Fundamental Study on Application of Artificial Neural Network Model to the Mixture Design of Soil Treated with Paper Sludge Ash-Based Stabilizer

Machine learning, especially artificial neural networks (ANNs), has been recently applied for complex events in geotechnical engineering. In this study, ANN models were applied for the mixture design of soils treated with paper sludge ash-based stabilizers (PSASs). The models were developed using data sources to determine the quantities of PSASs to be added to the soils to achieve the desired soil strength. To obtain the data sources for the modeling, a series of experiments were conducted in the laboratory. Then, machine learning models were built. The comparison between the predicted and measured soil strength indicated that the models could determine the quantities of PSASs to be added with high accuracy.