The Optimal ANN Model for Predicting Bearing Capacity of Shallow Foundations Trained on Scarce Data

TL;DR

This paper demonstrates that deep neural networks can accurately predict the bearing capacity of shallow foundations even with very limited training data, outperforming shallow networks in scarce data scenarios.

Contribution

It introduces an optimal DNN architecture for this prediction task and shows that fewer samples with high quality can be more effective than larger, noisier datasets.

Findings

DNNs outperform shallow networks with small datasets

Optimal DNN depth is between 5 to 7 layers

Training with only 6 samples yields high accuracy

Abstract

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.