bearing capacity with ANN models obtaining small but high-quality experimental training datasets instead of large training datasets affected by a higher error is an advisable approach.